{"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-1/papers/4","list_of":"/task/speech-recognition-1","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":4,"pages_in_order":58,"rows_per_page":100,"rows":[301,400],"of":5715,"counts":{"archive_papers_tagged":5715,"with_a_code_link":1277,"where_syntology_ran_a_sample":162,"not_listed_spam_title":0,"listed":5715,"listed_where_code_ran":162,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":134,"every_run_a_failure_of_syntologys_instrument":28,"listed_with_a_run_with_no_instrument_failure":134,"listed_every_run_a_failure_of_syntologys_instrument":28,"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-1","prev":"/task/speech-recognition-1/papers/3","next":"/task/speech-recognition-1/papers/5","papers":[{"url":"/paper/glm-4-voice-towards-intelligent-and-human","slug":"glm-4-voice-towards-intelligent-and-human","title":"GLM-4-Voice: Towards Intelligent and Human-Like End-to-End Spoken Chatbot","date":"2024-12-03","arxiv_id":"2412.02612","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/glm-4-voice-towards-intelligent-and-human#ran","syntology_url":"https://syntology.ai/paper/2412.02612","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.02612"}},"official":{"repos":["thudm/glm-4-voice"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/automating-feedback-analysis-in-surgical","slug":"automating-feedback-analysis-in-surgical","title":"Automating Feedback Analysis in Surgical Training: Detection, Categorization, and Assessment","date":"2024-12-01","arxiv_id":"2412.00760","repositories_listed":1,"syntology":null},{"url":"/paper/k2ssl-a-faster-and-better-framework-for-self","slug":"k2ssl-a-faster-and-better-framework-for-self","title":"k2SSL: A Faster and Better Framework for Self-Supervised Speech Representation Learning","date":"2024-11-26","arxiv_id":"2411.17100","repositories_listed":1,"syntology":null},{"url":"/paper/scaling-speech-text-pre-training-with","slug":"scaling-speech-text-pre-training-with","title":"Scaling Speech-Text Pre-training with Synthetic Interleaved Data","date":"2024-11-26","arxiv_id":"2411.17607","repositories_listed":1,"syntology":null},{"url":"/paper/backdoormbti-a-backdoor-learning-multimodal","slug":"backdoormbti-a-backdoor-learning-multimodal","title":"BackdoorMBTI: A Backdoor Learning Multimodal Benchmark Tool Kit for Backdoor Defense Evaluation","date":"2024-11-17","arxiv_id":"2411.11006","repositories_listed":1,"syntology":null},{"url":"/paper/bangladialecto-an-end-to-end-ai-powered","slug":"bangladialecto-an-end-to-end-ai-powered","title":"BanglaDialecto: An End-to-End AI-Powered Regional Speech Standardization","date":"2024-11-16","arxiv_id":"2411.10879","repositories_listed":1,"syntology":null},{"url":"/paper/wavchat-a-survey-of-spoken-dialogue-models","slug":"wavchat-a-survey-of-spoken-dialogue-models","title":"WavChat: A Survey of Spoken Dialogue Models","date":"2024-11-15","arxiv_id":"2411.13577","repositories_listed":1,"syntology":null},{"url":"/paper/xlsr-mamba-a-dual-column-bidirectional-state","slug":"xlsr-mamba-a-dual-column-bidirectional-state","title":"XLSR-Mamba: A Dual-Column Bidirectional State Space Model for Spoofing Attack Detection","date":"2024-11-15","arxiv_id":"2411.10027","repositories_listed":1,"syntology":null},{"url":"/paper/ctc-assisted-llm-based-contextual-asr","slug":"ctc-assisted-llm-based-contextual-asr","title":"CTC-Assisted LLM-Based Contextual ASR","date":"2024-11-10","arxiv_id":"2411.06437","repositories_listed":1,"syntology":null},{"url":"/paper/dialectal-coverage-and-generalization-in","slug":"dialectal-coverage-and-generalization-in","title":"Dialectal Coverage And Generalization in Arabic Speech Recognition","date":"2024-11-07","arxiv_id":"2411.05872","repositories_listed":1,"syntology":null},{"url":"/paper/unified-speech-recognition-a-single-model-for","slug":"unified-speech-recognition-a-single-model-for","title":"Unified Speech Recognition: A Single Model for Auditory, Visual, and Audiovisual Inputs","date":"2024-11-04","arxiv_id":"2411.02256","repositories_listed":1,"syntology":{"n":9,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":9,"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) · 6 unverified","sample_list":"/paper/unified-speech-recognition-a-single-model-for#ran","syntology_url":"https://syntology.ai/paper/2411.02256","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.02256"}},"official":{"repos":["ahaliassos/usr"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/spes-spectrogram-perturbation-for-explainable","slug":"spes-spectrogram-perturbation-for-explainable","title":"SPES: Spectrogram Perturbation for Explainable Speech-to-Text Generation","date":"2024-11-03","arxiv_id":"2411.01710","repositories_listed":1,"syntology":null},{"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/voicebench-benchmarking-llm-based-voice","slug":"voicebench-benchmarking-llm-based-voice","title":"VoiceBench: Benchmarking LLM-Based Voice Assistants","date":"2024-10-22","arxiv_id":"2410.17196","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/voicebench-benchmarking-llm-based-voice#ran","syntology_url":"https://syntology.ai/paper/2410.17196","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.17196"}},"official":{"repos":["matthewcym/voicebench"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/alignvsr-audio-visual-cross-modal-alignment","slug":"alignvsr-audio-visual-cross-modal-alignment","title":"AlignVSR: Audio-Visual Cross-Modal Alignment for Visual Speech Recognition","date":"2024-10-21","arxiv_id":"2410.16438","repositories_listed":1,"syntology":null},{"url":"/paper/moonshine-speech-recognition-for-live","slug":"moonshine-speech-recognition-for-live","title":"Moonshine: Speech Recognition for Live Transcription and Voice Commands","date":"2024-10-21","arxiv_id":"2410.15608","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":8,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/moonshine-speech-recognition-for-live#ran","syntology_url":"https://syntology.ai/paper/2410.15608","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.15608"}},"official":{"repos":["usefulsensors/moonshine"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/enhancing-multimodal-sentiment-analysis-for","slug":"enhancing-multimodal-sentiment-analysis-for","title":"Enhancing Multimodal Sentiment Analysis for Missing Modality through Self-Distillation and Unified Modality Cross-Attention","date":"2024-10-19","arxiv_id":"2410.15029","repositories_listed":1,"syntology":null},{"url":"/paper/eh-mam-easy-to-hard-masked-acoustic-modeling","slug":"eh-mam-easy-to-hard-masked-acoustic-modeling","title":"EH-MAM: Easy-to-Hard Masked Acoustic Modeling for Self-Supervised Speech Representation Learning","date":"2024-10-17","arxiv_id":"2410.13179","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/eh-mam-easy-to-hard-masked-acoustic-modeling#ran","syntology_url":"https://syntology.ai/paper/2410.13179","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.13179"}},"official":{"repos":["cs20s030/ehmam"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/a-framework-for-adapting-human-robot","slug":"a-framework-for-adapting-human-robot","title":"A Framework for Adapting Human-Robot Interaction to Diverse User Groups","date":"2024-10-15","arxiv_id":"2410.11377","repositories_listed":1,"syntology":null},{"url":"/paper/slam-aac-enhancing-audio-captioning-with","slug":"slam-aac-enhancing-audio-captioning-with","title":"SLAM-AAC: Enhancing Audio Captioning with Paraphrasing Augmentation and CLAP-Refine through LLMs","date":"2024-10-12","arxiv_id":"2410.09503","repositories_listed":1,"syntology":null},{"url":"/paper/cr-ctc-consistency-regularization-on-ctc-for","slug":"cr-ctc-consistency-regularization-on-ctc-for","title":"CR-CTC: Consistency regularization on CTC for improved speech recognition","date":"2024-10-07","arxiv_id":"2410.05101","repositories_listed":1,"syntology":null},{"url":"/paper/the-ocon-model-an-old-but-gold-solution-for","slug":"the-ocon-model-an-old-but-gold-solution-for","title":"The OCON model: an old but gold solution for distributable supervised classification","date":"2024-10-05","arxiv_id":"2410.05320","repositories_listed":1,"syntology":null},{"url":"/paper/multi-dialect-vietnamese-task-dataset","slug":"multi-dialect-vietnamese-task-dataset","title":"Multi-Dialect Vietnamese: Task, Dataset, Baseline Models and Challenges","date":"2024-10-04","arxiv_id":"2410.03458","repositories_listed":1,"syntology":null},{"url":"/paper/self-powered-llm-modality-expansion-for-large","slug":"self-powered-llm-modality-expansion-for-large","title":"Self-Powered LLM Modality Expansion for Large Speech-Text Models","date":"2024-10-04","arxiv_id":"2410.03798","repositories_listed":1,"syntology":null},{"url":"/paper/end-to-end-speech-recognition-with-pre","slug":"end-to-end-speech-recognition-with-pre","title":"End-to-End Speech Recognition with Pre-trained Masked Language Model","date":"2024-10-01","arxiv_id":"2410.00528","repositories_listed":1,"syntology":null},{"url":"/paper/mosel-950000-hours-of-speech-data-for-open","slug":"mosel-950000-hours-of-speech-data-for-open","title":"MOSEL: 950,000 Hours of Speech Data for Open-Source Speech Foundation Model Training on EU Languages","date":"2024-10-01","arxiv_id":"2410.01036","repositories_listed":1,"syntology":null},{"url":"/paper/afrihubert-a-self-supervised-speech","slug":"afrihubert-a-self-supervised-speech","title":"AfriHuBERT: A self-supervised speech representation model for African languages","date":"2024-09-30","arxiv_id":"2409.20201","repositories_listed":1,"syntology":null},{"url":"/paper/mamba-for-streaming-asr-combined-with","slug":"mamba-for-streaming-asr-combined-with","title":"Mamba for Streaming ASR Combined with Unimodal Aggregation","date":"2024-09-30","arxiv_id":"2410.00070","repositories_listed":1,"syntology":null},{"url":"/paper/cot-st-enhancing-llm-based-speech-translation","slug":"cot-st-enhancing-llm-based-speech-translation","title":"CoT-ST: Enhancing LLM-based Speech Translation with Multimodal Chain-of-Thought","date":"2024-09-29","arxiv_id":"2409.19510","repositories_listed":1,"syntology":null},{"url":"/paper/improving-multilingual-asr-in-the-wild-using","slug":"improving-multilingual-asr-in-the-wild-using","title":"Improving Multilingual ASR in the Wild Using Simple N-best Re-ranking","date":"2024-09-27","arxiv_id":"2409.18428","repositories_listed":1,"syntology":null},{"url":"/paper/semi-supervised-cognitive-state","slug":"semi-supervised-cognitive-state","title":"Semi-Supervised Cognitive State Classification from Speech with Multi-View Pseudo-Labeling","date":"2024-09-25","arxiv_id":"2409.16937","repositories_listed":1,"syntology":null},{"url":"/paper/weighted-cross-entropy-for-low-resource","slug":"weighted-cross-entropy-for-low-resource","title":"Weighted Cross-entropy for Low-Resource Languages in Multilingual Speech Recognition","date":"2024-09-25","arxiv_id":"2409.16954","repositories_listed":1,"syntology":null},{"url":"/paper/wesep-a-scalable-and-flexible-toolkit-towards","slug":"wesep-a-scalable-and-flexible-toolkit-towards","title":"WeSep: A Scalable and Flexible Toolkit Towards Generalizable Target Speaker Extraction","date":"2024-09-24","arxiv_id":"2409.15799","repositories_listed":1,"syntology":null},{"url":"/paper/revise-reason-and-recognize-llm-based-emotion","slug":"revise-reason-and-recognize-llm-based-emotion","title":"Revise, Reason, and Recognize: LLM-Based Emotion Recognition via Emotion-Specific Prompts and ASR Error Correction","date":"2024-09-23","arxiv_id":"2409.15551","repositories_listed":1,"syntology":null},{"url":"/paper/2409-14074","slug":"2409-14074","title":"MultiMed: Multilingual Medical Speech Recognition via Attention Encoder Decoder","date":"2024-09-21","arxiv_id":"2409.14074","repositories_listed":1,"syntology":null},{"url":"/paper/channel-aware-domain-adaptive-generative","slug":"channel-aware-domain-adaptive-generative","title":"Channel-Aware Domain-Adaptive Generative Adversarial Network for Robust Speech Recognition","date":"2024-09-19","arxiv_id":"2409.12386","repositories_listed":1,"syntology":null},{"url":"/paper/disentangling-speakers-in-multi-talker-speech","slug":"disentangling-speakers-in-multi-talker-speech","title":"Disentangling Speakers in Multi-Talker Speech Recognition with Speaker-Aware CTC","date":"2024-09-19","arxiv_id":"2409.12388","repositories_listed":1,"syntology":null},{"url":"/paper/asr-benchmarking-need-for-a-more","slug":"asr-benchmarking-need-for-a-more","title":"ASR Benchmarking: Need for a More Representative Conversational Dataset","date":"2024-09-18","arxiv_id":"2409.12042","repositories_listed":1,"syntology":null},{"url":"/paper/large-language-models-are-strong-audio-visual","slug":"large-language-models-are-strong-audio-visual","title":"Large Language Models are Strong Audio-Visual Speech Recognition Learners","date":"2024-09-18","arxiv_id":"2409.12319","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":2,"n_ran_checked":6,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":12,"phrase":"9 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/large-language-models-are-strong-audio-visual#ran","syntology_url":"https://syntology.ai/paper/2409.12319","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.12319"}},"official":{"repos":["umbertocappellazzo/llama-avsr"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":2,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/large-language-model-can-transcribe-speech-in","slug":"large-language-model-can-transcribe-speech-in","title":"Large Language Model Can Transcribe Speech in Multi-Talker Scenarios with Versatile Instructions","date":"2024-09-13","arxiv_id":"2409.08596","repositories_listed":1,"syntology":null},{"url":"/paper/linear-time-complexity-conformers-with","slug":"linear-time-complexity-conformers-with","title":"Linear Time Complexity Conformers with SummaryMixing for Streaming Speech Recognition","date":"2024-09-11","arxiv_id":"2409.07165","repositories_listed":1,"syntology":null},{"url":"/paper/advancing-topic-segmentation-of-broadcasted","slug":"advancing-topic-segmentation-of-broadcasted","title":"Advancing Topic Segmentation of Broadcasted Speech with Multilingual Semantic Embeddings","date":"2024-09-10","arxiv_id":"2409.06222","repositories_listed":1,"syntology":null},{"url":"/paper/progres-prompted-generative-rescoring-on-asr","slug":"progres-prompted-generative-rescoring-on-asr","title":"ProGRes: Prompted Generative Rescoring on ASR n-Best","date":"2024-08-30","arxiv_id":"2409.00217","repositories_listed":1,"syntology":null},{"url":"/paper/crisperwhisper-accurate-timestamps-on","slug":"crisperwhisper-accurate-timestamps-on","title":"CrisperWhisper: Accurate Timestamps on Verbatim Speech Transcriptions","date":"2024-08-29","arxiv_id":"2408.16589","repositories_listed":1,"syntology":null},{"url":"/paper/measuring-the-accuracy-of-automatic-speech","slug":"measuring-the-accuracy-of-automatic-speech","title":"Measuring the Accuracy of Automatic Speech Recognition Solutions","date":"2024-08-29","arxiv_id":"2408.16287","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-levenshtein-leveraging-multiple","slug":"beyond-levenshtein-leveraging-multiple","title":"Beyond Levenshtein: Leveraging Multiple Algorithms for Robust Word Error Rate Computations And Granular Error Classifications","date":"2024-08-28","arxiv_id":"2408.15616","repositories_listed":1,"syntology":null},{"url":"/paper/self-supervised-speech-representations-still","slug":"self-supervised-speech-representations-still","title":"Self-supervised Speech Representations Still Struggle with African American Vernacular English","date":"2024-08-26","arxiv_id":"2408.14262","repositories_listed":1,"syntology":null},{"url":"/paper/approaching-deep-learning-through-the","slug":"approaching-deep-learning-through-the","title":"Approaching Deep Learning through the Spectral Dynamics of Weights","date":"2024-08-21","arxiv_id":"2408.11804","repositories_listed":1,"syntology":{"n":14,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/approaching-deep-learning-through-the#ran","syntology_url":"https://syntology.ai/paper/2408.11804","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.11804"}},"official":{"repos":["dyunis/spectral_dynamics"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":5,"ran_from_kinds":["official"]}}},{"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/ser-evals-in-domain-and-out-of-domain","slug":"ser-evals-in-domain-and-out-of-domain","title":"SER Evals: In-domain and Out-of-domain Benchmarking for Speech Emotion Recognition","date":"2024-08-14","arxiv_id":"2408.07851","repositories_listed":1,"syntology":null},{"url":"/paper/li-tta-language-informed-test-time-adaptation","slug":"li-tta-language-informed-test-time-adaptation","title":"LI-TTA: Language Informed Test-Time Adaptation for Automatic Speech Recognition","date":"2024-08-11","arxiv_id":"2408.05769","repositories_listed":1,"syntology":null},{"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/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}],"record_sha256":"1ed9872d3b35018023ae82a2a8af85b69e1127bb50921614f6229c53c8a157a1","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}