{"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-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 (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":21,"of":21,"of_with_code":9,"tagged_in_all":21,"counts":{"archive_papers_tagged":21,"with_a_code_link":9,"where_syntology_ran_a_sample":5,"not_listed_spam_title":0,"listed":21,"listed_where_code_ran":5,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":3,"listed_every_run_a_failure_of_syntologys_instrument":2,"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"},"items":[{"url":"/paper/taste-text-aligned-speech-tokenization-and","slug":"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_constructed":0,"n_ran_checked":12,"n_instrument":2,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":20,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/taste-text-aligned-speech-tokenization-and#ran","syntology_url":"https://syntology.ai/paper/2504.07053","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.07053"}},"official":{"repos":["mtkresearch/taste-spokenlm"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":5,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/audio-jailbreak-attacks-exposing","slug":"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","slug":"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","slug":"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_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/dm-codec-distilling-multimodal#ran","syntology_url":"https://syntology.ai/paper/2410.15017","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.15017"}},"official":{"repos":["mubtasimahasan/dm-codec"],"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/sylber-syllabic-embedding-representation-of","slug":"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_constructed":2,"n_ran_checked":3,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/sylber-syllabic-embedding-representation-of#ran","syntology_url":"https://syntology.ai/paper/2410.07168","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.07168"}},"official":{"repos":["Berkeley-Speech-Group/sylber"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/syllablelm-learning-coarse-semantic-units-for","slug":"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_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/syllablelm-learning-coarse-semantic-units-for#ran","syntology_url":"https://syntology.ai/paper/2410.04029","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.04029"}},"official":{"repos":["alanbaade/SyllableLM"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/self-supervised-syllable-discovery-based-on","slug":"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","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/repcodec-a-speech-representation-codec-for","slug":"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_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/repcodec-a-speech-representation-codec-for#ran","syntology_url":"https://syntology.ai/paper/2309.00169","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.00169"}},"official":{"repos":["mct10/repcodec"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":null,"slug":"lm-spt-lm-aligned-semantic-distillation-for","title":"LM-SPT: LM-Aligned Semantic Distillation for Speech Tokenization","date":"2025-06-20","arxiv_id":"2506.16738","repositories_listed":0,"syntology":null},{"url":null,"slug":"factorized-rvq-gan-for-disentangled-speech","title":"Factorized RVQ-GAN For Disentangled Speech Tokenization","date":"2025-06-18","arxiv_id":"2506.15456","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-the-effect-of-segmentation-and","title":"Exploring the Effect of Segmentation and Vocabulary Size on Speech Tokenization for Speech Language Models","date":"2025-05-23","arxiv_id":"2505.17446","repositories_listed":0,"syntology":null},{"url":null,"slug":"impact-of-frame-rates-on-speech-tokenizer-a","title":"Impact of Frame Rates on Speech Tokenizer: A Case Study on Mandarin and English","date":"2025-05-20","arxiv_id":"2505.17076","repositories_listed":0,"syntology":null},{"url":null,"slug":"uniwav-towards-unified-pre-training-for","title":"UniWav: Towards Unified Pre-training for Speech Representation Learning and Generation","date":"2025-03-02","arxiv_id":"2503.00733","repositories_listed":0,"syntology":null},{"url":null,"slug":"recent-advances-in-discrete-speech-tokens-a","title":"Recent Advances in Discrete Speech Tokens: A Review","date":"2025-02-10","arxiv_id":"2502.06490","repositories_listed":0,"syntology":null},{"url":null,"slug":"dc-spin-a-speaker-invariant-speech-tokenizer","title":"DC-Spin: A Speaker-invariant Speech Tokenizer for Spoken Language Models","date":"2024-10-31","arxiv_id":"2410.24177","repositories_listed":0,"syntology":null},{"url":"/paper/last-language-model-aware-speech-tokenization","slug":"last-language-model-aware-speech-tokenization","title":"LAST: Language Model Aware Speech Tokenization","date":"2024-09-05","arxiv_id":"2409.03701","repositories_listed":0,"syntology":null},{"url":null,"slug":"stab-speech-tokenizer-assessment-benchmark","title":"STAB: Speech Tokenizer Assessment Benchmark","date":"2024-09-04","arxiv_id":"2409.02384","repositories_listed":0,"syntology":null},{"url":null,"slug":"discrete-multimodal-transformers-with-a","title":"Discrete Multimodal Transformers with a Pretrained Large Language Model for Mixed-Supervision Speech Processing","date":"2024-06-04","arxiv_id":"2406.06582","repositories_listed":0,"syntology":null},{"url":"/paper/scaling-properties-of-speech-language-models","slug":"scaling-properties-of-speech-language-models","title":"Scaling Properties of Speech Language Models","date":"2024-03-31","arxiv_id":"2404.00685","repositories_listed":0,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 3 unverified","sample_list":"/paper/scaling-properties-of-speech-language-models#ran","syntology_url":"https://syntology.ai/paper/2404.00685","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.00685"}},"official":null}},{"url":null,"slug":"base-tts-lessons-from-building-a-billion","title":"BASE TTS: Lessons from building a billion-parameter Text-to-Speech model on 100K hours of data","date":"2024-02-12","arxiv_id":"2402.08093","repositories_listed":0,"syntology":null}],"syntology_records":7,"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"},"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)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":5,"papers_where_code_ran_first_page":"/task/speech-tokenization/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/speech-tokenization/papers/ran/1","json":"/task/speech-tokenization/papers/ran/1.json","rows":5}],"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":"2026-10-05T00:36:11+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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"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"},"record_sha256":"7363dbc8ad2f322491d0c28b34a178d6969b3241295088ef25f252eed870db51","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}