{"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/unsupervised-speech-recognition-with-n","title":"Unsupervised Speech Recognition with N-Skipgram and Positional Unigram Matching","arxiv_id":"2310.02382","date":"2023-10-03","proceeding":null,"authors":["Liming Wang","Mark Hasegawa-Johnson","Chang D. Yoo"],"abstract":"Training unsupervised speech recognition systems presents challenges due to GAN-associated instability, misalignment between speech and text, and significant memory demands. To tackle these challenges, we introduce a novel ASR system, ESPUM. This system harnesses the power of lower-order N-skipgrams (up to N=3) combined with positional unigram statistics gathered from a small batch of samples. Evaluated on the TIMIT benchmark, our model showcases competitive performance in ASR and phoneme segmentation tasks. Access our publicly available code at https://github.com/lwang114/GraphUnsupASR.","url_abs":"https://arxiv.org/abs/2310.02382v1","url_pdf":"https://arxiv.org/pdf/2310.02382v1.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":"unsupervised-speech-recognition-with-n","repo_url":"https://github.com/lwang114/graphunsupasr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"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":{"syntology_url":"https://syntology.ai/paper/2310.02382","atlas_url":"https://app.syntology.ai/?focus=2310.02382","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.02382"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/lwang114/graphunsupasr","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":8,"unverified":1},"by_repo_kind":{"official":{"samples":9,"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":"d996cf06772c4c8f","entry":"detect_peaks","repo":"lwang114/graphunsupasr","repo_kind":"official","path":"espum/models/utils.py","file_url":"https://github.com/lwang114/graphunsupasr/blob/HEAD/espum/models/utils.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":"d996cf06772c4c8f"}},{"code_sha256_prefix":"5d7e11b26ae7fca1","entry":"get_assignments","repo":"lwang114/graphunsupasr","repo_kind":"official","path":"w2vu_generate.py","file_url":"https://github.com/lwang114/graphunsupasr/blob/HEAD/w2vu_generate.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":"5d7e11b26ae7fca1"}},{"code_sha256_prefix":"9d45b973f1eb1b50","entry":"get_convolution_index_set","repo":"lwang114/graphunsupasr","repo_kind":"official","path":"kaldi_self_train/st/steps/nnet2/make_multisplice_configs.py","file_url":"https://github.com/lwang114/graphunsupasr/blob/HEAD/kaldi_self_train/st/steps/nnet2/make_multisplice_configs.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":"9d45b973f1eb1b50"}},{"code_sha256_prefix":"1a82e55d7de6917c","entry":"get_dataset_itr","repo":"lwang114/graphunsupasr","repo_kind":"official","path":"w2vu_generate.py","file_url":"https://github.com/lwang114/graphunsupasr/blob/HEAD/w2vu_generate.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":"1a82e55d7de6917c"}},{"code_sha256_prefix":"801f1e8e0d260afb","entry":"load_lex","repo":"lwang114/graphunsupasr","repo_kind":"official","path":"kaldi_self_train/st/local/unsup_select.py","file_url":"https://github.com/lwang114/graphunsupasr/blob/HEAD/kaldi_self_train/st/local/unsup_select.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":"801f1e8e0d260afb"}},{"code_sha256_prefix":"c79df675e2681009","entry":"load_tra","repo":"lwang114/graphunsupasr","repo_kind":"official","path":"kaldi_self_train/st/local/unsup_select.py","file_url":"https://github.com/lwang114/graphunsupasr/blob/HEAD/kaldi_self_train/st/local/unsup_select.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":"c79df675e2681009"}},{"code_sha256_prefix":"bed7cf8a53b7f8b7","entry":"max_min_norm","repo":"lwang114/graphunsupasr","repo_kind":"official","path":"espum/models/utils.py","file_url":"https://github.com/lwang114/graphunsupasr/blob/HEAD/espum/models/utils.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":"bed7cf8a53b7f8b7"}},{"code_sha256_prefix":"b962727751797747","entry":"replicate_first_k_frames","repo":"lwang114/graphunsupasr","repo_kind":"official","path":"espum/models/utils.py","file_url":"https://github.com/lwang114/graphunsupasr/blob/HEAD/espum/models/utils.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":"b962727751797747"}},{"code_sha256_prefix":"f1c7206adbb45460","entry":"parse_splice_string","repo":"lwang114/graphunsupasr","repo_kind":"official","path":"kaldi_self_train/st/steps/nnet2/make_multisplice_configs.py","file_url":"https://github.com/lwang114/graphunsupasr/blob/HEAD/kaldi_self_train/st/steps/nnet2/make_multisplice_configs.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f1c7206adbb45460"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}