Papers › Deep Voice: Real-time Neural Text-to-Speech

Deep Voice: Real-time Neural Text-to-Speech

25 Feb 2017ICML 2017 8arXiv:1702.07825archive 2025-07-28

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

We present Deep Voice, a production-quality text-to-speech system constructed entirely from deep neural networks. Deep Voice lays the groundwork for truly end-to-end neural speech synthesis. The system comprises five major building blocks: a segmentation model for locating phoneme boundaries, a grapheme-to-phoneme conversion model, a phoneme duration prediction model, a fundamental frequency prediction model, and an audio synthesis model. For the segmentation model, we propose a novel way of performing phoneme boundary detection with deep neural networks using connectionist temporal classification (CTC) loss. For the audio synthesis model, we implement a variant of WaveNet that requires fewer parameters and trains faster than the original. By using a neural network for each component, our system is simpler and more flexible than traditional text-to-speech systems, where each component requires laborious feature engineering and extensive domain expertise. Finally, we show that inference with our system can be performed faster than real time and describe optimized WaveNet inference kernels on both CPU and GPU that achieve up to 400x speedups over existing implementations.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1702.07825")

Code

Syntology Ran 0 of 8 code samples harvested from 1 repository linked to this paper; 8 have no recorded run.

By repository: community (archive-listed): 8 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

NVIDIA/nv-wavenet mentioned on GitHubpytorchBSD-3-Clause report
prijatelj/crowd_noise mentioned on GitHubtf report
shortpoet/Final-Project mentioned on GitHub report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

8 samples harvested; 0 ran; 0 honoured the contract we drafted; 8 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

8unverified

Licence: 0 of the 8 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from NVIDIA/nv-wavenet. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

apply_gradient_allreduce NVIDIA/nv-wavenet/pytorch/distributed.py community (archive-listed) unverified BSD-3-Clause (permissive) · 32c820effc6374df · report
chunker NVIDIA/nv-wavenet/pytorch/inference.py community (archive-listed) unverified BSD-3-Clause (permissive) · 1130729f85801be6 · report
column_major NVIDIA/nv-wavenet/pytorch/nv_wavenet.py community (archive-listed) unverified BSD-3-Clause (permissive) · 51a7e4dc35ecf4cd · report
files_to_list NVIDIA/nv-wavenet/pytorch/utils.py community (archive-listed) unverified BSD-3-Clause (permissive) · 6e8184ff4faf3139 · report
interleave_lists NVIDIA/nv-wavenet/pytorch/nv_wavenet.py community (archive-listed) unverified BSD-3-Clause (permissive) · 3e81021da6bab249 · report
load_filepaths_and_text NVIDIA/nv-wavenet/pytorch/utils.py community (archive-listed) unverified BSD-3-Clause (permissive) · ddc7f9cc1be46004 · report
load_wav_to_torch NVIDIA/nv-wavenet/pytorch/utils.py community (archive-listed) unverified BSD-3-Clause (permissive) · 51d04ef582017e5d · report
reduce_tensor NVIDIA/nv-wavenet/pytorch/distributed.py community (archive-listed) unverified BSD-3-Clause (permissive) · 720ec6edbf432e1e · report

Tasks

Audio SynthesisBoundary DetectionFeature EngineeringSpeech SynthesisText to Speechtext-to-speech

3 archive task tags without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Dilated Causal ConvolutionMixture of Logistic DistributionsWaveNet

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections