{"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/unified-speech-text-pretraining-for-spoken","title":"Paralinguistics-Aware Speech-Empowered Large Language Models for Natural Conversation","arxiv_id":"2402.05706","date":"2024-02-08","proceeding":null,"authors":["Heeseung Kim","Soonshin Seo","Kyeongseok Jeong","Ohsung Kwon","Soyoon Kim","Jungwhan Kim","Jaehong Lee","Eunwoo Song","Myungwoo Oh","Jung-Woo Ha","Sungroh Yoon","Kang Min Yoo"],"abstract":"Recent work shows promising results in expanding the capabilities of large language models (LLM) to directly understand and synthesize speech. However, an LLM-based strategy for modeling spoken dialogs remains elusive, calling for further investigation. This paper introduces an extensive speech-text LLM framework, the Unified Spoken Dialog Model (USDM), designed to generate coherent spoken responses with naturally occurring prosodic features relevant to the given input speech without relying on explicit automatic speech recognition (ASR) or text-to-speech (TTS) systems. We have verified the inclusion of prosody in speech tokens that predominantly contain semantic information and have used this foundation to construct a prosody-infused speech-text model. Additionally, we propose a generalized speech-text pretraining scheme that enhances the capture of cross-modal semantics. To construct USDM, we fine-tune our speech-text model on spoken dialog data using a multi-step spoken dialog template that stimulates the chain-of-reasoning capabilities exhibited by the underlying LLM. Automatic and human evaluations on the DailyTalk dataset demonstrate that our approach effectively generates natural-sounding spoken responses, surpassing previous and cascaded baselines. Our code and checkpoints are available at https://github.com/naver-ai/usdm.","url_abs":"https://arxiv.org/abs/2402.05706v3","url_pdf":"https://arxiv.org/pdf/2402.05706v3.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":"unified-speech-text-pretraining-for-spoken","repo_url":"https://github.com/naver-ai/usdm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"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":"text-to-speech","task_name":"Text to Speech"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"},{"task_slug":"text-to-speech-1","task_name":"text-to-speech"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2402.05706","atlas_url":"https://app.syntology.ai/?focus=2402.05706","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.05706"}},"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":"deterministic:regex_extraction","url":"https://github.com/naverai/usdm","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/naver-ai/usdm","reach":null}],"summary":{"ran":6,"ran_draft_wrong":3,"ran_honours":1,"unverified":5},"by_repo_kind":{"official":{"samples":15,"ran":10,"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":"cd64f7d57cb575c2","entry":"Attention","repo":"naver-ai/usdm","repo_kind":"official","path":"src/decoder/voicebox/model/voicebox.py","file_url":"https://github.com/naver-ai/usdm/blob/HEAD/src/decoder/voicebox/model/voicebox.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cd64f7d57cb575c2"}},{"code_sha256_prefix":"9e31ddf294975779","entry":"FeedForward","repo":"naver-ai/usdm","repo_kind":"official","path":"src/decoder/voicebox/model/voicebox.py","file_url":"https://github.com/naver-ai/usdm/blob/HEAD/src/decoder/voicebox/model/voicebox.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9e31ddf294975779"}},{"code_sha256_prefix":"76ec3a4a379092d1","entry":"GELUActivation","repo":"naver-ai/usdm","repo_kind":"official","path":"src/decoder/voicebox/model/voicebox.py","file_url":"https://github.com/naver-ai/usdm/blob/HEAD/src/decoder/voicebox/model/voicebox.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"76ec3a4a379092d1"}},{"code_sha256_prefix":"4ef3da2aa5df518b","entry":"PositionalConvEmbedding","repo":"naver-ai/usdm","repo_kind":"official","path":"src/decoder/voicebox/model/voicebox.py","file_url":"https://github.com/naver-ai/usdm/blob/HEAD/src/decoder/voicebox/model/voicebox.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4ef3da2aa5df518b"}},{"code_sha256_prefix":"0b4d4cc427b7879e","entry":"SamePadLayer","repo":"naver-ai/usdm","repo_kind":"official","path":"src/decoder/voicebox/model/voicebox.py","file_url":"https://github.com/naver-ai/usdm/blob/HEAD/src/decoder/voicebox/model/voicebox.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0b4d4cc427b7879e"}},{"code_sha256_prefix":"49d5a83de91032ba","entry":"SinusoidalPosEmb","repo":"naver-ai/usdm","repo_kind":"official","path":"src/decoder/voicebox/model/voicebox.py","file_url":"https://github.com/naver-ai/usdm/blob/HEAD/src/decoder/voicebox/model/voicebox.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"49d5a83de91032ba"}},{"code_sha256_prefix":"1e11052145a9ed66","entry":"default_template","repo":"naver-ai/usdm","repo_kind":"official","path":"src/inference.py","file_url":"https://github.com/naver-ai/usdm/blob/HEAD/src/inference.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1e11052145a9ed66"}},{"code_sha256_prefix":"10df2826f0da0e19","entry":"generate_bad_words_ids","repo":"naver-ai/usdm","repo_kind":"official","path":"src/inference.py","file_url":"https://github.com/naver-ai/usdm/blob/HEAD/src/inference.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"10df2826f0da0e19"}},{"code_sha256_prefix":"bb307ac322982165","entry":"get_slopes","repo":"naver-ai/usdm","repo_kind":"official","path":"src/decoder/voicebox/model/voicebox.py","file_url":"https://github.com/naver-ai/usdm/blob/HEAD/src/decoder/voicebox/model/voicebox.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bb307ac322982165"}},{"code_sha256_prefix":"f18f010e48c28da6","entry":"strip_exact_multiple","repo":"naver-ai/usdm","repo_kind":"official","path":"src/inference.py","file_url":"https://github.com/naver-ai/usdm/blob/HEAD/src/inference.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f18f010e48c28da6"}},{"code_sha256_prefix":"76cadc87e9fc55ed","entry":"BaseModule","repo":"naver-ai/usdm","repo_kind":"official","path":"src/decoder/voicebox/model/voicebox.py","file_url":"https://github.com/naver-ai/usdm/blob/HEAD/src/decoder/voicebox/model/voicebox.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"76cadc87e9fc55ed"}},{"code_sha256_prefix":"746887986ebb3d15","entry":"CFM","repo":"naver-ai/usdm","repo_kind":"official","path":"src/decoder/voicebox/model/voicebox.py","file_url":"https://github.com/naver-ai/usdm/blob/HEAD/src/decoder/voicebox/model/voicebox.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"746887986ebb3d15"}},{"code_sha256_prefix":"0fab6f9a64d4c3c8","entry":"EncoderLayer","repo":"naver-ai/usdm","repo_kind":"official","path":"src/decoder/voicebox/model/voicebox.py","file_url":"https://github.com/naver-ai/usdm/blob/HEAD/src/decoder/voicebox/model/voicebox.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0fab6f9a64d4c3c8"}},{"code_sha256_prefix":"b7eb5907afb39920","entry":"Transformer","repo":"naver-ai/usdm","repo_kind":"official","path":"src/decoder/voicebox/model/voicebox.py","file_url":"https://github.com/naver-ai/usdm/blob/HEAD/src/decoder/voicebox/model/voicebox.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b7eb5907afb39920"}},{"code_sha256_prefix":"4dbcdd53c470b5de","entry":"Voicebox","repo":"naver-ai/usdm","repo_kind":"official","path":"src/decoder/voicebox/model/voicebox.py","file_url":"https://github.com/naver-ai/usdm/blob/HEAD/src/decoder/voicebox/model/voicebox.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4dbcdd53c470b5de"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}