{"url":"/task/speech-tokenization","name":"Speech Tokenization","slug":"speech-tokenization","description_markdown":"Speech tokenization is the task of representing speech signals as a sequence of discrete units. Such representations can be later used for various downstream tasks including automatic speech recognition, text-to-speech, etc. Such representation serves as the basis of Speech Language Models.","categories":[{"name":"Speech","url":"/area/speech"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":21,"papers_with_code":9,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":0,"subtasks":0,"parent_tasks":1},"benchmarks":[],"datasets":[],"subtasks":[],"parent_tasks":[{"url":"/task/spoken-language-understanding","name":"Spoken Language Understanding"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":9,"of":9,"tagged_in_all":21,"items":[{"url":"/paper/taste-text-aligned-speech-tokenization-and","title":"TASTE: Text-Aligned Speech Tokenization and Embedding for Spoken Language Modeling","date":"2025-04-09","arxiv_id":"2504.07053","repositories_listed":2,"syntology":{"n":20,"n_ran":14,"n_unverified":6,"n_pointer_only":20}},{"url":"/paper/audio-jailbreak-attacks-exposing","title":"Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework","date":"2025-05-24","arxiv_id":"2505.18864","repositories_listed":1,"syntology":null},{"url":"/paper/best-std-bidirectional-mamba-enhanced-speech","title":"BEST-STD: Bidirectional Mamba-Enhanced Speech Tokenization for Spoken Term Detection","date":"2024-11-21","arxiv_id":"2411.14100","repositories_listed":1,"syntology":null},{"url":"/paper/dm-codec-distilling-multimodal","title":"DM-Codec: Distilling Multimodal Representations for Speech Tokenization","date":"2024-10-19","arxiv_id":"2410.15017","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/sylber-syllabic-embedding-representation-of","title":"Sylber: Syllabic Embedding Representation of Speech from Raw Audio","date":"2024-10-09","arxiv_id":"2410.07168","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/syllablelm-learning-coarse-semantic-units-for","title":"SyllableLM: Learning Coarse Semantic Units for Speech Language Models","date":"2024-10-05","arxiv_id":"2410.04029","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/self-supervised-syllable-discovery-based-on","title":"Self-Supervised Syllable Discovery Based on Speaker-Disentangled HuBERT","date":"2024-09-16","arxiv_id":"2409.10103","repositories_listed":1,"syntology":null},{"url":"/paper/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_unverified":0,"n_pointer_only":1}},{"url":"/paper/repcodec-a-speech-representation-codec-for","title":"RepCodec: A Speech Representation Codec for Speech Tokenization","date":"2023-08-31","arxiv_id":"2309.00169","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}}],"syntology_records":6,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}