{"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-recognition/papers/5","list_of":"/task/speech-recognition","task":"Speech Recognition","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":5,"pages_in_order":65,"rows_per_page":100,"rows":[401,500],"of":6433,"counts":{"archive_papers_tagged":6433,"with_a_code_link":1373,"where_syntology_ran_a_sample":196,"not_listed_spam_title":0,"listed":6433,"listed_where_code_ran":196,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":162,"every_run_a_failure_of_syntologys_instrument":34,"listed_with_a_run_with_no_instrument_failure":162,"listed_every_run_a_failure_of_syntologys_instrument":34,"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-recognition","prev":"/task/speech-recognition/papers/4","next":"/task/speech-recognition/papers/6","papers":[{"url":"/paper/mooer-llm-based-speech-recognition-and","slug":"mooer-llm-based-speech-recognition-and","title":"MooER: LLM-based Speech Recognition and Translation Models from Moore Threads","date":"2024-08-09","arxiv_id":"2408.05101","repositories_listed":1,"syntology":null},{"url":"/paper/hydraformer-one-encoder-for-all-subsampling","slug":"hydraformer-one-encoder-for-all-subsampling","title":"HydraFormer: One Encoder For All Subsampling Rates","date":"2024-08-08","arxiv_id":"2408.04325","repositories_listed":1,"syntology":null},{"url":"/paper/preserving-spoken-content-in-voice","slug":"preserving-spoken-content-in-voice","title":"Preserving spoken content in voice anonymisation with character-level vocoder conditioning","date":"2024-08-08","arxiv_id":"2408.04306","repositories_listed":1,"syntology":null},{"url":"/paper/wav2graph-a-framework-for-supervised-learning","slug":"wav2graph-a-framework-for-supervised-learning","title":"wav2graph: A Framework for Supervised Learning Knowledge Graph from Speech","date":"2024-08-08","arxiv_id":"2408.04174","repositories_listed":1,"syntology":null},{"url":"/paper/2408-02369","slug":"2408-02369","title":"The NPU-ASLP System Description for Visual Speech Recognition in CNVSRC 2024","date":"2024-08-05","arxiv_id":"2408.02369","repositories_listed":1,"syntology":null},{"url":"/paper/2408-01808","slug":"2408-01808","title":"ALIF: Low-Cost Adversarial Audio Attacks on Black-Box Speech Platforms using Linguistic Features","date":"2024-08-03","arxiv_id":"2408.01808","repositories_listed":1,"syntology":null},{"url":"/paper/2408-00624","slug":"2408-00624","title":"SynesLM: A Unified Approach for Audio-visual Speech Recognition and Translation via Language Model and Synthetic Data","date":"2024-08-01","arxiv_id":"2408.00624","repositories_listed":1,"syntology":null},{"url":"/paper/self-supervised-models-in-automatic-whispered","slug":"self-supervised-models-in-automatic-whispered","title":"Leveraging Self-Supervised Models for Automatic Whispered Speech Recognition","date":"2024-07-30","arxiv_id":"2407.21211","repositories_listed":1,"syntology":null},{"url":"/paper/dynamic-language-group-based-moe-enhancing","slug":"dynamic-language-group-based-moe-enhancing","title":"Dynamic Language Group-Based MoE: Enhancing Code-Switching Speech Recognition with Hierarchical Routing","date":"2024-07-26","arxiv_id":"2407.18581","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-dysarthric-speech-recognition-for","slug":"enhancing-dysarthric-speech-recognition-for","title":"Enhancing Dysarthric Speech Recognition for Unseen Speakers via Prototype-Based Adaptation","date":"2024-07-26","arxiv_id":"2407.18461","repositories_listed":1,"syntology":null},{"url":"/paper/scaling-a-simple-approach-to-zero-shot-speech","slug":"scaling-a-simple-approach-to-zero-shot-speech","title":"Scaling A Simple Approach to Zero-Shot Speech Recognition","date":"2024-07-25","arxiv_id":"2407.17852","repositories_listed":1,"syntology":null},{"url":"/paper/evolutionary-prompt-design-for-llm-based-post","slug":"evolutionary-prompt-design-for-llm-based-post","title":"Evolutionary Prompt Design for LLM-Based Post-ASR Error Correction","date":"2024-07-23","arxiv_id":"2407.16370","repositories_listed":1,"syntology":null},{"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/2408-00005","slug":"2408-00005","title":"Framework for Curating Speech Datasets and Evaluating ASR Systems: A Case Study for Polish","date":"2024-07-18","arxiv_id":"2408.00005","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 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) · 3 unverified","sample_list":"/paper/2408-00005#ran","syntology_url":"https://syntology.ai/paper/2408.00005","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.00005"}},"official":{"repos":["goodmike31/pl-asr-bigos-tools"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/adaptive-cascading-network-for-continual-test","slug":"adaptive-cascading-network-for-continual-test","title":"Adaptive Cascading Network for Continual Test-Time Adaptation","date":"2024-07-17","arxiv_id":"2407.12240","repositories_listed":1,"syntology":null},{"url":"/paper/identifying-speakers-in-dialogue-transcripts","slug":"identifying-speakers-in-dialogue-transcripts","title":"Identifying Speakers in Dialogue Transcripts: A Text-based Approach Using Pretrained Language Models","date":"2024-07-16","arxiv_id":"2407.12094","repositories_listed":1,"syntology":null},{"url":"/paper/vibravox-a-dataset-of-french-speech-captured","slug":"vibravox-a-dataset-of-french-speech-captured","title":"Vibravox: A Dataset of French Speech Captured with Body-conduction Audio Sensors","date":"2024-07-16","arxiv_id":"2407.11828","repositories_listed":1,"syntology":null},{"url":"/paper/do-you-act-like-you-talk-exploring-pose-based","slug":"do-you-act-like-you-talk-exploring-pose-based","title":"Do You Act Like You Talk? Exploring Pose-based Driver Action Classification with Speech Recognition Networks","date":"2024-07-15","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/textless-dependency-parsing-by-labeled","slug":"textless-dependency-parsing-by-labeled","title":"Textless Dependency Parsing by Labeled Sequence Prediction","date":"2024-07-14","arxiv_id":"2407.10118","repositories_listed":1,"syntology":null},{"url":"/paper/a-streaming-multi-channel-end-to-end-speech","slug":"a-streaming-multi-channel-end-to-end-speech","title":"CUSIDE-array: A Streaming Multi-Channel End-to-End Speech Recognition System with Realistic Evaluations","date":"2024-07-13","arxiv_id":"2407.09807","repositories_listed":1,"syntology":null},{"url":"/paper/empowering-whisper-as-a-joint-multi-talker","slug":"empowering-whisper-as-a-joint-multi-talker","title":"Empowering Whisper as a Joint Multi-Talker and Target-Talker Speech Recognition System","date":"2024-07-13","arxiv_id":"2407.09817","repositories_listed":1,"syntology":null},{"url":"/paper/explaining-spectrograms-in-machine-learning-a","slug":"explaining-spectrograms-in-machine-learning-a","title":"Explaining Spectrograms in Machine Learning: A Study on Neural Networks for Speech Classification","date":"2024-07-10","arxiv_id":"2407.17416","repositories_listed":1,"syntology":null},{"url":"/paper/a-voice-and-speech-corpus-of-patients-who","slug":"a-voice-and-speech-corpus-of-patients-who","title":"A voice and speech corpus of patients who underwent upper airway surgery in pre- and post-operative states","date":"2024-07-09","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/tailored-design-of-audio-visual-speech","slug":"tailored-design-of-audio-visual-speech","title":"Tailored Design of Audio-Visual Speech Recognition Models using Branchformers","date":"2024-07-09","arxiv_id":"2407.06606","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/controlling-whisper-universal-acoustic","slug":"controlling-whisper-universal-acoustic","title":"Controlling Whisper: Universal Acoustic Adversarial Attacks to Control Speech Foundation Models","date":"2024-07-05","arxiv_id":"2407.04482","repositories_listed":1,"syntology":null},{"url":"/paper/performance-analysis-of-speech-encoders-for","slug":"performance-analysis-of-speech-encoders-for","title":"Performance Analysis of Speech Encoders for Low-Resource SLU and ASR in Tunisian Dialect","date":"2024-07-05","arxiv_id":"2407.04533","repositories_listed":1,"syntology":null},{"url":"/paper/written-term-detection-improves-spoken-term","slug":"written-term-detection-improves-spoken-term","title":"Written Term Detection Improves Spoken Term Detection","date":"2024-07-05","arxiv_id":"2407.04601","repositories_listed":1,"syntology":null},{"url":"/paper/improving-self-supervised-pre-training-using","slug":"improving-self-supervised-pre-training-using","title":"Improving Self-supervised Pre-training using Accent-Specific Codebooks","date":"2024-07-04","arxiv_id":"2407.03734","repositories_listed":1,"syntology":null},{"url":"/paper/learning-video-temporal-dynamics-with-cross","slug":"learning-video-temporal-dynamics-with-cross","title":"Learning Video Temporal Dynamics with Cross-Modal Attention for Robust Audio-Visual Speech Recognition","date":"2024-07-04","arxiv_id":"2407.03563","repositories_listed":1,"syntology":{"n":13,"n_ran":12,"n_constructed":2,"n_ran_checked":8,"n_instrument":4,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":8,"phrase":"12 ran (of which 2 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/learning-video-temporal-dynamics-with-cross#ran","syntology_url":"https://syntology.ai/paper/2407.03563","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03563"}},"official":{"repos":["sungnyun/avsr-temporal-dynamics"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":2,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-convformer-extending-conformer-with","slug":"multi-convformer-extending-conformer-with","title":"Multi-Convformer: Extending Conformer with Multiple Convolution Kernels","date":"2024-07-04","arxiv_id":"2407.03718","repositories_listed":1,"syntology":null},{"url":"/paper/pinyin-regularization-in-error-correction-for","slug":"pinyin-regularization-in-error-correction-for","title":"Pinyin Regularization in Error Correction for Chinese Speech Recognition with Large Language Models","date":"2024-07-02","arxiv_id":"2407.01909","repositories_listed":1,"syntology":null},{"url":"/paper/enhanced-asr-robustness-to-packet-loss-with-a","slug":"enhanced-asr-robustness-to-packet-loss-with-a","title":"Enhanced ASR Robustness to Packet Loss with a Front-End Adaptation Network","date":"2024-06-27","arxiv_id":"2406.18928","repositories_listed":1,"syntology":null},{"url":"/paper/voices-unheard-nlp-resources-and-models-for","slug":"voices-unheard-nlp-resources-and-models-for","title":"Voices Unheard: NLP Resources and Models for Yorùbá Regional Dialects","date":"2024-06-27","arxiv_id":"2406.19564","repositories_listed":1,"syntology":null},{"url":"/paper/arzen-llm-code-switched-egyptian-arabic","slug":"arzen-llm-code-switched-egyptian-arabic","title":"ArzEn-LLM: Code-Switched Egyptian Arabic-English Translation and Speech Recognition Using LLMs","date":"2024-06-26","arxiv_id":"2406.18120","repositories_listed":1,"syntology":null},{"url":"/paper/automatic-speech-recognition-for-the-nepali","slug":"automatic-speech-recognition-for-the-nepali","title":"Automatic speech recognition for the Nepali language using CNN, bidirectional LSTM and ResNet","date":"2024-06-25","arxiv_id":"2406.17825","repositories_listed":1,"syntology":null},{"url":"/paper/fasa-a-flexible-and-automatic-speech-aligner","slug":"fasa-a-flexible-and-automatic-speech-aligner","title":"FASA: a Flexible and Automatic Speech Aligner for Extracting High-quality Aligned Children Speech Data","date":"2024-06-25","arxiv_id":"2406.17926","repositories_listed":1,"syntology":null},{"url":"/paper/towards-building-an-end-to-end-multilingual","slug":"towards-building-an-end-to-end-multilingual","title":"Towards Building an End-to-End Multilingual Automatic Lyrics Transcription Model","date":"2024-06-25","arxiv_id":"2406.17618","repositories_listed":1,"syntology":null},{"url":"/paper/growing-trees-on-sounds-assessing-strategies","slug":"growing-trees-on-sounds-assessing-strategies","title":"Growing Trees on Sounds: Assessing Strategies for End-to-End Dependency Parsing of Speech","date":"2024-06-18","arxiv_id":"2406.12621","repositories_listed":1,"syntology":null},{"url":"/paper/syncvsr-data-efficient-visual-speech","slug":"syncvsr-data-efficient-visual-speech","title":"SyncVSR: Data-Efficient Visual Speech Recognition with End-to-End Crossmodal Audio Token Synchronization","date":"2024-06-18","arxiv_id":"2406.12233","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-online-continual-learning-for","slug":"unsupervised-online-continual-learning-for","title":"Unsupervised Online Continual Learning for Automatic Speech Recognition","date":"2024-06-18","arxiv_id":"2406.12503","repositories_listed":1,"syntology":null},{"url":"/paper/self-train-before-you-transcribe","slug":"self-train-before-you-transcribe","title":"Self-Train Before You Transcribe","date":"2024-06-17","arxiv_id":"2406.12937","repositories_listed":1,"syntology":null},{"url":"/paper/continual-test-time-adaptation-for-end-to-end","slug":"continual-test-time-adaptation-for-end-to-end","title":"Continual Test-time Adaptation for End-to-end Speech Recognition on Noisy Speech","date":"2024-06-16","arxiv_id":"2406.11064","repositories_listed":1,"syntology":null},{"url":"/paper/optimized-speculative-sampling-for-gpu","slug":"optimized-speculative-sampling-for-gpu","title":"Optimized Speculative Sampling for GPU Hardware Accelerators","date":"2024-06-16","arxiv_id":"2406.11016","repositories_listed":1,"syntology":null},{"url":"/paper/simul-whisper-attention-guided-streaming","slug":"simul-whisper-attention-guided-streaming","title":"Simul-Whisper: Attention-Guided Streaming Whisper with Truncation Detection","date":"2024-06-14","arxiv_id":"2406.10052","repositories_listed":1,"syntology":null},{"url":"/paper/whisper-flamingo-integrating-visual-features","slug":"whisper-flamingo-integrating-visual-features","title":"Whisper-Flamingo: Integrating Visual Features into Whisper for Audio-Visual Speech Recognition and Translation","date":"2024-06-14","arxiv_id":"2406.10082","repositories_listed":1,"syntology":{"n":18,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":7,"n_honours":2,"n_violates":0,"n_no_contract":8,"n_pointer_only":18,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/whisper-flamingo-integrating-visual-features#ran","syntology_url":"https://syntology.ai/paper/2406.10082","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.10082"}},"official":{"repos":["roudimit/whisper-flamingo"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/language-complexity-and-speech-recognition","slug":"language-complexity-and-speech-recognition","title":"Language Complexity and Speech Recognition Accuracy: Orthographic Complexity Hurts, Phonological Complexity Doesn't","date":"2024-06-13","arxiv_id":"2406.09202","repositories_listed":1,"syntology":null},{"url":"/paper/laser-learning-by-aligning-self-supervised","slug":"laser-learning-by-aligning-self-supervised","title":"LASER: Learning by Aligning Self-supervised Representations of Speech for Improving Content-related Tasks","date":"2024-06-13","arxiv_id":"2406.09153","repositories_listed":1,"syntology":null},{"url":"/paper/guiding-frame-level-ctc-alignments-using-self","slug":"guiding-frame-level-ctc-alignments-using-self","title":"Guiding Frame-Level CTC Alignments Using Self-knowledge Distillation","date":"2024-06-12","arxiv_id":"2406.07909","repositories_listed":1,"syntology":null},{"url":"/paper/speech-emotion-recognition-with-asr","slug":"speech-emotion-recognition-with-asr","title":"Speech Emotion Recognition with ASR Transcripts: A Comprehensive Study on Word Error Rate and Fusion Techniques","date":"2024-06-12","arxiv_id":"2406.08353","repositories_listed":1,"syntology":null},{"url":"/paper/towards-unsupervised-speech-recognition","slug":"towards-unsupervised-speech-recognition","title":"Towards Unsupervised Speech Recognition Without Pronunciation Models","date":"2024-06-12","arxiv_id":"2406.08380","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/towards-unsupervised-speech-recognition#ran","syntology_url":"https://syntology.ai/paper/2406.08380","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.08380"}},"official":{"repos":["jeromeni/wholeword-uasr-jstti"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/label-looping-highly-efficient-decoding-for","slug":"label-looping-highly-efficient-decoding-for","title":"Label-Looping: Highly Efficient Decoding for Transducers","date":"2024-06-10","arxiv_id":"2406.06220","repositories_listed":1,"syntology":null},{"url":"/paper/prompting-large-language-models-with-audio","slug":"prompting-large-language-models-with-audio","title":"Prompting Large Language Models with Audio for General-Purpose Speech Summarization","date":"2024-06-10","arxiv_id":"2406.05968","repositories_listed":1,"syntology":null},{"url":"/paper/do-prompts-really-prompt-exploring-the-prompt","slug":"do-prompts-really-prompt-exploring-the-prompt","title":"Do Prompts Really Prompt? Exploring the Prompt Understanding Capability of Whisper","date":"2024-06-09","arxiv_id":"2406.05806","repositories_listed":1,"syntology":null},{"url":"/paper/llm-based-speaker-diarization-correction-a","slug":"llm-based-speaker-diarization-correction-a","title":"LLM-based speaker diarization correction: A generalizable approach","date":"2024-06-07","arxiv_id":"2406.04927","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-performance-plateaus-a-comprehensive","slug":"beyond-performance-plateaus-a-comprehensive","title":"Beyond Performance Plateaus: A Comprehensive Study on Scalability in Speech Enhancement","date":"2024-06-06","arxiv_id":"2406.04269","repositories_listed":1,"syntology":null},{"url":"/paper/blsp-emo-towards-empathetic-large-speech","slug":"blsp-emo-towards-empathetic-large-speech","title":"BLSP-Emo: Towards Empathetic Large Speech-Language Models","date":"2024-06-06","arxiv_id":"2406.03872","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":3,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/blsp-emo-towards-empathetic-large-speech#ran","syntology_url":"https://syntology.ai/paper/2406.03872","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.03872"}},"official":{"repos":["cwang621/blsp-emo"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/label-synchronous-neural-transducer-for-e2e","slug":"label-synchronous-neural-transducer-for-e2e","title":"Label-Synchronous Neural Transducer for E2E Simultaneous Speech Translation","date":"2024-06-06","arxiv_id":"2406.04541","repositories_listed":1,"syntology":null},{"url":"/paper/lipger-visually-conditioned-generative-error","slug":"lipger-visually-conditioned-generative-error","title":"LipGER: Visually-Conditioned Generative Error Correction for Robust Automatic Speech Recognition","date":"2024-06-06","arxiv_id":"2406.04432","repositories_listed":1,"syntology":null},{"url":"/paper/to-distill-or-not-to-distill-on-the","slug":"to-distill-or-not-to-distill-on-the","title":"To Distill or Not to Distill? On the Robustness of Robust Knowledge Distillation","date":"2024-06-06","arxiv_id":"2406.04512","repositories_listed":1,"syntology":null},{"url":"/paper/error-preserving-automatic-speech-recognition","slug":"error-preserving-automatic-speech-recognition","title":"Error-preserving Automatic Speech Recognition of Young English Learners' Language","date":"2024-06-05","arxiv_id":"2406.03235","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/whistle-data-efficient-multilingual-and","slug":"whistle-data-efficient-multilingual-and","title":"Whistle: Data-Efficient Multilingual and Crosslingual Speech Recognition via Weakly Phonetic Supervision","date":"2024-06-04","arxiv_id":"2406.02166","repositories_listed":1,"syntology":null},{"url":"/paper/transvip-speech-to-speech-translation-system","slug":"transvip-speech-to-speech-translation-system","title":"TransVIP: Speech to Speech Translation System with Voice and Isochrony Preservation","date":"2024-05-28","arxiv_id":"2405.17809","repositories_listed":1,"syntology":null},{"url":"/paper/a-variance-preserving-interpolation-approach","slug":"a-variance-preserving-interpolation-approach","title":"A Variance-Preserving Interpolation Approach for Diffusion Models with Applications to Single Channel Speech Enhancement and Recognition","date":"2024-05-27","arxiv_id":"2405.16952","repositories_listed":1,"syntology":null},{"url":"/paper/federating-dynamic-models-using-early-exit","slug":"federating-dynamic-models-using-early-exit","title":"Federating Dynamic Models using Early-Exit Architectures for Automatic Speech Recognition on Heterogeneous Clients","date":"2024-05-27","arxiv_id":"2405.17376","repositories_listed":1,"syntology":null},{"url":"/paper/a-survey-on-vision-language-action-models-for","slug":"a-survey-on-vision-language-action-models-for","title":"A Survey on Vision-Language-Action Models for Embodied AI","date":"2024-05-23","arxiv_id":"2405.14093","repositories_listed":1,"syntology":null},{"url":"/paper/contrastive-and-consistency-learning-for","slug":"contrastive-and-consistency-learning-for","title":"Contrastive and Consistency Learning for Neural Noisy-Channel Model in Spoken Language Understanding","date":"2024-05-23","arxiv_id":"2405.15097","repositories_listed":1,"syntology":null},{"url":"/paper/let-s-fuse-step-by-step-a-generative-fusion","slug":"let-s-fuse-step-by-step-a-generative-fusion","title":"Let's Fuse Step by Step: A Generative Fusion Decoding Algorithm with LLMs for Multi-modal Text Recognition","date":"2024-05-23","arxiv_id":"2405.14259","repositories_listed":1,"syntology":null},{"url":"/paper/self-taught-recognizer-toward-unsupervised","slug":"self-taught-recognizer-toward-unsupervised","title":"Self-Taught Recognizer: Toward Unsupervised Adaptation for Speech Foundation Models","date":"2024-05-23","arxiv_id":"2405.14161","repositories_listed":1,"syntology":null},{"url":"/paper/fadam-adam-is-a-natural-gradient-optimizer","slug":"fadam-adam-is-a-natural-gradient-optimizer","title":"FAdam: Adam is a natural gradient optimizer using diagonal empirical Fisher information","date":"2024-05-21","arxiv_id":"2405.12807","repositories_listed":1,"syntology":null},{"url":"/paper/mamba-in-speech-towards-an-alternative-to","slug":"mamba-in-speech-towards-an-alternative-to","title":"Mamba in Speech: Towards an Alternative to Self-Attention","date":"2024-05-21","arxiv_id":"2405.12609","repositories_listed":1,"syntology":null},{"url":"/paper/acoustic-modeling-for-overlapping-speech","slug":"acoustic-modeling-for-overlapping-speech","title":"Acoustic modeling for Overlapping Speech Recognition: JHU Chime-5 Challenge System","date":"2024-05-17","arxiv_id":"2405.11078","repositories_listed":1,"syntology":null},{"url":"/paper/no-more-mumbles-enhancing-robot","slug":"no-more-mumbles-enhancing-robot","title":"No More Mumbles: Enhancing Robot Intelligibility through Speech Adaptation","date":"2024-05-15","arxiv_id":"2405.09708","repositories_listed":1,"syntology":null},{"url":"/paper/rene-a-pre-trained-multi-modal-architecture","slug":"rene-a-pre-trained-multi-modal-architecture","title":"Rene: A Pre-trained Multi-modal Architecture for Auscultation of Respiratory Diseases","date":"2024-05-13","arxiv_id":"2405.07442","repositories_listed":1,"syntology":null},{"url":"/paper/soccernet-echoes-a-soccer-game-audio","slug":"soccernet-echoes-a-soccer-game-audio","title":"SoccerNet-Echoes: A Soccer Game Audio Commentary Dataset","date":"2024-05-12","arxiv_id":"2405.07354","repositories_listed":1,"syntology":null},{"url":"/paper/watch-your-mouth-silent-speech-recognition","slug":"watch-your-mouth-silent-speech-recognition","title":"Watch Your Mouth: Silent Speech Recognition with Depth Sensing","date":"2024-05-11","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/audio-visual-speech-recognition-based-on","slug":"audio-visual-speech-recognition-based-on","title":"Audio-Visual Speech Recognition based on Regulated Transformer and Spatio-Temporal Fusion Strategy for Driver Assistive Systems","date":"2024-05-09","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/muting-whisper-a-universal-acoustic","slug":"muting-whisper-a-universal-acoustic","title":"Muting Whisper: A Universal Acoustic Adversarial Attack on Speech Foundation Models","date":"2024-05-09","arxiv_id":"2405.06134","repositories_listed":1,"syntology":null},{"url":"/paper/open-implementation-and-study-of-best-rq-for","slug":"open-implementation-and-study-of-best-rq-for","title":"Open Implementation and Study of BEST-RQ for Speech Processing","date":"2024-05-07","arxiv_id":"2405.04296","repositories_listed":1,"syntology":null},{"url":"/paper/mixat-a-data-set-of-bilingual-emirati-english","slug":"mixat-a-data-set-of-bilingual-emirati-english","title":"Mixat: A Data Set of Bilingual Emirati-English Speech","date":"2024-05-04","arxiv_id":"2405.02578","repositories_listed":1,"syntology":null},{"url":"/paper/unveiling-the-potential-of-llm-based-asr-on","slug":"unveiling-the-potential-of-llm-based-asr-on","title":"Unveiling the Potential of LLM-Based ASR on Chinese Open-Source Datasets","date":"2024-05-03","arxiv_id":"2405.02132","repositories_listed":1,"syntology":null},{"url":"/paper/mamba-360-survey-of-state-space-models-as","slug":"mamba-360-survey-of-state-space-models-as","title":"Mamba-360: Survey of State Space Models as Transformer Alternative for Long Sequence Modelling: Methods, Applications, and Challenges","date":"2024-04-24","arxiv_id":"2404.16112","repositories_listed":1,"syntology":null},{"url":"/paper/killkan-the-automatic-speech-recognition","slug":"killkan-the-automatic-speech-recognition","title":"Killkan: The Automatic Speech Recognition Dataset for Kichwa with Morphosyntactic Information","date":"2024-04-23","arxiv_id":"2404.15501","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-neural-oscillations-during-speech","slug":"exploring-neural-oscillations-during-speech","title":"Exploring neural oscillations during speech perception via surrogate gradient spiking neural networks","date":"2024-04-22","arxiv_id":"2404.14024","repositories_listed":1,"syntology":null},{"url":"/paper/less-peaky-and-more-accurate-ctc-forced","slug":"less-peaky-and-more-accurate-ctc-forced","title":"Less Peaky and More Accurate CTC Forced Alignment by Label Priors","date":"2024-04-22","arxiv_id":"2406.02560","repositories_listed":1,"syntology":{"n":10,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 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) · 7 unverified","sample_list":"/paper/less-peaky-and-more-accurate-ctc-forced#ran","syntology_url":"https://syntology.ai/paper/2406.02560","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.02560"}},"official":{"repos":["huangruizhe/audio"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/semantically-corrected-amharic-automatic","slug":"semantically-corrected-amharic-automatic","title":"Semantically Corrected Amharic Automatic Speech Recognition","date":"2024-04-20","arxiv_id":"2404.13362","repositories_listed":1,"syntology":null},{"url":"/paper/teaching-a-multilingual-large-language-model","slug":"teaching-a-multilingual-large-language-model","title":"Teaching a Multilingual Large Language Model to Understand Multilingual Speech via Multi-Instructional Training","date":"2024-04-16","arxiv_id":"2404.10922","repositories_listed":1,"syntology":null},{"url":"/paper/vietmed-a-dataset-and-benchmark-for-automatic","slug":"vietmed-a-dataset-and-benchmark-for-automatic","title":"VietMed: A Dataset and Benchmark for Automatic Speech Recognition of Vietnamese in the Medical Domain","date":"2024-04-08","arxiv_id":"2404.05659","repositories_listed":1,"syntology":null},{"url":"/paper/cmulab-an-open-source-framework-for-training","slug":"cmulab-an-open-source-framework-for-training","title":"CMULAB: An Open-Source Framework for Training and Deployment of Natural Language Processing Models","date":"2024-04-03","arxiv_id":"2404.02408","repositories_listed":1,"syntology":null},{"url":"/paper/braven-improving-self-supervised-pre-training","slug":"braven-improving-self-supervised-pre-training","title":"BRAVEn: Improving Self-Supervised Pre-training for Visual and Auditory Speech Recognition","date":"2024-04-02","arxiv_id":"2404.02098","repositories_listed":1,"syntology":{"n":14,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/braven-improving-self-supervised-pre-training#ran","syntology_url":"https://syntology.ai/paper/2404.02098","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.02098"}},"official":{"repos":["ahaliassos/raven"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/kallaama-a-transcribed-speech-dataset-about","slug":"kallaama-a-transcribed-speech-dataset-about","title":"Kallaama: A Transcribed Speech Dataset about Agriculture in the Three Most Widely Spoken Languages in Senegal","date":"2024-04-02","arxiv_id":"2404.01991","repositories_listed":1,"syntology":null},{"url":"/paper/elitr-bench-a-meeting-assistant-benchmark-for","slug":"elitr-bench-a-meeting-assistant-benchmark-for","title":"ELITR-Bench: A Meeting Assistant Benchmark for Long-Context Language Models","date":"2024-03-29","arxiv_id":"2403.20262","repositories_listed":1,"syntology":null},{"url":"/paper/phowhisper-automatic-speech-recognition-for","slug":"phowhisper-automatic-speech-recognition-for","title":"PhoWhisper: Automatic Speech Recognition for Vietnamese","date":"2024-03-27","arxiv_id":"2406.02555","repositories_listed":1,"syntology":null},{"url":"/paper/flowerformer-empowering-neural-architecture","slug":"flowerformer-empowering-neural-architecture","title":"FlowerFormer: Empowering Neural Architecture Encoding using a Flow-aware Graph Transformer","date":"2024-03-19","arxiv_id":"2403.12821","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":6,"phrase":"3 ran (of which 0 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) · 3 unverified","sample_list":"/paper/flowerformer-empowering-neural-architecture#ran","syntology_url":"https://syntology.ai/paper/2403.12821","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.12821"}},"official":{"repos":["y0ngjaenius/cvpr2024_flowerformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/spoken-100-a-cross-lingual-benchmarking","slug":"spoken-100-a-cross-lingual-benchmarking","title":"SpokeN-100: A Cross-Lingual Benchmarking Dataset for The Classification of Spoken Numbers in Different Languages","date":"2024-03-14","arxiv_id":"2403.09753","repositories_listed":1,"syntology":null},{"url":"/paper/speechcolab-leaderboard-an-open-source","slug":"speechcolab-leaderboard-an-open-source","title":"SpeechColab Leaderboard: An Open-Source Platform for Automatic Speech Recognition Evaluation","date":"2024-03-13","arxiv_id":"2403.08196","repositories_listed":1,"syntology":null},{"url":"/paper/real-time-multimodal-cognitive-assistant-for","slug":"real-time-multimodal-cognitive-assistant-for","title":"Real-Time Multimodal Cognitive Assistant for Emergency Medical Services","date":"2024-03-11","arxiv_id":"2403.06734","repositories_listed":1,"syntology":null},{"url":"/paper/score-self-supervised-correspondence-fine","slug":"score-self-supervised-correspondence-fine","title":"SCORE: Self-supervised Correspondence Fine-tuning for Improved Content Representations","date":"2024-03-10","arxiv_id":"2403.06260","repositories_listed":1,"syntology":null},{"url":"/paper/speech-robust-bench-a-robustness-benchmark","slug":"speech-robust-bench-a-robustness-benchmark","title":"Speech Robust Bench: A Robustness Benchmark For Speech Recognition","date":"2024-03-08","arxiv_id":"2403.07937","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/speech-robust-bench-a-robustness-benchmark#ran","syntology_url":"https://syntology.ai/paper/2403.07937","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.07937"}},"official":{"repos":["ahmedshah1494/speech_robust_bench"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]}}}],"record_sha256":"5bfd07459daf9f0e20c6c5fb5faf99ebd97c35b7e5a49f04d7673dea19ae7608","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}