{"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":"/paper/last-language-model-aware-speech-tokenization","title":"LAST: Language Model Aware Speech Tokenization","arxiv_id":"2409.03701","date":"2024-09-05","proceeding":null,"authors":["Arnon Turetzky","Yossi Adi"],"abstract":"Speech tokenization serves as the foundation of speech language model (LM), enabling them to perform various tasks such as spoken language modeling, text-to-speech, speech-to-text, etc. Most speech tokenizers are trained independently of the LM training process, relying on separate acoustic models and quantization methods. Following such an approach may create a mismatch between the tokenization process and its usage afterward. In this study, we propose a novel approach to training a speech tokenizer by leveraging objectives from pre-trained textual LMs. We advocate for the integration of this objective into the process of learning discrete speech representations. Our aim is to transform features from a pre-trained speech model into a new feature space that enables better clustering for speech LMs. We empirically investigate the impact of various model design choices, including speech vocabulary size and text LM size. Our results demonstrate the proposed tokenization method outperforms the evaluated baselines considering both spoken language modeling and speech-to-text. More importantly, unlike prior work, the proposed method allows the utilization of a single pre-trained LM for processing both speech and text inputs, setting it apart from conventional tokenization approaches.","url_abs":"https://arxiv.org/abs/2409.03701v2","url_pdf":"https://arxiv.org/pdf/2409.03701v2.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":[],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"quantization","task_name":"Quantization"},{"task_slug":"speech-tokenization","task_name":"Speech Tokenization"},{"task_slug":"speech-to-text","task_name":"Speech-to-Text"},{"task_slug":"text-to-speech","task_name":"Text to Speech"},{"task_slug":"model","task_name":"model"},{"task_slug":"text-to-speech-1","task_name":"text-to-speech"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/language-modelling-on-salmon","task":"Language Modelling","dataset":"SALMon","model":"LAST 1.3B","rank_in_archive_order":2,"of":10,"metrics":{"Background (Domain) Consistency":"56.0","Background (Random) Consistency":"61.0","Background Alignment":"53.0","Gender Consistency":"68.5","Room Consistency":"62.5","Sentiment Alignment":"53.5","Sentiment Consistency":"65.0","Speaker Consistency":"64.5"},"uses_additional_data":true},{"leaderboard":"/sota/language-modelling-on-salmon","task":"Language Modelling","dataset":"SALMon","model":"LAST 350M","rank_in_archive_order":3,"of":10,"metrics":{"Background (Domain) Consistency":"55.5","Background (Random) Consistency":"60.5","Background Alignment":"54.5","Gender Consistency":"70.5","Room Consistency":"61.0","Sentiment Alignment":"51.5","Sentiment Consistency":"64.0","Speaker Consistency":"63.0"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2409.03701","atlas_url":"https://app.syntology.ai/?focus=2409.03701","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2409.03701"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2409.03701\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2409.03701"},"call":"get_concepts_for_paper(arxiv_id=\"2409.03701\")"}],"by_repo":[],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"ecbdc740ec0845bc034a18d20ff4ae7c9ee25a555f9a9a96717b8707402578e1","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}