Improving separation of overlapped speech for meeting conversations using uncalibrated microphone array.

Keisuke Nakamura Randy Gomez

Published in: ASRU (2017)

Keyphrases

multi party
conversational speech
speech recognition
speaker diarization
camera parameters
human communication
image sequences
speech synthesis
content analysis
speech signal
endpoint detection
uncalibrated images
camera calibration
multi agent
recognition engine
computer vision
information retrieval