Papers › Towards Building Text-To-Speech Systems for the Next Billion Users

Towards Building Text-To-Speech Systems for the Next Billion Users

17 Nov 2022arXiv:2211.09536archive 2025-07-28

Gokul Karthik Kumar, Praveen S V, Pratyush Kumar, Mitesh M. Khapra, Karthik Nandakumar

Deep learning based text-to-speech (TTS) systems have been evolving rapidly with advances in model architectures, training methodologies, and generalization across speakers and languages. However, these advances have not been thoroughly investigated for Indian language speech synthesis. Such investigation is computationally expensive given the number and diversity of Indian languages, relatively lower resource availability, and the diverse set of advances in neural TTS that remain untested. In this paper, we evaluate the choice of acoustic models, vocoders, supplementary loss functions, training schedules, and speaker and language diversity for Dravidian and Indo-Aryan languages. Based on this, we identify monolingual models with FastPitch and HiFi-GAN V1, trained jointly on male and female speakers to perform the best. With this setup, we train and evaluate TTS models for 13 languages and find our models to significantly improve upon existing models in all languages as measured by mean opinion scores. We open-source all models on the Bhashini platform.

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

The archive's official repository (gokulkarthik/text2speech) was not harvested; the 1 sample below comes from 1 community repository.

Syntology 1 code sample harvested from 1 repository linked to this paper: 1 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; 0 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 1 sample from 1 repository, 1 ran (1 with no instrument failure; 0 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.

Levels written on 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

gokulkarthik/text2speech officialmentioned on GitHubpytorchSyntology: not harvested report
ai4bharat/indic-tts mentioned on GitHubpytorchMITSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified 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

1 sample harvested: 1 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; 0 where Syntology's instrument failed) · 0 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

Licence: 0 of the 1 sample 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 ai4bharat/indic-tts. “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.

ai4bharat/indic-tts community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
formatter_indictts vocoder.py ran MIT (permissive) · d8144ca77e15f25f · report fixture: signature root_path:str/0/str, meta_file:str/0/str · returned list · level recorded 2026-09-25

Tasks

DiversitySpeech SynthesisSpeech Synthesis - AssameseSpeech Synthesis - BengaliSpeech Synthesis - BodoSpeech Synthesis - GujaratiSpeech Synthesis - HindiSpeech Synthesis - KannadaSpeech Synthesis - MalayalamSpeech Synthesis - ManipuriSpeech Synthesis - MarathiSpeech Synthesis - RajasthaniSpeech Synthesis - TamilSpeech Synthesis - TeluguText to SpeechText-To-Speech Synthesistext-to-speech

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Speech Synthesis - Assamese IndicTTS AI4BharatTTS - FastPitch with HiFiGAN Mean Opinion Score 2.39 #1 of 1 Archive leaderboard report
Speech Synthesis - Bengali IndicTTS AI4BharatTTS - FastPitch with HiFiGAN Mean Opinion Score 3.37 #1 of 1 Archive leaderboard report
Speech Synthesis - Bodo IndicTTS AI4BharatTTS - FastPitch with HiFiGAN Mean Opinion Score 3.53 #1 of 1 Archive leaderboard report
Speech Synthesis - Gujarati IndicTTS AI4BharatTTS - FastPitch with HiFiGAN Mean Opinion Score 3.58 #1 of 1 Archive leaderboard report
Speech Synthesis - Hindi IndicTTS AI4BharatTTS - FastPitch with HiFiGAN Mean Opinion Score 4.00 #1 of 1 Archive leaderboard report
Speech Synthesis - Kannada IndicTTS AI4BharatTTS - FastPitch with HiFiGAN Mean Opinion Score 3.68 #1 of 1 Archive leaderboard report
Speech Synthesis - Malayalam IndicTTS AI4BharatTTS - FastPitch with HiFiGAN Mean Opinion Score 3.64 #1 of 1 Archive leaderboard report
Speech Synthesis - Manipuri IndicTTS AI4BharatTTS - FastPitch with HiFiGAN Mean Opinion Score 3.30 #1 of 1 Archive leaderboard report
Speech Synthesis - Marathi IndicTTS AI4BharatTTS - FastPitch with HiFiGAN Mean Opinion Score 3.26 #1 of 1 Archive leaderboard report
Speech Synthesis - Rajasthani IndicTTS AI4BharatTTS - FastPitch with HiFiGAN Mean Opinion Score 3.40 #1 of 1 Archive leaderboard report
Speech Synthesis - Tamil IndicTTS AI4BharatTTS - FastPitch with HiFiGAN Mean Opinion Score 3.84 #1 of 1 Archive leaderboard report
Speech Synthesis - Telugu IndicTTS AI4BharatTTS - FastPitch with HiFiGAN Mean Opinion Score 3.66 #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

AttentionConvolutionDense ConnectionsFastPitchHiFi-GANLayer NormalizationLinear LayerMulti-Head AttentionResidual ConnectionSoftmax

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