{"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/zero-shot-multi-speaker-text-to-speech-with","title":"Zero-Shot Multi-Speaker Text-To-Speech with State-of-the-art Neural Speaker Embeddings","arxiv_id":"1910.10838","date":"2019-10-23","proceeding":null,"authors":["Erica Cooper","Cheng-I Lai","Yusuke Yasuda","Fuming Fang","Xin Wang","Nanxin Chen","Junichi Yamagishi"],"abstract":"While speaker adaptation for end-to-end speech synthesis using speaker embeddings can produce good speaker similarity for speakers seen during training, there remains a gap for zero-shot adaptation to unseen speakers. We investigate multi-speaker modeling for end-to-end text-to-speech synthesis and study the effects of different types of state-of-the-art neural speaker embeddings on speaker similarity for unseen speakers. Learnable dictionary encoding-based speaker embeddings with angular softmax loss can improve equal error rates over x-vectors in a speaker verification task; these embeddings also improve speaker similarity and naturalness for unseen speakers when used for zero-shot adaptation to new speakers in end-to-end speech synthesis.","url_abs":"https://arxiv.org/abs/1910.10838v1","url_pdf":"https://arxiv.org/pdf/1910.10838v1.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":"zero-shot-multi-speaker-text-to-speech-with","repo_url":"https://github.com/nii-yamagishilab/multi-speaker-tacotron","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"zero-shot-multi-speaker-text-to-speech-with","repo_url":"https://github.com/jefflai108/pytorch-kaldi-neural-speaker-embeddings","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"zero-shot-multi-speaker-text-to-speech-with","repo_url":"https://github.com/keonlee9420/Comprehensive-Tacotron2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1910.10838","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.10838"}},"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/jefflai108/pytorch-kaldi-neural-speaker-embeddings","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/keonlee9420/Comprehensive-Tacotron2","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nii-yamagishilab/multi-speaker-tacotron","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"summary":{"ran":2,"ran_honours":1,"unverified":4},"by_repo_kind":{"listed":{"samples":7,"ran":3,"repositories":2}},"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":"2f8f70723c6fc25c","entry":"ComputeErrorRates","repo":"jefflai108/pytorch-kaldi-neural-speaker-embeddings","repo_kind":"listed","path":"local/compute_min_dcf.py","file_url":"https://github.com/jefflai108/pytorch-kaldi-neural-speaker-embeddings/blob/HEAD/local/compute_min_dcf.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"2f8f70723c6fc25c"}},{"code_sha256_prefix":"2e9b31102cfe118e","entry":"ComputeMinDcf","repo":"jefflai108/pytorch-kaldi-neural-speaker-embeddings","repo_kind":"listed","path":"local/compute_min_dcf.py","file_url":"https://github.com/jefflai108/pytorch-kaldi-neural-speaker-embeddings/blob/HEAD/local/compute_min_dcf.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"2e9b31102cfe118e"}},{"code_sha256_prefix":"a26f85d7c72ef39a","entry":"get_padding","repo":"keonlee9420/Comprehensive-Tacotron2","repo_kind":"listed","path":"hifigan/models.py","file_url":"https://github.com/keonlee9420/Comprehensive-Tacotron2/blob/HEAD/hifigan/models.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"code_sha256_prefix":"86780365dd768108","entry":"CheckArgs","repo":"jefflai108/pytorch-kaldi-neural-speaker-embeddings","repo_kind":"listed","path":"local/compute_min_dcf.py","file_url":"https://github.com/jefflai108/pytorch-kaldi-neural-speaker-embeddings/blob/HEAD/local/compute_min_dcf.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"86780365dd768108"}},{"code_sha256_prefix":"94f5ce4a61807513","entry":"prepare_music","repo":"jefflai108/pytorch-kaldi-neural-speaker-embeddings","repo_kind":"listed","path":"local/make_musan.py","file_url":"https://github.com/jefflai108/pytorch-kaldi-neural-speaker-embeddings/blob/HEAD/local/make_musan.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"94f5ce4a61807513"}},{"code_sha256_prefix":"20c0f408f04ba8f4","entry":"prepare_speech","repo":"jefflai108/pytorch-kaldi-neural-speaker-embeddings","repo_kind":"listed","path":"local/make_musan.py","file_url":"https://github.com/jefflai108/pytorch-kaldi-neural-speaker-embeddings/blob/HEAD/local/make_musan.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"20c0f408f04ba8f4"}},{"code_sha256_prefix":"5d14f1525bf40158","entry":"process_music_annotations","repo":"jefflai108/pytorch-kaldi-neural-speaker-embeddings","repo_kind":"listed","path":"local/make_musan.py","file_url":"https://github.com/jefflai108/pytorch-kaldi-neural-speaker-embeddings/blob/HEAD/local/make_musan.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"5d14f1525bf40158"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}