SpeechLLM
PulseAugur coverage of SpeechLLM — every cluster mentioning SpeechLLM across labs, papers, and developer communities, ranked by signal.
-
SpeechLLM offers multi-level L2 assessment with natural language rationales
Researchers have developed a SpeechLLM designed for assessing L2 speech proficiency across multiple granularities and providing natural language rationales. This model, trained using a hybrid approach of supervised fine…
-
FiLM technique enhances ASR for pathological speech
Researchers have developed a new method for improving automatic speech recognition (ASR) for pathological speech using a technique called Feature-wise Linear Modulation (FiLM). This approach injects speaker-specific inf…
-
SpeechLLM achieves real-time translation with 1-2 second latency
Researchers have developed a new SpeechLLM architecture designed for real-time speech-to-text translation. Unlike previous systems that process entire utterances or output at fixed intervals, this model learns to determ…