A decoder-only TTS trained on force-aligned interleaved text-speech chunks generates audio after a few words, achieving ~30ms TTS latency and WER comparable to non-streaming.
Audi- olm: a language modeling approach to audio generation,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
SpeakStream: Streaming Text-to-Speech with Interleaved Data
A decoder-only TTS trained on force-aligned interleaved text-speech chunks generates audio after a few words, achieving ~30ms TTS latency and WER comparable to non-streaming.