{"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/deep-voice-3-scaling-text-to-speech-with","title":"Deep Voice 3: Scaling Text-to-Speech with Convolutional Sequence Learning","arxiv_id":"1710.07654","date":"2017-10-20","proceeding":"ICLR 2018 1","authors":["Wei Ping","Kainan Peng","Andrew Gibiansky","Sercan O. Arik","Ajay Kannan","Sharan Narang","Jonathan Raiman","John Miller"],"abstract":"We present Deep Voice 3, a fully-convolutional attention-based neural\ntext-to-speech (TTS) system. Deep Voice 3 matches state-of-the-art neural\nspeech synthesis systems in naturalness while training ten times faster. We\nscale Deep Voice 3 to data set sizes unprecedented for TTS, training on more\nthan eight hundred hours of audio from over two thousand speakers. In addition,\nwe identify common error modes of attention-based speech synthesis networks,\ndemonstrate how to mitigate them, and compare several different waveform\nsynthesis methods. We also describe how to scale inference to ten million\nqueries per day on one single-GPU server.","url_abs":"http://arxiv.org/abs/1710.07654v3","url_pdf":"http://arxiv.org/pdf/1710.07654v3.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":"deep-voice-3-scaling-text-to-speech-with","repo_url":"https://github.com/HaiFengZeng/clari_wavenet_vocoder","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"deep-voice-3-scaling-text-to-speech-with","repo_url":"https://github.com/TartuNLP/deepvoice3_pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"deep-voice-3-scaling-text-to-speech-with","repo_url":"https://github.com/kaiidams/voice100","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"deep-voice-3-scaling-text-to-speech-with","repo_url":"https://github.com/kaiidams/voice100-tts","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"deep-voice-3-scaling-text-to-speech-with","repo_url":"https://github.com/kinimod23/ATS_Project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"deep-voice-3-scaling-text-to-speech-with","repo_url":"https://github.com/mitsu-h/deepvoice3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"deep-voice-3-scaling-text-to-speech-with","repo_url":"https://github.com/r9y9/deepvoice3_pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"speech-synthesis","task_name":"Speech Synthesis"},{"task_slug":"text-to-speech","task_name":"Text to Speech"},{"task_slug":"text-to-speech-1","task_name":"text-to-speech"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dv3-attention-block","method_name":"DV3 Attention Block"},{"method_slug":"dv3-convolution-block","method_name":"DV3 Convolution Block"},{"method_slug":"deep-voice-3","method_name":"Deep Voice 3"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dilated-causal-convolution","method_name":"Dilated Causal Convolution"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"glu","method_name":"Gated Linear Unit"},{"method_slug":"gradient-clipping","method_name":"Gradient Clipping"},{"method_slug":"griffin-lim-algorithm","method_name":"Griffin-Lim Algorithm"},{"method_slug":"l1-regularization","method_name":"L1 Regularization"},{"method_slug":"mixture-of-logistic-distributions","method_name":"Mixture of Logistic Distributions"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"softsign-activation","method_name":"Softsign Activation"},{"method_slug":"wavenet","method_name":"WaveNet"},{"method_slug":"weight-normalization","method_name":"Weight Normalization"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1710.07654","atlas_url":"https://app.syntology.ai/?focus=1710.07654","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.07654"}},"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/kaiidams/voice100-tts","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/HaiFengZeng/clari_wavenet_vocoder","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mitsu-h/deepvoice3","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kinimod23/ATS_Project","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/r9y9/deepvoice3_pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kaiidams/voice100","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/TartuNLP/deepvoice3_pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{},"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":1,"samples":[{"code_sha256_prefix":"afbe89316d22c0f4","entry":"expand_speaker_embed","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"afbe89316d22c0f4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}