Single-channel speaker diarization based on spatial features | IEEE Conference Publication | IEEE Xplore

Single-channel speaker diarization based on spatial features


Abstract:

Speaker diarization has gained much importance over the past five years in helping overcome key challenges faced by automatic meeting transcription systems. Current state...Show More

Abstract:

Speaker diarization has gained much importance over the past five years in helping overcome key challenges faced by automatic meeting transcription systems. Current state-of-the-art algorithms can only utilize spatial information when multi-microphone recordings are available. In this paper, we propose the novel use of reverberation as a source of spatial information obtained from single-channel recordings to perform speaker diarization. The proposed system is shown to reduce speaker classification errors by 34% when compared with current MFCC based single-channel systems.
Date of Conference: 18-21 October 2015
Date Added to IEEE Xplore: 30 November 2015
ISBN Information:
Conference Location: New Paltz, NY, USA

References

References is not available for this document.