{"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-real-time-neural-text-to-speech","title":"Deep Voice: Real-time Neural Text-to-Speech","arxiv_id":"1702.07825","date":"2017-02-25","proceeding":"ICML 2017 8","authors":["Sercan O. Arik","Mike Chrzanowski","Adam Coates","Gregory Diamos","Andrew Gibiansky","Yongguo Kang","Xi-An Li","John Miller","Andrew Ng","Jonathan Raiman","Shubho Sengupta","Mohammad Shoeybi"],"abstract":"We present Deep Voice, a production-quality text-to-speech system constructed\nentirely from deep neural networks. Deep Voice lays the groundwork for truly\nend-to-end neural speech synthesis. The system comprises five major building\nblocks: a segmentation model for locating phoneme boundaries, a\ngrapheme-to-phoneme conversion model, a phoneme duration prediction model, a\nfundamental frequency prediction model, and an audio synthesis model. For the\nsegmentation model, we propose a novel way of performing phoneme boundary\ndetection with deep neural networks using connectionist temporal classification\n(CTC) loss. For the audio synthesis model, we implement a variant of WaveNet\nthat requires fewer parameters and trains faster than the original. By using a\nneural network for each component, our system is simpler and more flexible than\ntraditional text-to-speech systems, where each component requires laborious\nfeature engineering and extensive domain expertise. Finally, we show that\ninference with our system can be performed faster than real time and describe\noptimized WaveNet inference kernels on both CPU and GPU that achieve up to 400x\nspeedups over existing implementations.","url_abs":"http://arxiv.org/abs/1702.07825v2","url_pdf":"http://arxiv.org/pdf/1702.07825v2.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-real-time-neural-text-to-speech","repo_url":"https://github.com/NVIDIA/nv-wavenet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"deep-voice-real-time-neural-text-to-speech","repo_url":"https://github.com/prijatelj/crowd_noise","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"deep-voice-real-time-neural-text-to-speech","repo_url":"https://github.com/shortpoet/Final-Project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"audio-synthesis","task_name":"Audio Synthesis"},{"task_slug":"boundary-detection","task_name":"Boundary Detection"},{"task_slug":null,"task_name":"CPU"},{"task_slug":"feature-engineering","task_name":"Feature Engineering"},{"task_slug":null,"task_name":"GPU"},{"task_slug":null,"task_name":"Grapheme-to-Phoneme Conversion"},{"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":"dilated-causal-convolution","method_name":"Dilated Causal Convolution"},{"method_slug":"mixture-of-logistic-distributions","method_name":"Mixture of Logistic Distributions"},{"method_slug":"wavenet","method_name":"WaveNet"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1702.07825","atlas_url":"https://app.syntology.ai/?focus=1702.07825","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1702.07825"}},"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/NVIDIA/nv-wavenet","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shortpoet/Final-Project","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/prijatelj/crowd_noise","reach":{"status":"ok"}}],"summary":{"unverified":8},"by_repo_kind":{"listed":{"samples":8,"ran":0,"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":"32c820effc6374df","entry":"apply_gradient_allreduce","repo":"NVIDIA/nv-wavenet","repo_kind":"listed","path":"pytorch/distributed.py","file_url":"https://github.com/NVIDIA/nv-wavenet/blob/HEAD/pytorch/distributed.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":"32c820effc6374df"}},{"code_sha256_prefix":"1130729f85801be6","entry":"chunker","repo":"NVIDIA/nv-wavenet","repo_kind":"listed","path":"pytorch/inference.py","file_url":"https://github.com/NVIDIA/nv-wavenet/blob/HEAD/pytorch/inference.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":"1130729f85801be6"}},{"code_sha256_prefix":"51a7e4dc35ecf4cd","entry":"column_major","repo":"NVIDIA/nv-wavenet","repo_kind":"listed","path":"pytorch/nv_wavenet.py","file_url":"https://github.com/NVIDIA/nv-wavenet/blob/HEAD/pytorch/nv_wavenet.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":"51a7e4dc35ecf4cd"}},{"code_sha256_prefix":"6e8184ff4faf3139","entry":"files_to_list","repo":"NVIDIA/nv-wavenet","repo_kind":"listed","path":"pytorch/utils.py","file_url":"https://github.com/NVIDIA/nv-wavenet/blob/HEAD/pytorch/utils.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":"6e8184ff4faf3139"}},{"code_sha256_prefix":"3e81021da6bab249","entry":"interleave_lists","repo":"NVIDIA/nv-wavenet","repo_kind":"listed","path":"pytorch/nv_wavenet.py","file_url":"https://github.com/NVIDIA/nv-wavenet/blob/HEAD/pytorch/nv_wavenet.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":"3e81021da6bab249"}},{"code_sha256_prefix":"ddc7f9cc1be46004","entry":"load_filepaths_and_text","repo":"NVIDIA/nv-wavenet","repo_kind":"listed","path":"pytorch/utils.py","file_url":"https://github.com/NVIDIA/nv-wavenet/blob/HEAD/pytorch/utils.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":"ddc7f9cc1be46004"}},{"code_sha256_prefix":"51d04ef582017e5d","entry":"load_wav_to_torch","repo":"NVIDIA/nv-wavenet","repo_kind":"listed","path":"pytorch/utils.py","file_url":"https://github.com/NVIDIA/nv-wavenet/blob/HEAD/pytorch/utils.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":"51d04ef582017e5d"}},{"code_sha256_prefix":"720ec6edbf432e1e","entry":"reduce_tensor","repo":"NVIDIA/nv-wavenet","repo_kind":"listed","path":"pytorch/distributed.py","file_url":"https://github.com/NVIDIA/nv-wavenet/blob/HEAD/pytorch/distributed.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":"720ec6edbf432e1e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}