Speech Foundation Models
PulseAugur coverage of Speech Foundation Models — every cluster mentioning Speech Foundation Models across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
CAL-MOS method improves speech quality prediction using frozen foundation models
Researchers have developed CAL-MOS, a novel method for predicting Mean Opinion Scores (MOS) in speech quality assessment. This approach addresses the challenge of selecting the most informative layers within Speech Foun…
-
New VQ-Bench evaluation reveals biases in speech foundation models
A new evaluation suite called VQ-Bench has been developed to assess how speech foundation models (SFMs) interpret subtle vocal variations beyond just spoken words. Researchers found that some leading commercial SFMs fai…
-
SpeechLLMs show mixed results in translation benchmarks, cascades still lead
A new comprehensive test suite, Hearing to Translate, has been developed to evaluate the effectiveness of integrating speech modality directly into Large Language Models (LLMs) for speech-to-text translation. The study …