Title :
Algorithms for Alignment of Co-Channel Speech Signals in Adaptive Speech Separation
Author :
Cox, Nicholas J. ; Page, Christopher J. ; Petrescu, Razvan F. ; Aziz, Syed Mahfuzul
Author_Institution :
Univ. of South Australia, Mawson Lakes
Abstract :
This paper presents preprocessing algorithms for reducing misalignment of co-channel speech signals in order to improve the accuracy of adaptive speech separation. The use of adaptive decorrelation filtering as a front end processor in speech recognition systems improve performance when the input signals from the two channels are synchronized. However the performance of ADF is degraded when the co-channel signals are misaligned. We address this problem by proposing a pre-processor to the ADF with a view to align the co-channel signals. We have implemented two different algorithms for synchronizing the co-channel speech signals using cross-correlation. These algorithms improve the performance of speech recognition.
Keywords :
filtering theory; satellite computers; source separation; speech recognition; adaptive decorrelation filtering; adaptive speech separation; cochannel speech signals alignment; front end processor; preprocessing algorithms; Adaptive filters; Automatic speech recognition; Decorrelation; Equations; Interference; Loudspeakers; Microphones; Reverberation; Signal processing; Speech recognition;
Conference_Titel :
Information and Communication Technology, 2007. ICICT '07. International Conference on
Conference_Location :
Dhaka
Print_ISBN :
984-32-3394-8
DOI :
10.1109/ICICT.2007.375399