{"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/improving-spoken-language-modeling-with","title":"Improving Spoken Language Modeling with Phoneme Classification: A Simple Fine-tuning Approach","arxiv_id":"2410.00025","date":"2024-09-16","proceeding":null,"authors":["Maxime Poli","Emmanuel Chemla","Emmanuel Dupoux"],"abstract":"Recent progress in Spoken Language Modeling has shown that learning language directly from speech is feasible. Generating speech through a pipeline that operates at the text level typically loses nuances, intonations, and non-verbal vocalizations. Modeling directly from speech opens up the path to more natural and expressive systems. On the other hand, speech-only systems require up to three orders of magnitude more data to catch up to their text-based counterparts in terms of their semantic abilities. We show that fine-tuning speech representation models on phoneme classification leads to more context-invariant representations, and language models trained on these units achieve comparable lexical comprehension to ones trained on hundred times more data.","url_abs":"https://arxiv.org/abs/2410.00025v2","url_pdf":"https://arxiv.org/pdf/2410.00025v2.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":"improving-spoken-language-modeling-with","repo_url":"https://github.com/bootphon/spokenlm-phoneme","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.00025","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.00025"}},"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":"deterministic:regex_extraction","url":"https://github.com/bootphon/spokenlm-phoneme","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/bootphon/abkhazia","reach":{"status":"ok","spdx":"GPL-3.0"}}],"summary":{"ran":9,"unverified":1},"by_repo_kind":{"official":{"samples":5,"ran":4,"repositories":1},"found_in_text":{"samples":5,"ran":5,"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":5,"samples":[{"code_sha256_prefix":"da70784a17f5a99f","entry":"convert_to_word_position_dependent","repo":"bootphon/abkhazia","repo_kind":"found_in_text","path":"abkhazia/align/align.py","file_url":"https://github.com/bootphon/abkhazia/blob/HEAD/abkhazia/align/align.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"da70784a17f5a99f"}},{"code_sha256_prefix":"495bb33ee68ab0d9","entry":"create_mask_from_lengths","repo":"bootphon/spokenlm-phoneme","repo_kind":"official","path":"src/phonslm/utils.py","file_url":"https://github.com/bootphon/spokenlm-phoneme/blob/HEAD/src/phonslm/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":"495bb33ee68ab0d9"}},{"code_sha256_prefix":"9f11e9e71c6dfb7e","entry":"format","repo":"bootphon/abkhazia","repo_kind":"found_in_text","path":"abkhazia/decode/_score.py","file_url":"https://github.com/bootphon/abkhazia/blob/HEAD/abkhazia/decode/_score.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"9f11e9e71c6dfb7e"}},{"code_sha256_prefix":"25a7919224d25905","entry":"merge_phones_words_alignments","repo":"bootphon/abkhazia","repo_kind":"found_in_text","path":"abkhazia/align/align.py","file_url":"https://github.com/bootphon/abkhazia/blob/HEAD/abkhazia/align/align.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"25a7919224d25905"}},{"code_sha256_prefix":"5fb17634a6954e38","entry":"read_alignments","repo":"bootphon/spokenlm-phoneme","repo_kind":"official","path":"src/phonslm/reader.py","file_url":"https://github.com/bootphon/spokenlm-phoneme/blob/HEAD/src/phonslm/reader.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":"5fb17634a6954e38"}},{"code_sha256_prefix":"5ba01378940cd9b8","entry":"read_manifest","repo":"bootphon/spokenlm-phoneme","repo_kind":"official","path":"src/phonslm/reader.py","file_url":"https://github.com/bootphon/spokenlm-phoneme/blob/HEAD/src/phonslm/reader.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":"5ba01378940cd9b8"}},{"code_sha256_prefix":"d3d4227b0bbc5b45","entry":"read_params","repo":"bootphon/abkhazia","repo_kind":"found_in_text","path":"abkhazia/language/language_model.py","file_url":"https://github.com/bootphon/abkhazia/blob/HEAD/abkhazia/language/language_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"d3d4227b0bbc5b45"}},{"code_sha256_prefix":"f0a1639034c77c40","entry":"read_units","repo":"bootphon/spokenlm-phoneme","repo_kind":"official","path":"src/phonslm/reader.py","file_url":"https://github.com/bootphon/spokenlm-phoneme/blob/HEAD/src/phonslm/reader.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":"f0a1639034c77c40"}},{"code_sha256_prefix":"042695abb6ed965e","entry":"skip_scoring","repo":"bootphon/abkhazia","repo_kind":"found_in_text","path":"abkhazia/decode/_score.py","file_url":"https://github.com/bootphon/abkhazia/blob/HEAD/abkhazia/decode/_score.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"042695abb6ed965e"}},{"code_sha256_prefix":"544715b72418e8c9","entry":"load_kmeans","repo":"bootphon/spokenlm-phoneme","repo_kind":"official","path":"src/phonslm/utils.py","file_url":"https://github.com/bootphon/spokenlm-phoneme/blob/HEAD/src/phonslm/utils.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":"544715b72418e8c9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}