Papers › Efficiently Trainable Text-to-Speech System Based on Deep Convolutional Networks with...

Efficiently Trainable Text-to-Speech System Based on Deep Convolutional Networks with Guided Attention

24 Oct 2017arXiv:1710.08969archive 2025-07-28

Hideyuki Tachibana, Katsuya Uenoyama, Shunsuke Aihara

This paper describes a novel text-to-speech (TTS) technique based on deep convolutional neural networks (CNN), without use of any recurrent units. Recurrent neural networks (RNN) have become a standard technique to model sequential data recently, and this technique has been used in some cutting-edge neural TTS techniques. However, training RNN components often requires a very powerful computer, or a very long time, typically several days or weeks. Recent other studies, on the other hand, have shown that CNN-based sequence synthesis can be much faster than RNN-based techniques, because of high parallelizability. The objective of this paper is to show that an alternative neural TTS based only on CNN alleviate these economic costs of training. In our experiment, the proposed Deep Convolutional TTS was sufficiently trained overnight (15 hours), using an ordinary gaming PC equipped with two GPUs, while the quality of the synthesized speech was almost acceptable.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 28 code samples harvested from 5 repositories linked to this paper: 16 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 1 where Syntology's instrument failed) · 12 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 28 samples from 5 repositories, 16 ran (15 with no instrument failure; 1 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 4 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

22 repositories listed; official and paper-mentioned ones first.

CSTR-Edinburgh/ophelia mentioned on GitHubApache-2.0Syntology: 14 samples, 6 ran (0 instrument-failed) · 8 unverified report
Kyubyong/dc_tts mentioned on GitHubtfApache-2.0Syntology: 2 samples, 0 ran · 2 unverified report
Nvillaluenga/DC_TTS mentioned on GitHubtfSyntology: not harvested report
SeanPLeary/dc_tts-transfer-learning mentioned on GitHubtfSyntology: not harvested report
TartuNLP/deepvoice3_pytorch mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
adityapandya1/review-of-DCTTS mentioned on GitHubSyntology: not harvested report
alisterta/Persian-text-to-speech mentioned on GitHubtfSyntology: not harvested report
coqui-ai/TTS mentioned on GitHubpytorchMPL-2.0Syntology: not harvested report
creotiv/RussianTTS-Tacotron2 mentioned on GitHubpytorchSyntology: not harvested report
dimasikson/Audio-cleaning-with-Deep-Learning mentioned on GitHubtfSyntology: not harvested report
izzajalandoni/tts_models mentioned on GitHubpytorchBSD-3-ClauseSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to High Fidelity Speech Synthesis with Adversarial Networks (arXiv:1909.11646; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
jessearodriguez/LJ-Audio-dataset-generator mentioned on GitHubtfApache-2.0Syntology: not harvested report
keonlee9420/Comprehensive-Tacotron2 mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Zero-Shot Multi-Speaker Text-To-Speech with State-of-the-art Neural Speaker Embeddings (arXiv:1910.10838; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
keonlee9420/PortaSpeech mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to PortaSpeech: Portable and High-Quality Generative Text-to-Speech (arXiv:2109.15166; that paper's own run record: 12 ran (of which 1 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
merts1/dc_tts-turkish-implementation-T-rk-e-metinden-sese- mentioned on GitHubtfSyntology: not harvested report
merts1/dc_tts-turkish-implementation-Turkce-metinden-sese- mentioned on GitHubtfSyntology: not harvested report
noetits/ICE-Talk mentioned on GitHubtfApache-2.0Syntology: 8 samples, 6 ran (0 instrument-failed) · 2 unverified report
oliverwatts/ophelia mentioned on GitHubApache-2.0Syntology: not harvested report
r9y9/deepvoice3_pytorch mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
tiberiu44/TTS-Cube mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ClariNet: Parallel Wave Generation in End-to-End Text-to-Speech (arXiv:1807.07281; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
tugstugi/pytorch-dc-tts mentioned on GitHubpytorchMITSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
ung200/thats-what-obama-said mentioned on GitHubtfSyntology: not harvested 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

28 samples harvested: 16 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 1 where Syntology's instrument failed) · 12 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · our draft was wrong
15ran
12unverified

Licence: 1 of the 28 samples is 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 5 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

CSTR-Edinburgh/ophelia community (archive-listed) 14 samples, 6 ran (0 instrument-failed) · 8 unverified
basename libutil.py ran fingerprinted Apache-2.0 (permissive) · d8171e0ad0828450 · report fixture: signature fname:str/0/str · returned str · level recorded 2026-09-26
get_labels_indices data_load.py ran fingerprinted Apache-2.0 (permissive) · d6f8fc346bb63fa6 · report fixture: signature num_ind:int/0/int · returned ndarray · level recorded 2026-09-26
load_config in 389 papers configuration.py ran Apache-2.0 (permissive) · 324dd3942a2ddf83 · report fixture: signature config_fname:str/0/str · returned Hyperparams · level recorded 2026-09-26
load_vocab in 107 papers data_load.py ran Apache-2.0 (permissive) · ed89c632018002ae · report fixture: signature hp:HyperparameterConfig/0/? · returned tuple · level recorded 2026-09-26
read_norm_data libutil.py ran Apache-2.0 (permissive) · 7cf1ea807d160502 · report fixture: signature fname:str/0/str, stream_names:list/1/str · returned dict · level recorded 2026-09-26
text_normalize data_load.py ran Apache-2.0 (permissive) · bb87040e802a5688 · report fixture: signature text:str/0/str, hp:HyperparamConfig/0/? · returned str · level recorded 2026-09-26
AudioEnc networks.py unverified Apache-2.0 (permissive) · e4e0b7b26475d975 · report
MerlinTextEnc networks.py unverified Apache-2.0 (permissive) · c5cba2e8a4c727f2 · report
TextEnc networks.py unverified Apache-2.0 (permissive) · ba4c6a02fe3d374d · report
embed in 13 papers modules.py unverified Apache-2.0 (permissive) · 47b69c1525e362f1 · report
filter_variables_for_update architectures.py unverified Apache-2.0 (permissive) · c0429bb726c5e40c · report
learn_channel_contributions modules.py unverified Apache-2.0 (permissive) · ca18f95be1d5909c · report
readlist libutil.py unverified Apache-2.0 (permissive) · 3f081be1fc3120fa · report
Kyubyong/dc_tts community (archive-listed) 2 samples, 0 ran · 2 unverified
highwaynet modules.py unverified Apache-2.0 (permissive) · d549024a49fc32ba · report
noetits/ICE-Talk community (archive-listed) 8 samples, 6 ran (0 instrument-failed) · 2 unverified
closest_node perceptual_experiment/ice_tts_server.py ran Apache-2.0 (permissive) · d62d395f3bcbf830 · report fixture: signature node:ndarray/1/float, nodes:ndarray/2/float · returned int64 · level recorded 2026-09-26
closest_node server/ice_tts_server.py ran Apache-2.0 (permissive) · 57cd6ddf283c039d · report fixture: signature node:ndarray/1/float, nodes:ndarray/2/float · returned int64 · level recorded 2026-09-26
load_config in 389 papers configuration.py ran Apache-2.0 (permissive) · e7f70dd6bd569571 · report fixture: signature config_fname:str/0/str · returned Hyperparams · level recorded 2026-09-26
map_range perceptual_experiment/ice_tts_server.py ran Apache-2.0 (permissive) · 84dc7d3d58bc8567 · report fixture: signature x:float/0/float, x0:float/0/float, x1:float/0/float, y0:float/0/float, y1:float/0/float · returned float · level recorded 2026-09-26
map_range server/ice_tts_server.py ran Apache-2.0 (permissive) · 4e8579cfe6446a88 · report fixture: signature x:float/0/float, x0:float/0/float, x1:float/0/float, y0:float/0/float, y1:float/0/float · returned float · level recorded 2026-09-26
phones_normalize data_load.py ran Apache-2.0 (permissive) · a915021af11bdd1a · report fixture: signature text:str/0/str, char2idx:dict/0/?, speaker_code:str/0/str · returned list · level recorded 2026-09-26
Audio2Emo networks.py unverified Apache-2.0 (permissive) · 974c61cc45a1f486 · report
TextEnc networks.py unverified Apache-2.0 (permissive) · d2ca2d8a3bc33553 · report
r9y9/deepvoice3_pytorch community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
expand_speaker_embed deepvoice3_pytorch/deepvoice3.py ran · our draft was wrong fingerprinted licence not identified · pointer only · afbe89316d22c0f4 · report fixture: signature inputs_btc:Tensor/3/float, speaker_embed:Tensor/2/float, tdim:int/0/int · returned Tensor · level recorded 2026-09-22
tugstugi/pytorch-dc-tts community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
collate_fn in 500 papers datasets/data_loader.py ran MIT (permissive) · 7b716d9e1a746cbe · report fixture: signature batch:list/1/dict · returned dict · level recorded 2026-09-26
get_last_checkpoint_file_name utils.py ran fingerprinted MIT (permissive) · fdbf8a94e43df2cd · report fixture: signature logdir:str/0/str · returned str · level recorded 2026-09-26
load_checkpoint in 277 papers utils.py ran MIT (permissive) · 6ee51bc0f357e66f · report fixture: signature checkpoint_file_name:str/0/str, model:callable/0/?, optimizer:SGD/0/? · returned tuple · level recorded 2026-09-26

Tasks

Text to SpeechText-To-Speech Synthesistext-to-speech

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1D CNN

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