Multi-speaker separation employing microphone array and vertex finding algorithm
MetadataShow full item record
© 2018 IEEE. This paper proposes a new speaker detection and signal separation algorithm for multiple speakers using microphone array data recorded in a room environment. The algorithm utilizes the fact that in multi-speaker conversations not all speakers are speaking simultaneously there are time segments when only a single speaker is active. Based on that observation a speech activity detector for each speaker (MVAD) has been developed. It is based on SRP-PHAT estimates for different blocks of data. We have shown that these estimates form vertexes in a convex polygon which can be employed to obtain MVAD detections. Those detections are then used to form Minimum Variance Distortionless Response (MVDR) beamformers. Evaluations based on real recorded speech data with 4 speakers show that the algorithm provides good interference suppression and low speech distortion for this difficult scenario.
Showing items related by title, author, creator and subject.
Multiple moving speaker tracking via degenerate unmixing estimation technique and Cardinality Balanced Multi-target Multi-Bernoulli Filter (DUET-CBMeMBer)Chong, N.; Wong, S.; Vo, Ba Tuong; Nordholm, Sven; Murray, Iain (2014)The "cocktail party problem" has always been a challenging problem to solve and many blind source separation algorithms have been proposed as solutions. This problem has mainly been discussed for non-moving sound sources ...
Jafari, I.; Haque, S.; Togneri, R.; Nordholm, Sven (2011)Recently, the concept of time-frequency masking has developed as an important approach to the blind source separation problem, particularly when in the presence of reverberation. However, previous research has been limited ...
Sabet, Peyman G.P.; Zhang, G. (2017)This paper explores an overlooked yet intriguing phenomenon: the different preferences of first language (L1) and second language (L2) groups in the use of I don’t think and I think+not. Based on naturally occurring data ...