Skip to content
AI News HubLIVE
Original source2 min read

The TTS-STT Flywheel: Synthetic Entity-Dense Audio Closes the Indic ASR Gap Where Commercial and Open-Source Systems Fail

Summary

Open-source and commercial ASR systems perform poorly on niche-domain Indic speech recognition tasks such as digit strings, currency amounts, addresses, and code-mixed phrases. This paper proposes a TTS-STT flywheel that generates ~22,000 synthetic entity-dense utterances, achieving an entity hit rate (EHR) of 0.98 on a Telugu test set, compared to 0.027 for the best open-source model and 0.16 for a commercial system. Code, data, and dictionaries are open-sourced.

SourcearXiv Computational LinguisticsAuthor: Venkata Pushpak Teja Menta
The TTS-STT Flywheel: Synthetic Entity-Dense Audio Closes the Indic ASR Gap Where Commercial and Open-Source Systems Fail
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[2605.03073] The TTS-STT Flywheel: Synthetic Entity-Dense Audio Closes the Indic ASR Gap Where Commercial and Open-Source Systems Fail

Skip to main content

Learn about arXiv becoming an independent nonprofit.

We gratefully acknowledge support from the Simons Foundation, member institutions, and all contributors. Donate

> cs > arXiv:2605.03073

Help | Advanced Search

All fields Title Author Abstract Comments Journal reference ACM classification MSC classification Report number arXiv identifier DOI ORCID arXiv author ID Help pages Full text

Search

GO

quick links

Login

Help Pages

About

-->

Computer Science > Computation and Language

arXiv:2605.03073 (cs)

[Submitted on 4 May 2026]

Title:The TTS-STT Flywheel: Synthetic Entity-Dense Audio Closes the Indic ASR Gap Where Commercial and Open-Source Systems Fail

Authors:Venkata Pushpak Teja Menta

View a PDF of the paper titled The TTS-STT Flywheel: Synthetic Entity-Dense Audio Closes the Indic ASR Gap Where Commercial and Open-Source Systems Fail, by Venkata Pushpak Teja Menta

View PDF HTML (experimental)

Abstract:Niche-domain Indic ASR -- digit strings, currency amounts, addresses, brand names, English/Indic codemix -- is under-served by both open-source SOTA and commercial systems. On a synthesised entity-dense Telugu test set (held-out by synthesis system), vasista22/whisper-telugu-large-v2 (open SOTA) achieves Entity-Hit-Rate (EHR) 0.027 and Deepgram Nova-3 (commercial) 0.16. We close this gap with a self-contained TTSSTT flywheel: an open-source Indic TTS pipeline synthesises ~22,000 entity-dense Indic-English code-mix utterances at = 0.98. Code, holdouts, predictions, EDSA corpus, and entity dictionaries are released open-source.

Comments: 8 pages, 2 figures. Companion to arXiv:2604.25441 (Praxy Voice TTS), arXiv:2604.25476 (PSP), arXiv:2605.00777 (LASE)

Subjects:

Computation and Language (cs.CL); Sound (cs.SD)

Cite as: arXiv:2605.03073 [cs.CL]

(or arXiv:2605.03073v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2605.03073

Focus to learn more

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Venkata Pushpak Teja Menta [view email] [v1] Mon, 4 May 2026 18:43:30 UTC (328 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled The TTS-STT Flywheel: Synthetic Entity-Dense Audio Closes the Indic ASR Gap Where Commercial and Open-Source Systems Fail, by Venkata Pushpak Teja Menta

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CL

new | recent | 2026-05

Change to browse by:

cs cs.SD

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

export BibTeX citation Loading...

BibTeX formatted citation

×

loading...

Data provided by:

Bookmark

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

About

Help

contact arXivClick here to contact arXiv Contact

subscribe to arXiv mailingsClick here to subscribe Subscribe

Copyright

Privacy Policy

Web Accessibility Assistance

arXiv Operational Status

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • Open-source and commercial ASR achieve very low entity hit rates on Indic niche domains.
  • A TTS-STT flywheel generates synthetic entity-dense code-mixed audio to boost STT performance.
  • EHR improved from 0.027/0.16 to 0.98 on a held-out Telugu test set.
  • All code, datasets, and entity dictionaries are released open-source.

Highlights and analysis are generated automatically and may contain errors. Check the original source.