Speech overlap detection using convolutive non-negative sparse coding: New improvements and insights

This paper presents recent advances in the application of convolutive non-negative sparse coding (CNSC) to the problem of overlap detection in the context of conference meetings and speaker diarization. CNSC is used to project a mixed speaker signal onto separate speaker bases and hence to detect intervals of competing speech. We present new energy ratio and total energy features which give significant improvements over our previous work. The system is assessed using a subset of the AMI meeting corpus. We report results which are comparable to the state of the art which support the potential of a new approach to overlap detection. An analysis of system performance highlights the importance of further work to addresses weaknesses in detecting particularly short segments of overlapping speech.