keonlee9420/DailyTalk

Official repository of DailyTalk: Spoken Dialogue Dataset for Conversational Text-to-Speech, ICASSP 2023

39
/ 100
Emerging

Contains 2,541 recorded dialogues with annotated conversational attributes, enabling training of context-aware TTS systems that model dialogue history. The baseline implements non-autoregressive transformer-based synthesis with optional historical encoders (supporting the Guo et al. approach) and uses HiFi-GAN vocoding, with unsupervised phoneme-level duration modeling and Montreal Forced Aligner for alignment extraction.

252 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

252

Forks

14

Language

Python

License

MIT

Last pushed

Jun 05, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/keonlee9420/DailyTalk"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.