{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/towards-unsupervised-speech-recognition","title":"Towards Unsupervised Speech Recognition Without Pronunciation Models","arxiv_id":"2406.08380","date":"2024-06-12","proceeding":null,"authors":["Junrui Ni","Liming Wang","Yang Zhang","Kaizhi Qian","Heting Gao","Mark Hasegawa-Johnson","Chang D. Yoo"],"abstract":"Recent advancements in supervised automatic speech recognition (ASR) have achieved remarkable performance, largely due to the growing availability of large transcribed speech corpora. However, most languages lack sufficient paired speech and text data to effectively train these systems. In this article, we tackle the challenge of developing ASR systems without paired speech and text corpora by proposing the removal of reliance on a phoneme lexicon. We explore a new research direction: word-level unsupervised ASR, and experimentally demonstrate that an unsupervised speech recognizer can emerge from joint speech-to-speech and text-to-text masked token-infilling. Using a curated speech corpus containing a fixed number of English words, our system iteratively refines the word segmentation structure and achieves a word error rate of between 20-23%, depending on the vocabulary size, without parallel transcripts, oracle word boundaries, or a pronunciation lexicon. This innovative model surpasses the performance of previous unsupervised ASR models under the lexicon-free setting.","url_abs":"https://arxiv.org/abs/2406.08380v2","url_pdf":"https://arxiv.org/pdf/2406.08380v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"towards-unsupervised-speech-recognition","repo_url":"https://github.com/jeromeni/wholeword-uasr-jstti","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"automatic-speech-recognition-2","task_name":"Automatic Speech Recognition"},{"task_slug":"automatic-speech-recognition","task_name":"Automatic Speech Recognition (ASR)"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"unsupervised-speech-recognition","task_name":"Unsupervised Speech Recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.08380","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.08380"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jeromeni/wholeword-uasr-jstti","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"ran":6,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":8,"ran":8,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"5cf9b5e522af96d5","entry":"boundaries_to_intervals","repo":"jeromeni/wholeword-uasr-jstti","repo_kind":"official","path":"GradSeg/eval_segmentation.py","file_url":"https://github.com/jeromeni/wholeword-uasr-jstti/blob/HEAD/GradSeg/eval_segmentation.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5cf9b5e522af96d5"}},{"code_sha256_prefix":"a73490164e4bb95c","entry":"get_emb","repo":"jeromeni/wholeword-uasr-jstti","repo_kind":"official","path":"GradSeg/data_loader.py","file_url":"https://github.com/jeromeni/wholeword-uasr-jstti/blob/HEAD/GradSeg/data_loader.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a73490164e4bb95c"}},{"code_sha256_prefix":"a5c12d20fafb384f","entry":"get_grad_mag","repo":"jeromeni/wholeword-uasr-jstti","repo_kind":"official","path":"GradSeg/grad_segmenter_new_loader.py","file_url":"https://github.com/jeromeni/wholeword-uasr-jstti/blob/HEAD/GradSeg/grad_segmenter_new_loader.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a5c12d20fafb384f"}},{"code_sha256_prefix":"54dbd7b3ecbb6448","entry":"get_intervals_from_dir","repo":"jeromeni/wholeword-uasr-jstti","repo_kind":"official","path":"GradSeg/eval_segmentation.py","file_url":"https://github.com/jeromeni/wholeword-uasr-jstti/blob/HEAD/GradSeg/eval_segmentation.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"54dbd7b3ecbb6448"}},{"code_sha256_prefix":"4e7fcd91f3f7615d","entry":"get_seg","repo":"jeromeni/wholeword-uasr-jstti","repo_kind":"official","path":"GradSeg/grad_segmenter_new_loader.py","file_url":"https://github.com/jeromeni/wholeword-uasr-jstti/blob/HEAD/GradSeg/grad_segmenter_new_loader.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4e7fcd91f3f7615d"}},{"code_sha256_prefix":"007132725ae94d97","entry":"get_single_emb","repo":"jeromeni/wholeword-uasr-jstti","repo_kind":"official","path":"GradSeg/data_loader.py","file_url":"https://github.com/jeromeni/wholeword-uasr-jstti/blob/HEAD/GradSeg/data_loader.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"007132725ae94d97"}},{"code_sha256_prefix":"bdd3717607f29767","entry":"intervals_to_boundaries","repo":"jeromeni/wholeword-uasr-jstti","repo_kind":"official","path":"GradSeg/eval_segmentation.py","file_url":"https://github.com/jeromeni/wholeword-uasr-jstti/blob/HEAD/GradSeg/eval_segmentation.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bdd3717607f29767"}},{"code_sha256_prefix":"600ff6697348d17b","entry":"score_boundaries","repo":"jeromeni/wholeword-uasr-jstti","repo_kind":"official","path":"wav2boundaries/convert_wavbnd_outs_to_gradseg_style.py","file_url":"https://github.com/jeromeni/wholeword-uasr-jstti/blob/HEAD/wav2boundaries/convert_wavbnd_outs_to_gradseg_style.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"600ff6697348d17b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}