TTSDS2: Resources and Benchmark for Evaluating Human-Quality Text to Speech Systems

ICLROral2026

Authors
Christoph Minixhofer, Ondrej Klejch, Peter Bell
Affiliation
University of Edinburgh, University of Edinburgh
Venue
ICLR 2026
Track
Oral

TL;DR

With TTSDS2, we introduce a metric and benchmark for TTS, covering 14 languages, which consistently correlates with human judgements.

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

benchmark speech

← All ICLR 2026 Oral papers · Browse the whole archive