{"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/fewer-token-neural-speech-codec-with-time","title":"Fewer-token Neural Speech Codec with Time-invariant Codes","arxiv_id":"2310.00014","date":"2023-09-15","proceeding":null,"authors":["Yong Ren","Tao Wang","Jiangyan Yi","Le Xu","Jianhua Tao","Chuyuan Zhang","Junzuo Zhou"],"abstract":"Language model based text-to-speech (TTS) models, like VALL-E, have gained attention for their outstanding in-context learning capability in zero-shot scenarios. Neural speech codec is a critical component of these models, which can convert speech into discrete token representations. However, excessive token sequences from the codec may negatively affect prediction accuracy and restrict the progression of Language model based TTS models. To address this issue, this paper proposes a novel neural speech codec with time-invariant codes named TiCodec. By encoding and quantizing time-invariant information into a separate code, TiCodec can reduce the amount of frame-level information that needs encoding, effectively decreasing the number of tokens as codes of speech. Furthermore, this paper introduces a time-invariant encoding consistency loss to enhance the consistency of time-invariant code within an utterance and force it to capture more global information, which can benefit the zero-shot TTS task. Experimental results demonstrate that TiCodec can not only enhance the quality of reconstruction speech with fewer tokens but also increase the similarity and naturalness, as well as reduce the word error rate of the synthesized speech by the TTS model.","url_abs":"https://arxiv.org/abs/2310.00014v2","url_pdf":"https://arxiv.org/pdf/2310.00014v2.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":"fewer-token-neural-speech-codec-with-time","repo_url":"https://github.com/y-ren16/ticodec","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.00014","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.00014"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/y-ren16/ticodec","reach":{"status":"ok"}}],"summary":{"ran":4,"ran_draft_wrong":1,"unverified":4},"by_repo_kind":{"official":{"samples":9,"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":9,"samples":[{"code_sha256_prefix":"407da000922ac538","entry":"apply_parametrization_norm","repo":"y-ren16/ticodec","repo_kind":"official","path":"academicodec/modules/conv.py","file_url":"https://github.com/y-ren16/ticodec/blob/HEAD/academicodec/modules/conv.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"407da000922ac538"}},{"code_sha256_prefix":"7137577cbef51217","entry":"discriminator_loss","repo":"y-ren16/ticodec","repo_kind":"official","path":"academicodec/models/ticodec/models.py","file_url":"https://github.com/y-ren16/ticodec/blob/HEAD/academicodec/models/ticodec/models.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7137577cbef51217"}},{"code_sha256_prefix":"e453b51f0ed5fb28","entry":"feature_loss","repo":"y-ren16/ticodec","repo_kind":"official","path":"academicodec/models/ticodec/models.py","file_url":"https://github.com/y-ren16/ticodec/blob/HEAD/academicodec/models/ticodec/models.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e453b51f0ed5fb28"}},{"code_sha256_prefix":"1a9d74439d969cfd","entry":"generator_loss","repo":"y-ren16/ticodec","repo_kind":"official","path":"academicodec/models/ticodec/models.py","file_url":"https://github.com/y-ren16/ticodec/blob/HEAD/academicodec/models/ticodec/models.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1a9d74439d969cfd"}},{"code_sha256_prefix":"88bf809d1bc9db4c","entry":"sequence_mask","repo":"y-ren16/ticodec","repo_kind":"official","path":"academicodec/models/ticodec/speakenc.py","file_url":"https://github.com/y-ren16/ticodec/blob/HEAD/academicodec/models/ticodec/speakenc.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"88bf809d1bc9db4c"}},{"code_sha256_prefix":"be031b15a988a556","entry":"dynamic_range_compression","repo":"y-ren16/ticodec","repo_kind":"official","path":"academicodec/models/ticodec/meldataset.py","file_url":"https://github.com/y-ren16/ticodec/blob/HEAD/academicodec/models/ticodec/meldataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"be031b15a988a556"}},{"code_sha256_prefix":"9e30e7d510c9d341","entry":"dynamic_range_decompression","repo":"y-ren16/ticodec","repo_kind":"official","path":"academicodec/models/ticodec/meldataset.py","file_url":"https://github.com/y-ren16/ticodec/blob/HEAD/academicodec/models/ticodec/meldataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9e30e7d510c9d341"}},{"code_sha256_prefix":"8d9aa381c6147164","entry":"get_extra_padding_for_conv1d","repo":"y-ren16/ticodec","repo_kind":"official","path":"academicodec/modules/conv.py","file_url":"https://github.com/y-ren16/ticodec/blob/HEAD/academicodec/modules/conv.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8d9aa381c6147164"}},{"code_sha256_prefix":"ceb9db5dc46e3669","entry":"read_ecdc_header","repo":"y-ren16/ticodec","repo_kind":"official","path":"academicodec/binary.py","file_url":"https://github.com/y-ren16/ticodec/blob/HEAD/academicodec/binary.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ceb9db5dc46e3669"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}