{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/speech-synthesis/papers/2","list_of":"/task/speech-synthesis","task":"Speech Synthesis","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":2,"pages_in_order":13,"rows_per_page":100,"rows":[101,200],"of":1249,"counts":{"archive_papers_tagged":1249,"with_a_code_link":366,"where_syntology_ran_a_sample":101,"not_listed_spam_title":0,"listed":1249,"listed_where_code_ran":101,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":85,"every_run_a_failure_of_syntologys_instrument":16,"listed_with_a_run_with_no_instrument_failure":85,"listed_every_run_a_failure_of_syntologys_instrument":16,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/speech-synthesis","prev":"/task/speech-synthesis","next":"/task/speech-synthesis/papers/3","papers":[{"url":"/paper/parallel-wavenet-fast-high-fidelity-speech","slug":"parallel-wavenet-fast-high-fidelity-speech","title":"Parallel WaveNet: Fast High-Fidelity Speech Synthesis","date":"2017-11-28","arxiv_id":"1711.10433","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/parallel-wavenet-fast-high-fidelity-speech#ran","syntology_url":"https://syntology.ai/paper/1711.10433","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.10433"}},"official":null}},{"url":"/paper/deepgesture-a-conversational-gesture","slug":"deepgesture-a-conversational-gesture","title":"DeepGesture: A conversational gesture synthesis system based on emotions and semantics","date":"2025-07-03","arxiv_id":"2507.03147","repositories_listed":1,"syntology":null},{"url":"/paper/rapflow-tts-rapid-and-high-fidelity-text-to","slug":"rapflow-tts-rapid-and-high-fidelity-text-to","title":"RapFlow-TTS: Rapid and High-Fidelity Text-to-Speech with Improved Consistency Flow Matching","date":"2025-06-20","arxiv_id":"2506.16741","repositories_listed":1,"syntology":null},{"url":"/paper/instructttseval-benchmarking-complex-natural","slug":"instructttseval-benchmarking-complex-natural","title":"InstructTTSEval: Benchmarking Complex Natural-Language Instruction Following in Text-to-Speech Systems","date":"2025-06-19","arxiv_id":"2506.16381","repositories_listed":1,"syntology":null},{"url":"/paper/pushing-the-performance-of-synthetic-speech","slug":"pushing-the-performance-of-synthetic-speech","title":"Pushing the Performance of Synthetic Speech Detection with Kolmogorov-Arnold Networks and Self-Supervised Learning Models","date":"2025-06-17","arxiv_id":"2506.14153","repositories_listed":1,"syntology":null},{"url":"/paper/zipvoice-fast-and-high-quality-zero-shot-text","slug":"zipvoice-fast-and-high-quality-zero-shot-text","title":"ZipVoice: Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching","date":"2025-06-16","arxiv_id":"2506.13053","repositories_listed":1,"syntology":null},{"url":"/paper/omnidrca-parallel-speech-text-foundation","slug":"omnidrca-parallel-speech-text-foundation","title":"OmniDRCA: Parallel Speech-Text Foundation Model via Dual-Resolution Speech Representations and Contrastive Alignment","date":"2025-06-11","arxiv_id":"2506.09349","repositories_listed":1,"syntology":null},{"url":"/paper/2506-08967","slug":"2506-08967","title":"Step-Audio-AQAA: a Fully End-to-End Expressive Large Audio Language Model","date":"2025-06-10","arxiv_id":"2506.08967","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/2506-08967#ran","syntology_url":"https://syntology.ai/paper/2506.08967","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.08967"}},"official":null}},{"url":"/paper/audio-jailbreak-an-open-comprehensive","slug":"audio-jailbreak-an-open-comprehensive","title":"Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models","date":"2025-05-21","arxiv_id":"2505.15406","repositories_listed":1,"syntology":null},{"url":"/paper/articulatory-feature-prediction-from-surface","slug":"articulatory-feature-prediction-from-surface","title":"Articulatory Feature Prediction from Surface EMG during Speech Production","date":"2025-05-20","arxiv_id":"2505.13814","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-speech-language-modeling-via-energy","slug":"efficient-speech-language-modeling-via-energy","title":"Efficient Speech Language Modeling via Energy Distance in Continuous Latent Space","date":"2025-05-19","arxiv_id":"2505.13181","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":3,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"phrase":"5 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/efficient-speech-language-modeling-via-energy#ran","syntology_url":"https://syntology.ai/paper/2505.13181","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.13181"}},"official":{"repos":["ictnlp/sled-tts"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/dialogueagents-a-hybrid-agent-based-speech","slug":"dialogueagents-a-hybrid-agent-based-speech","title":"DialogueAgents: A Hybrid Agent-Based Speech Synthesis Framework for Multi-Party Dialogue","date":"2025-04-20","arxiv_id":"2504.14482","repositories_listed":1,"syntology":null},{"url":"/paper/safespeech-robust-and-universal-voice","slug":"safespeech-robust-and-universal-voice","title":"SafeSpeech: Robust and Universal Voice Protection Against Malicious Speech Synthesis","date":"2025-04-14","arxiv_id":"2504.09839","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":3,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/safespeech-robust-and-universal-voice#ran","syntology_url":"https://syntology.ai/paper/2504.09839","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.09839"}},"official":{"repos":["wxzyd123/safespeech"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/speechdialoguefactory-generating-high-quality","slug":"speechdialoguefactory-generating-high-quality","title":"SpeechDialogueFactory: Generating High-Quality Speech Dialogue Data to Accelerate Your Speech-LLM Development","date":"2025-03-31","arxiv_id":"2503.23848","repositories_listed":1,"syntology":null},{"url":"/paper/wavefm-a-high-fidelity-and-efficient-vocoder","slug":"wavefm-a-high-fidelity-and-efficient-vocoder","title":"WaveFM: A High-Fidelity and Efficient Vocoder Based on Flow Matching","date":"2025-03-20","arxiv_id":"2503.16689","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/wavefm-a-high-fidelity-and-efficient-vocoder#ran","syntology_url":"https://syntology.ai/paper/2503.16689","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.16689"}},"official":{"repos":["luotianze666/wavefm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/mooncast-high-quality-zero-shot-podcast","slug":"mooncast-high-quality-zero-shot-podcast","title":"MoonCast: High-Quality Zero-Shot Podcast Generation","date":"2025-03-18","arxiv_id":"2503.14345","repositories_listed":1,"syntology":null},{"url":"/paper/divise-direct-visual-input-speech-synthesis","slug":"divise-direct-visual-input-speech-synthesis","title":"DiVISe: Direct Visual-Input Speech Synthesis Preserving Speaker Characteristics And Intelligibility","date":"2025-03-07","arxiv_id":"2503.05223","repositories_listed":1,"syntology":null},{"url":"/paper/2503-00455","slug":"2503-00455","title":"PodAgent: A Comprehensive Framework for Podcast Generation","date":"2025-03-01","arxiv_id":"2503.00455","repositories_listed":1,"syntology":null},{"url":"/paper/llasa-scaling-train-time-and-inference-time","slug":"llasa-scaling-train-time-and-inference-time","title":"Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesis","date":"2025-02-06","arxiv_id":"2502.04128","repositories_listed":1,"syntology":null},{"url":"/paper/developing-multilingual-speech-synthesis","slug":"developing-multilingual-speech-synthesis","title":"Developing multilingual speech synthesis system for Ojibwe, Mi'kmaq, and Maliseet","date":"2025-02-04","arxiv_id":"2502.02703","repositories_listed":1,"syntology":null},{"url":"/paper/retrieval-augmented-dialogue-knowledge","slug":"retrieval-augmented-dialogue-knowledge","title":"Retrieval-Augmented Dialogue Knowledge Aggregation for Expressive Conversational Speech Synthesis","date":"2025-01-11","arxiv_id":"2501.06467","repositories_listed":1,"syntology":null},{"url":"/paper/ancogen-analysis-control-and-generation-of","slug":"ancogen-analysis-control-and-generation-of","title":"AnCoGen: Analysis, Control and Generation of Speech with a Masked Autoencoder","date":"2025-01-09","arxiv_id":"2501.05332","repositories_listed":1,"syntology":null},{"url":"/paper/openomni-large-language-models-pivot-zero","slug":"openomni-large-language-models-pivot-zero","title":"OpenOmni: Large Language Models Pivot Zero-shot Omnimodal Alignment across Language with Real-time Self-Aware Emotional Speech Synthesis","date":"2025-01-08","arxiv_id":"2501.04561","repositories_listed":1,"syntology":null},{"url":"/paper/region-based-optimization-in-continual","slug":"region-based-optimization-in-continual","title":"Region-Based Optimization in Continual Learning for Audio Deepfake Detection","date":"2024-12-16","arxiv_id":"2412.11551","repositories_listed":1,"syntology":null},{"url":"/paper/cosyvoice-2-scalable-streaming-speech","slug":"cosyvoice-2-scalable-streaming-speech","title":"CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models","date":"2024-12-13","arxiv_id":"2412.10117","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-latent-language-modeling-with-next","slug":"multimodal-latent-language-modeling-with-next","title":"Multimodal Latent Language Modeling with Next-Token Diffusion","date":"2024-12-11","arxiv_id":"2412.08635","repositories_listed":1,"syntology":null},{"url":"/paper/towards-controllable-speech-synthesis-in-the","slug":"towards-controllable-speech-synthesis-in-the","title":"Towards Controllable Speech Synthesis in the Era of Large Language Models: A Survey","date":"2024-12-09","arxiv_id":"2412.06602","repositories_listed":1,"syntology":null},{"url":"/paper/smoothcache-a-universal-inference","slug":"smoothcache-a-universal-inference","title":"SmoothCache: A Universal Inference Acceleration Technique for Diffusion Transformers","date":"2024-11-15","arxiv_id":"2411.10510","repositories_listed":1,"syntology":null},{"url":"/paper/lina-speech-gated-linear-attention-is-a-fast","slug":"lina-speech-gated-linear-attention-is-a-fast","title":"Lina-Speech: Gated Linear Attention is a Fast and Parameter-Efficient Learner for text-to-speech synthesis","date":"2024-10-30","arxiv_id":"2410.23320","repositories_listed":1,"syntology":null},{"url":"/paper/mitigating-unauthorized-speech-synthesis-for","slug":"mitigating-unauthorized-speech-synthesis-for","title":"Mitigating Unauthorized Speech Synthesis for Voice Protection","date":"2024-10-28","arxiv_id":"2410.20742","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":4,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mitigating-unauthorized-speech-synthesis-for#ran","syntology_url":"https://syntology.ai/paper/2410.20742","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.20742"}},"official":{"repos":["wxzyd123/pivotal_objective_perturbation"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/sttatts-unified-speech-to-text-and-text-to","slug":"sttatts-unified-speech-to-text-and-text-to","title":"STTATTS: Unified Speech-To-Text And Text-To-Speech Model","date":"2024-10-24","arxiv_id":"2410.18607","repositories_listed":1,"syntology":null},{"url":"/paper/emoknob-enhance-voice-cloning-with-fine","slug":"emoknob-enhance-voice-cloning-with-fine","title":"EmoKnob: Enhance Voice Cloning with Fine-Grained Emotion Control","date":"2024-10-01","arxiv_id":"2410.00316","repositories_listed":1,"syntology":null},{"url":"/paper/audio-codec-augmentation-for-robust","slug":"audio-codec-augmentation-for-robust","title":"Audio Codec Augmentation for Robust Collaborative Watermarking of Speech Synthesis","date":"2024-09-20","arxiv_id":"2409.13382","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/audio-codec-augmentation-for-robust#ran","syntology_url":"https://syntology.ai/paper/2409.13382","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.13382"}},"official":{"repos":["ljuvela/collaborative-watermarking-with-codecs"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/ssr-speech-towards-stable-safe-and-robust","slug":"ssr-speech-towards-stable-safe-and-robust","title":"SSR-Speech: Towards Stable, Safe and Robust Zero-shot Text-based Speech Editing and Synthesis","date":"2024-09-11","arxiv_id":"2409.07556","repositories_listed":1,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ssr-speech-towards-stable-safe-and-robust#ran","syntology_url":"https://syntology.ai/paper/2409.07556","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.07556"}},"official":{"repos":["WangHelin1997/SSR-Speech"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/sample-efficient-diffusion-for-text-to-speech","slug":"sample-efficient-diffusion-for-text-to-speech","title":"Sample-Efficient Diffusion for Text-To-Speech Synthesis","date":"2024-09-01","arxiv_id":"2409.03717","repositories_listed":1,"syntology":null},{"url":"/paper/codec-does-matter-exploring-the-semantic","slug":"codec-does-matter-exploring-the-semantic","title":"Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model","date":"2024-08-30","arxiv_id":"2408.17175","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/codec-does-matter-exploring-the-semantic#ran","syntology_url":"https://syntology.ai/paper/2408.17175","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.17175"}},"official":{"repos":["zhenye234/xcodec"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/mini-omni-language-models-can-hear-talk-while","slug":"mini-omni-language-models-can-hear-talk-while","title":"Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming","date":"2024-08-29","arxiv_id":"2408.16725","repositories_listed":1,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":2,"n_no_contract":9,"n_pointer_only":1,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 2 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/mini-omni-language-models-can-hear-talk-while#ran","syntology_url":"https://syntology.ai/paper/2408.16725","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.16725"}},"official":{"repos":["gpt-omni/mini-omni"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/speechcraft-a-fine-grained-expressive-speech","slug":"speechcraft-a-fine-grained-expressive-speech","title":"SpeechCraft: A Fine-grained Expressive Speech Dataset with Natural Language Description","date":"2024-08-24","arxiv_id":"2408.13608","repositories_listed":1,"syntology":null},{"url":"/paper/generating-data-with-text-to-speech-and-large","slug":"generating-data-with-text-to-speech-and-large","title":"Generating Data with Text-to-Speech and Large-Language Models for Conversational Speech Recognition","date":"2024-08-17","arxiv_id":"2408.09215","repositories_listed":1,"syntology":null},{"url":"/paper/accelerating-high-fidelity-waveform","slug":"accelerating-high-fidelity-waveform","title":"Accelerating High-Fidelity Waveform Generation via Adversarial Flow Matching Optimization","date":"2024-08-15","arxiv_id":"2408.08019","repositories_listed":1,"syntology":null},{"url":"/paper/periodwave-multi-period-flow-matching-for","slug":"periodwave-multi-period-flow-matching-for","title":"PeriodWave: Multi-Period Flow Matching for High-Fidelity Waveform Generation","date":"2024-08-14","arxiv_id":"2408.07547","repositories_listed":1,"syntology":null},{"url":"/paper/present-zero-shot-text-to-prosody-control","slug":"present-zero-shot-text-to-prosody-control","title":"PRESENT: Zero-Shot Text-to-Prosody Control","date":"2024-08-13","arxiv_id":"2408.06827","repositories_listed":1,"syntology":null},{"url":"/paper/saslaw-dialogue-speech-corpus-with-audio","slug":"saslaw-dialogue-speech-corpus-with-audio","title":"SaSLaW: Dialogue Speech Corpus with Audio-visual Egocentric Information Toward Environment-adaptive Dialogue Speech Synthesis","date":"2024-08-13","arxiv_id":"2408.06858","repositories_listed":1,"syntology":null},{"url":"/paper/2407-21491","slug":"2407-21491","title":"Generative Expressive Conversational Speech Synthesis","date":"2024-07-31","arxiv_id":"2407.21491","repositories_listed":1,"syntology":null},{"url":"/paper/voxsim-a-perceptual-voice-similarity-dataset","slug":"voxsim-a-perceptual-voice-similarity-dataset","title":"VoxSim: A perceptual voice similarity dataset","date":"2024-07-26","arxiv_id":"2407.18505","repositories_listed":1,"syntology":{"n":14,"n_ran":13,"n_constructed":0,"n_ran_checked":10,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":9,"n_pointer_only":14,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/voxsim-a-perceptual-voice-similarity-dataset#ran","syntology_url":"https://syntology.ai/paper/2407.18505","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.18505"}},"official":{"repos":["kaistmm/voxsim_trainer"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/dmel-speech-tokenization-made-simple","slug":"dmel-speech-tokenization-made-simple","title":"dMel: Speech Tokenization made Simple","date":"2024-07-22","arxiv_id":"2407.15835","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/dmel-speech-tokenization-made-simple#ran","syntology_url":"https://syntology.ai/paper/2407.15835","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.15835"}},"official":{"repos":["apple/dmel"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/rasa-building-expressive-speech-synthesis","slug":"rasa-building-expressive-speech-synthesis","title":"Rasa: Building Expressive Speech Synthesis Systems for Indian Languages in Low-resource Settings","date":"2024-07-19","arxiv_id":"2407.14056","repositories_listed":1,"syntology":null},{"url":"/paper/cosyvoice-a-scalable-multilingual-zero-shot","slug":"cosyvoice-a-scalable-multilingual-zero-shot","title":"CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens","date":"2024-07-07","arxiv_id":"2407.05407","repositories_listed":1,"syntology":null},{"url":"/paper/fine-grained-and-interpretable-neural-speech","slug":"fine-grained-and-interpretable-neural-speech","title":"Fine-Grained and Interpretable Neural Speech Editing","date":"2024-07-07","arxiv_id":"2407.05471","repositories_listed":1,"syntology":null},{"url":"/paper/probing-the-feasibility-of-multilingual","slug":"probing-the-feasibility-of-multilingual","title":"Probing the Feasibility of Multilingual Speaker Anonymization","date":"2024-07-03","arxiv_id":"2407.02937","repositories_listed":1,"syntology":null},{"url":"/paper/dex-tts-diffusion-based-expressive-text-to","slug":"dex-tts-diffusion-based-expressive-text-to","title":"DEX-TTS: Diffusion-based EXpressive Text-to-Speech with Style Modeling on Time Variability","date":"2024-06-27","arxiv_id":"2406.19135","repositories_listed":1,"syntology":null},{"url":"/paper/one-class-learning-with-adaptive-centroid","slug":"one-class-learning-with-adaptive-centroid","title":"One-Class Learning with Adaptive Centroid Shift for Audio Deepfake Detection","date":"2024-06-24","arxiv_id":"2406.16716","repositories_listed":1,"syntology":null},{"url":"/paper/articulatory-phonetics-informed-controllable","slug":"articulatory-phonetics-informed-controllable","title":"Articulatory Phonetics Informed Controllable Expressive Speech Synthesis","date":"2024-06-15","arxiv_id":"2406.10514","repositories_listed":1,"syntology":null},{"url":"/paper/meta-learning-text-to-speech-synthesis-in","slug":"meta-learning-text-to-speech-synthesis-in","title":"Meta Learning Text-to-Speech Synthesis in over 7000 Languages","date":"2024-06-10","arxiv_id":"2406.06403","repositories_listed":1,"syntology":null},{"url":"/paper/small-e-small-language-model-with-linear","slug":"small-e-small-language-model-with-linear","title":"Small-E: Small Language Model with Linear Attention for Efficient Speech Synthesis","date":"2024-06-06","arxiv_id":"2406.04467","repositories_listed":1,"syntology":null},{"url":"/paper/streamspeech-simultaneous-speech-to-speech","slug":"streamspeech-simultaneous-speech-to-speech","title":"StreamSpeech: Simultaneous Speech-to-Speech Translation with Multi-task Learning","date":"2024-06-05","arxiv_id":"2406.03049","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/streamspeech-simultaneous-speech-to-speech#ran","syntology_url":"https://syntology.ai/paper/2406.03049","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.03049"}},"official":{"repos":["ictnlp/streamspeech"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/controlspeech-towards-simultaneous-zero-shot","slug":"controlspeech-towards-simultaneous-zero-shot","title":"ControlSpeech: Towards Simultaneous and Independent Zero-shot Speaker Cloning and Zero-shot Language Style Control","date":"2024-06-03","arxiv_id":"2406.01205","repositories_listed":1,"syntology":null},{"url":"/paper/mm-tts-a-unified-framework-for-multimodal","slug":"mm-tts-a-unified-framework-for-multimodal","title":"UMETTS: A Unified Framework for Emotional Text-to-Speech Synthesis with Multimodal Prompts","date":"2024-04-29","arxiv_id":"2404.18398","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/mm-tts-a-unified-framework-for-multimodal#ran","syntology_url":"https://syntology.ai/paper/2404.18398","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.18398"}},"official":{"repos":["kttrcdl/umetts"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/flashspeech-efficient-zero-shot-speech","slug":"flashspeech-efficient-zero-shot-speech","title":"FlashSpeech: Efficient Zero-Shot Speech Synthesis","date":"2024-04-23","arxiv_id":"2404.14700","repositories_listed":1,"syntology":null},{"url":"/paper/llama-vits-enhancing-tts-synthesis-with","slug":"llama-vits-enhancing-tts-synthesis-with","title":"Llama-VITS: Enhancing TTS Synthesis with Semantic Awareness","date":"2024-04-10","arxiv_id":"2404.06714","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/llama-vits-enhancing-tts-synthesis-with#ran","syntology_url":"https://syntology.ai/paper/2404.06714","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.06714"}},"official":{"repos":["xincanfeng/vitsgpt"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/hypertts-parameter-efficient-adaptation-in","slug":"hypertts-parameter-efficient-adaptation-in","title":"HyperTTS: Parameter Efficient Adaptation in Text to Speech using Hypernetworks","date":"2024-04-06","arxiv_id":"2404.04645","repositories_listed":1,"syntology":null},{"url":"/paper/kazemotts-a-dataset-for-kazakh-emotional-text","slug":"kazemotts-a-dataset-for-kazakh-emotional-text","title":"KazEmoTTS: A Dataset for Kazakh Emotional Text-to-Speech Synthesis","date":"2024-04-01","arxiv_id":"2404.01033","repositories_listed":1,"syntology":null},{"url":"/paper/cm-tts-enhancing-real-time-text-to-speech","slug":"cm-tts-enhancing-real-time-text-to-speech","title":"CM-TTS: Enhancing Real Time Text-to-Speech Synthesis Efficiency through Weighted Samplers and Consistency Models","date":"2024-03-31","arxiv_id":"2404.00569","repositories_listed":1,"syntology":null},{"url":"/paper/humane-speech-synthesis-through-zero-shot","slug":"humane-speech-synthesis-through-zero-shot","title":"Humane Speech Synthesis through Zero-Shot Emotion and Disfluency Generation","date":"2024-03-31","arxiv_id":"2404.01339","repositories_listed":1,"syntology":null},{"url":"/paper/rfwave-multi-band-rectified-flow-for-audio","slug":"rfwave-multi-band-rectified-flow-for-audio","title":"RFWave: Multi-band Rectified Flow for Audio Waveform Reconstruction","date":"2024-03-08","arxiv_id":"2403.05010","repositories_listed":1,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/rfwave-multi-band-rectified-flow-for-audio#ran","syntology_url":"https://syntology.ai/paper/2403.05010","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.05010"}},"official":{"repos":["bfs18/rfwave"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/naturalspeech-3-zero-shot-speech-synthesis","slug":"naturalspeech-3-zero-shot-speech-synthesis","title":"NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models","date":"2024-03-05","arxiv_id":"2403.03100","repositories_listed":1,"syntology":null},{"url":"/paper/towards-decoding-brain-activity-during","slug":"towards-decoding-brain-activity-during","title":"Towards Decoding Brain Activity During Passive Listening of Speech","date":"2024-02-26","arxiv_id":"2402.16996","repositories_listed":1,"syntology":null},{"url":"/paper/bayesian-parameter-efficient-fine-tuning-for","slug":"bayesian-parameter-efficient-fine-tuning-for","title":"Bayesian Parameter-Efficient Fine-Tuning for Overcoming Catastrophic Forgetting","date":"2024-02-19","arxiv_id":"2402.12220","repositories_listed":1,"syntology":null},{"url":"/paper/eva-gan-enhanced-various-audio-generation-via","slug":"eva-gan-enhanced-various-audio-generation-via","title":"EVA-GAN: Enhanced Various Audio Generation via Scalable Generative Adversarial Networks","date":"2024-01-31","arxiv_id":"2402.00892","repositories_listed":1,"syntology":null},{"url":"/paper/emotion-rendering-for-conversational-speech","slug":"emotion-rendering-for-conversational-speech","title":"Emotion Rendering for Conversational Speech Synthesis with Heterogeneous Graph-Based Context Modeling","date":"2023-12-19","arxiv_id":"2312.11947","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/emotion-rendering-for-conversational-speech#ran","syntology_url":"https://syntology.ai/paper/2312.11947","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.11947"}},"official":{"repos":["walker-hyf/ecss"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/what-to-remember-self-adaptive-continual","slug":"what-to-remember-self-adaptive-continual","title":"What to Remember: Self-Adaptive Continual Learning for Audio Deepfake Detection","date":"2023-12-15","arxiv_id":"2312.09651","repositories_listed":1,"syntology":null},{"url":"/paper/neural-text-to-articulate-talk-deep-text-to","slug":"neural-text-to-articulate-talk-deep-text-to","title":"Neural Text to Articulate Talk: Deep Text to Audiovisual Speech Synthesis achieving both Auditory and Photo-realism","date":"2023-12-11","arxiv_id":"2312.06613","repositories_listed":1,"syntology":null},{"url":"/paper/learning-arousal-valence-representation-from","slug":"learning-arousal-valence-representation-from","title":"Learning Arousal-Valence Representation from Categorical Emotion Labels of Speech","date":"2023-11-24","arxiv_id":"2311.14816","repositories_listed":1,"syntology":null},{"url":"/paper/apnet2-high-quality-and-high-efficiency","slug":"apnet2-high-quality-and-high-efficiency","title":"APNet2: High-quality and High-efficiency Neural Vocoder with Direct Prediction of Amplitude and Phase Spectra","date":"2023-11-20","arxiv_id":"2311.11545","repositories_listed":1,"syntology":null},{"url":"/paper/chatgpt-in-the-context-of-precision","slug":"chatgpt-in-the-context-of-precision","title":"ChatGPT in the context of precision agriculture data analytics","date":"2023-11-10","arxiv_id":"2311.06390","repositories_listed":1,"syntology":null},{"url":"/paper/improved-child-text-to-speech-synthesis","slug":"improved-child-text-to-speech-synthesis","title":"Improved Child Text-to-Speech Synthesis through Fastpitch-based Transfer Learning","date":"2023-11-07","arxiv_id":"2311.04313","repositories_listed":1,"syntology":null},{"url":"/paper/artst-arabic-text-and-speech-transformer","slug":"artst-arabic-text-and-speech-transformer","title":"ArTST: Arabic Text and Speech Transformer","date":"2023-10-25","arxiv_id":"2310.16621","repositories_listed":1,"syntology":null},{"url":"/paper/autodiff-combining-auto-encoder-and-diffusion","slug":"autodiff-combining-auto-encoder-and-diffusion","title":"AutoDiff: combining Auto-encoder and Diffusion model for tabular data synthesizing","date":"2023-10-24","arxiv_id":"2310.15479","repositories_listed":1,"syntology":null},{"url":"/paper/attentive-multi-layer-perceptron-for-non","slug":"attentive-multi-layer-perceptron-for-non","title":"Attentive Multi-Layer Perceptron for Non-autoregressive Generation","date":"2023-10-14","arxiv_id":"2310.09512","repositories_listed":1,"syntology":null},{"url":"/paper/generative-adversarial-training-for-text-to","slug":"generative-adversarial-training-for-text-to","title":"Generative Adversarial Training for Text-to-Speech Synthesis Based on Raw Phonetic Input and Explicit Prosody Modelling","date":"2023-10-14","arxiv_id":"2310.09636","repositories_listed":1,"syntology":null},{"url":"/paper/partial-rank-similarity-minimization-method","slug":"partial-rank-similarity-minimization-method","title":"Partial Rank Similarity Minimization Method for Quality MOS Prediction of Unseen Speech Synthesis Systems in Zero-Shot and Semi-supervised setting","date":"2023-10-08","arxiv_id":"2310.05078","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-speech-synthesis-by-training","slug":"evaluating-speech-synthesis-by-training","title":"Evaluating Speech Synthesis by Training Recognizers on Synthetic Speech","date":"2023-10-01","arxiv_id":"2310.00706","repositories_listed":1,"syntology":null},{"url":"/paper/p-flow-a-fast-and-data-efficient-zero-shot","slug":"p-flow-a-fast-and-data-efficient-zero-shot","title":"P-Flow: A Fast and Data-Efficient Zero-Shot TTS through Speech Prompting","date":"2023-09-22","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/towards-joint-modeling-of-dialogue-response","slug":"towards-joint-modeling-of-dialogue-response","title":"Towards Joint Modeling of Dialogue Response and Speech Synthesis based on Large Language Model","date":"2023-09-20","arxiv_id":"2309.11000","repositories_listed":1,"syntology":null},{"url":"/paper/hiftnet-a-fast-high-quality-neural-vocoder","slug":"hiftnet-a-fast-high-quality-neural-vocoder","title":"HiFTNet: A Fast High-Quality Neural Vocoder with Harmonic-plus-Noise Filter and Inverse Short Time Fourier Transform","date":"2023-09-18","arxiv_id":"2309.09493","repositories_listed":1,"syntology":null},{"url":"/paper/funcodec-a-fundamental-reproducible-and","slug":"funcodec-a-fundamental-reproducible-and","title":"FunCodec: A Fundamental, Reproducible and Integrable Open-source Toolkit for Neural Speech Codec","date":"2023-09-14","arxiv_id":"2309.07405","repositories_listed":1,"syntology":null},{"url":"/paper/towards-universal-speech-discrete-tokens-a","slug":"towards-universal-speech-discrete-tokens-a","title":"Towards Universal Speech Discrete Tokens: A Case Study for ASR and TTS","date":"2023-09-14","arxiv_id":"2309.07377","repositories_listed":1,"syntology":null},{"url":"/paper/can-large-scale-vocoded-spoofed-data-improve","slug":"can-large-scale-vocoded-spoofed-data-improve","title":"Can large-scale vocoded spoofed data improve speech spoofing countermeasure with a self-supervised front end?","date":"2023-09-12","arxiv_id":"2309.06014","repositories_listed":1,"syntology":null},{"url":"/paper/matcha-tts-a-fast-tts-architecture-with","slug":"matcha-tts-a-fast-tts-architecture-with","title":"Matcha-TTS: A fast TTS architecture with conditional flow matching","date":"2023-09-06","arxiv_id":"2309.03199","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/matcha-tts-a-fast-tts-architecture-with#ran","syntology_url":"https://syntology.ai/paper/2309.03199","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.03199"}},"official":{"repos":["shivammehta25/Matcha-TTS"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/qs-tts-towards-semi-supervised-text-to-speech","slug":"qs-tts-towards-semi-supervised-text-to-speech","title":"QS-TTS: Towards Semi-Supervised Text-to-Speech Synthesis via Vector-Quantized Self-Supervised Speech Representation Learning","date":"2023-08-31","arxiv_id":"2309.00126","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-training-of-denoising-diffusion","slug":"adversarial-training-of-denoising-diffusion","title":"Adversarial Training of Denoising Diffusion Model Using Dual Discriminators for High-Fidelity Multi-Speaker TTS","date":"2023-08-03","arxiv_id":"2308.01573","repositories_listed":1,"syntology":null},{"url":"/paper/many-to-many-spoken-language-translation-via","slug":"many-to-many-spoken-language-translation-via","title":"Textless Unit-to-Unit training for Many-to-Many Multilingual Speech-to-Speech Translation","date":"2023-08-03","arxiv_id":"2308.01831","repositories_listed":1,"syntology":null},{"url":"/paper/diffprosody-diffusion-based-latent-prosody","slug":"diffprosody-diffusion-based-latent-prosody","title":"DiffProsody: Diffusion-based Latent Prosody Generation for Expressive Speech Synthesis with Prosody Conditional Adversarial Training","date":"2023-07-31","arxiv_id":"2307.16549","repositories_listed":1,"syntology":null},{"url":"/paper/sc-vall-e-style-controllable-zero-shot-text","slug":"sc-vall-e-style-controllable-zero-shot-text","title":"SC VALL-E: Style-Controllable Zero-Shot Text to Speech Synthesizer","date":"2023-07-20","arxiv_id":"2307.10550","repositories_listed":1,"syntology":null},{"url":"/paper/deep-speech-synthesis-from-mri-based","slug":"deep-speech-synthesis-from-mri-based","title":"Deep Speech Synthesis from MRI-Based Articulatory Representations","date":"2023-07-05","arxiv_id":"2307.02471","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/deep-speech-synthesis-from-mri-based#ran","syntology_url":"https://syntology.ai/paper/2307.02471","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.02471"}},"official":{"repos":["articulatory/articulatory"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/disentanglement-in-a-gan-for-unconditional","slug":"disentanglement-in-a-gan-for-unconditional","title":"Disentanglement in a GAN for Unconditional Speech Synthesis","date":"2023-07-04","arxiv_id":"2307.01673","repositories_listed":1,"syntology":null},{"url":"/paper/emospeech-guiding-fastspeech2-towards","slug":"emospeech-guiding-fastspeech2-towards","title":"EmoSpeech: Guiding FastSpeech2 Towards Emotional Text to Speech","date":"2023-06-28","arxiv_id":"2307.00024","repositories_listed":1,"syntology":null},{"url":"/paper/voicebox-text-guided-multilingual-universal","slug":"voicebox-text-guided-multilingual-universal","title":"Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale","date":"2023-06-23","arxiv_id":"2306.15687","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":0,"n_honours":3,"n_violates":3,"n_no_contract":3,"n_pointer_only":3,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 3 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/voicebox-text-guided-multilingual-universal#ran","syntology_url":"https://syntology.ai/paper/2306.15687","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.15687"}},"official":null}},{"url":"/paper/styletts-2-towards-human-level-text-to-speech","slug":"styletts-2-towards-human-level-text-to-speech","title":"StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models","date":"2023-06-13","arxiv_id":"2306.07691","repositories_listed":1,"syntology":{"n":4,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 4 unverified","sample_list":"/paper/styletts-2-towards-human-level-text-to-speech#ran","syntology_url":"https://syntology.ai/paper/2306.07691","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.07691"}},"official":null}},{"url":"/paper/vifs-an-end-to-end-variational-inference-for","slug":"vifs-an-end-to-end-variational-inference-for","title":"VIFS: An End-to-End Variational Inference for Foley Sound Synthesis","date":"2023-06-08","arxiv_id":"2306.05004","repositories_listed":1,"syntology":null}],"record_sha256":"51968b5a38fdfb0744a926521232d613fd90c3c8289bf551837896b6cde12a23","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}