A new open family of speech-language models trained on public data matches or beats prior systems across ASR, TTS, and text benchmarks.
18Note the out-domain corpus in [25] is of sufficiently high quality, so we believe this degradation is more from domain mismatch
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
dataset 1polarities
use dataset 1representative citing papers
citing papers explorer
-
OpusLM: A Family of Open Unified Speech Language Models
A new open family of speech-language models trained on public data matches or beats prior systems across ASR, TTS, and text benchmarks.