{"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/dualcodec-a-low-frame-rate-semantically-1","title":"DualCodec: A Low-Frame-Rate, Semantically-Enhanced Neural Audio Codec for Speech Generation","arxiv_id":"2505.13000","date":"2025-05-19","proceeding":null,"authors":["Jiaqi Li","Xiaolong Lin","Zhekai Li","Shixi Huang","Yuancheng Wang","Chaoren Wang","Zhenpeng Zhan","Zhizheng Wu"],"abstract":"Neural audio codecs form the foundational building blocks for language model (LM)-based speech generation. Typically, there is a trade-off between frame rate and audio quality. This study introduces a low-frame-rate, semantically enhanced codec model. Existing approaches distill semantically rich self-supervised (SSL) representations into the first-layer codec tokens. This work proposes DualCodec, a dual-stream encoding approach that integrates SSL and waveform representations within an end-to-end codec framework. In this setting, DualCodec enhances the semantic information in the first-layer codec and enables the codec system to maintain high audio quality while operating at a low frame rate. Note that a low-frame-rate codec improves the efficiency of speech generation. Experimental results on audio codec and speech generation tasks confirm the effectiveness of the proposed DualCodec compared to state-of-the-art codec systems, such as Mimi Codec, SpeechTokenizer, DAC, and Encodec. Demos are available at: https://dualcodec.github.io, code is available at: https://github.com/jiaqili3/DualCodec","url_abs":"https://arxiv.org/abs/2505.13000v1","url_pdf":"https://arxiv.org/pdf/2505.13000v1.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":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"dualcodec-a-low-frame-rate-semantically-1","repo_url":"https://github.com/jiaqili3/DualCodec","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2505.13000","atlas_url":"https://app.syntology.ai/?focus=2505.13000","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.13000"}},"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/jiaqili3/DualCodec","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":6,"ran_fixture":1,"unverified":1},"by_repo_kind":{"official":{"samples":8,"ran":7,"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":"ceaa742d42b41c00","entry":"batch","repo":"jiaqili3/DualCodec","repo_kind":"official","path":"dualcodec/dataset/processor.py","file_url":"https://github.com/jiaqili3/DualCodec/blob/HEAD/dualcodec/dataset/processor.py","link_basis":"harvester_set","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":"ceaa742d42b41c00"}},{"code_sha256_prefix":"d548fecaa09ac280","entry":"pad_to_length","repo":"jiaqili3/DualCodec","repo_kind":"official","path":"dualcodec/model_codec/dac_model.py","file_url":"https://github.com/jiaqili3/DualCodec/blob/HEAD/dualcodec/model_codec/dac_model.py","link_basis":"harvester_set","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":"d548fecaa09ac280"}},{"code_sha256_prefix":"6be4da9d721293fb","entry":"prepare_gluster_dataset","repo":"jiaqili3/DualCodec","repo_kind":"official","path":"dualcodec/dataset/dataset.py","file_url":"https://github.com/jiaqili3/DualCodec/blob/HEAD/dualcodec/dataset/dataset.py","link_basis":"harvester_set","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":"6be4da9d721293fb"}},{"code_sha256_prefix":"d02d287ae67db103","entry":"read_json_lists","repo":"jiaqili3/DualCodec","repo_kind":"official","path":"dualcodec/dataset/file_utils.py","file_url":"https://github.com/jiaqili3/DualCodec/blob/HEAD/dualcodec/dataset/file_utils.py","link_basis":"harvester_set","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":"d02d287ae67db103"}},{"code_sha256_prefix":"76cb8017cf220876","entry":"read_lists","repo":"jiaqili3/DualCodec","repo_kind":"official","path":"dualcodec/dataset/file_utils.py","file_url":"https://github.com/jiaqili3/DualCodec/blob/HEAD/dualcodec/dataset/file_utils.py","link_basis":"harvester_set","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":"76cb8017cf220876"}},{"code_sha256_prefix":"f247e4748f379a76","entry":"snake","repo":"jiaqili3/DualCodec","repo_kind":"official","path":"dualcodec/model_codec/dac_layers.py","file_url":"https://github.com/jiaqili3/DualCodec/blob/HEAD/dualcodec/model_codec/dac_layers.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f247e4748f379a76"}},{"code_sha256_prefix":"06cc7e2f6e744cda","entry":"tokenize","repo":"jiaqili3/DualCodec","repo_kind":"official","path":"dualcodec/dataset/processor.py","file_url":"https://github.com/jiaqili3/DualCodec/blob/HEAD/dualcodec/dataset/processor.py","link_basis":"harvester_set","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":"06cc7e2f6e744cda"}},{"code_sha256_prefix":"dc6ecd768e01e65d","entry":"Dataset","repo":"jiaqili3/DualCodec","repo_kind":"official","path":"dualcodec/dataset/dataset.py","file_url":"https://github.com/jiaqili3/DualCodec/blob/HEAD/dualcodec/dataset/dataset.py","link_basis":"harvester_set","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":"dc6ecd768e01e65d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}