Concept语音大模型 / Speech Large Language Model
SpeechLLM
An end-to-end speech recognition model that integrates large language model capabilities with speech processing. It exhibits strong general-purpose spoken language understanding but faces challenges in accurately recognizing rare or out-of-vocabulary words.
Timeline (last 90 days)
Sep 25
PTC-Bias is a two-stage context biasing framework based on phoneme-level temporal competition, designed to improve the recognition of rare words in speech large language models.
Unverified50%