{"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/pslm-parallel-generation-of-text-and-speech","title":"PSLM: Parallel Generation of Text and Speech with LLMs for Low-Latency Spoken Dialogue Systems","arxiv_id":"2406.12428","date":"2024-06-18","proceeding":null,"authors":["Kentaro Mitsui","Koh Mitsuda","Toshiaki Wakatsuki","Yukiya Hono","Kei Sawada"],"abstract":"Multimodal language models that process both text and speech have a potential for applications in spoken dialogue systems. However, current models face two major challenges in response generation latency: (1) generating a spoken response requires the prior generation of a written response, and (2) speech sequences are significantly longer than text sequences. This study addresses these issues by extending the input and output sequences of the language model to support the parallel generation of text and speech. Our experiments on spoken question answering tasks demonstrate that our approach improves latency while maintaining the quality of response content. Additionally, we show that latency can be further reduced by generating speech in multiple sequences. Demo samples are available at https://rinnakk.github.io/research/publications/PSLM.","url_abs":"https://arxiv.org/abs/2406.12428v2","url_pdf":"https://arxiv.org/pdf/2406.12428v2.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":"pslm-parallel-generation-of-text-and-speech","repo_url":"https://github.com/eleutherai/gpt-neox","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"response-generation","task_name":"Response Generation"},{"task_slug":"spoken-dialogue-systems","task_name":"Spoken Dialogue Systems"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2406.12428","atlas_url":"https://app.syntology.ai/?focus=2406.12428","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12428"}},"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/eleutherai/gpt-neox","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":3,"unverified":5},"by_repo_kind":{"official":{"samples":8,"ran":3,"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":"8b9c3d0602aaf347","entry":"extract_markdown_default","repo":"eleutherai/gpt-neox","repo_kind":"official","path":"configs/neox_args_sync.py","file_url":"https://github.com/eleutherai/gpt-neox/blob/HEAD/configs/neox_args_sync.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":"8b9c3d0602aaf347"}},{"code_sha256_prefix":"53f8236a7d4057b0","entry":"extract_markdown_description","repo":"eleutherai/gpt-neox","repo_kind":"official","path":"configs/neox_args_sync.py","file_url":"https://github.com/eleutherai/gpt-neox/blob/HEAD/configs/neox_args_sync.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":"53f8236a7d4057b0"}},{"code_sha256_prefix":"813543c3a6d7b9d1","entry":"normalize_description","repo":"eleutherai/gpt-neox","repo_kind":"official","path":"configs/neox_args_sync.py","file_url":"https://github.com/eleutherai/gpt-neox/blob/HEAD/configs/neox_args_sync.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"813543c3a6d7b9d1"}},{"code_sha256_prefix":"69002400aad5a8a6","entry":"get_checkpoint_tag","repo":"eleutherai/gpt-neox","repo_kind":"official","path":"megatron/checkpointing.py","file_url":"https://github.com/eleutherai/gpt-neox/blob/HEAD/megatron/checkpointing.py","link_basis":"harvester_set","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":"69002400aad5a8a6"}},{"code_sha256_prefix":"d5081f28e2befd2c","entry":"get_docs","repo":"eleutherai/gpt-neox","repo_kind":"official","path":"configs/gen_docs.py","file_url":"https://github.com/eleutherai/gpt-neox/blob/HEAD/configs/gen_docs.py","link_basis":"harvester_set","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":"d5081f28e2befd2c"}},{"code_sha256_prefix":"3a5fc202b5d9ec24","entry":"monitor_method_cuda_wall_times","repo":"eleutherai/gpt-neox","repo_kind":"official","path":"megatron/devutil.py","file_url":"https://github.com/eleutherai/gpt-neox/blob/HEAD/megatron/devutil.py","link_basis":"harvester_set","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":"3a5fc202b5d9ec24"}},{"code_sha256_prefix":"50c9c165cf801f59","entry":"pairwise","repo":"eleutherai/gpt-neox","repo_kind":"official","path":"configs/gen_docs.py","file_url":"https://github.com/eleutherai/gpt-neox/blob/HEAD/configs/gen_docs.py","link_basis":"harvester_set","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":"50c9c165cf801f59"}},{"code_sha256_prefix":"64dd872a8ac47294","entry":"to_md","repo":"eleutherai/gpt-neox","repo_kind":"official","path":"configs/gen_docs.py","file_url":"https://github.com/eleutherai/gpt-neox/blob/HEAD/configs/gen_docs.py","link_basis":"harvester_set","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":"64dd872a8ac47294"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}