We explore audio, speech and language processing
to learn behavioral signals via pipeline work

Welcome to SLP

SAIL has comprehensive and extensive research on audio, speech and language processing. In addition to aiming to create core signal processing and machine learning algorithmic advances in these domains, the goal is to support a variety of downstream applications—both for deriving human conversational interaction analytics and for supporting human-machine interactions.

Each team devote to learn behavioral signal processing via pipeline work which includes audio pre-processing and feature extraction, voice activity detection (VAD), speaker diarization and role assignment, automatic speech recognition (ASR) and speech/language analysis by unimodal and multimodal approaches.