TDScore: Learning Synthetic Speech Quality Predictors from TTS Training Dynamics without Human annotation

Natacha Miniconi; Meysam Shamsi; Anthony Larcher

RResearcharAcademic radar for researchers

Feed Venues Groups Network Inbox Profile

Your academic radar

One personalized feed of papers, calls for papers, collaborators and datasets — plus research groups and paid-in-points study recruitment.

Create account Log in

Top venues

Browse all

Loading…

TDScore: Learning Synthetic Speech Quality Predictors from TTS Training Dynamics without Human annotation · Researchar

Back to feed

Paperopenalex

HLC

TDScore: Learning Synthetic Speech Quality Predictors from TTS Training Dynamics without Human annotation

Natacha Miniconi, Meysam Shamsi, Anthony Larcher · HAL (Le Centre pour la Communication Scientifique Directe) 2026 · 2026

0citations

Speech Recognition and SynthesisSpeech and Audio ProcessingEmotion and Mood RecognitionAnnotationQuality (philosophy)Computer science+2

HLCHAL (Le Centre pour la Communication Scientifique Directe)Repository

Download PDF Publisher

Citations by source

Synced 2026-09-27T02:31:55.632010Z

0OpenAlex · primary0Semantic Scholar0Crossref

Counts differ because each database indexes a different set of publications. We treat OpenAlex as the canonical count; Google Scholar is not shown (no API, and crawling it violates its ToS).

Abstract

International audience

Discussion (0)

No comments yet — start the discussion below.