An Online Solution for Localisation, Tracking and Separation of Moving Speech Sources
MetadataShow full item record
The problem of separating a time varying number of speech sources in a room is difficult to solve. The challenge lies in estimating the number and the location of these speech sources. Furthermore, the tracked speech sources need to be separated. This thesis proposes a solution which utilises the Random Finite Set approach to estimate the number and location of these speech sources and subsequently separate the speech source mixture via time frequency masking.
Showing items related by title, author, creator and subject.
Tracking and separation of multiple moving speech sources via cardinality balanced multi-Target multi Bernoulli (CBMeMBer) filter and time frequency maskingChong, Nicholas; Nordholm, Sven; Vo, Ba Tuong; Murray, Iain (2017)In a 'conference room scenario', the number of speech sources are not known a priori and the number of speech sources which are active remains unknown as these speech sources appear and disappear throughout the measurement ...
Dam, H.; Nordholm, Sven (2013)This paper investigates the problem of subband speech separation from a mixture of two speech signals in a room environment. Due to the lack of source information, a sound source localization is proposed for beamformer ...
A novel fuzzy clustering algorithm using observation weighting and context information for reverberant blind speech separationKuhne, M.; Togneri, R.; Nordholm, Sven (2009)Time-frequency masking has evolved as a powerful tool for tackling blind source separation problems. In previous work, mask estimation was performed with the help of well-known standard cluster algorithms. Spatial observation ...