Technical Program

Paper Detail

Paper:	SLP-L7.4
Session:	Speech Enhancement for Noise Suppression
Time:	Thursday, May 18, 11:00 - 11:20
Presentation:	Lecture
Topic:	Speech and Spoken Language Processing: Speech Enhancement (for Impaired Situations)
Title:	AN ITERATIVE TRAJECTORY REGENERATION ALGORITHM FOR SEPARATING MIXED SPEECH SOURCES
Authors:	Siu wa Lee, Chinese University of Hong Kong, Hong Kong SAR of China; Frank K. Soong, Microsoft Research Asia, China; P. C. Ching, Chinese University of Hong Kong, Hong Kong SAR of China
Abstract:	Hamonicity and continuity are two important perceptual cues for separating mixed speech sources. This paper focuses on the separation of two speech sources with a single-microphone input. An iterative, least-squares (LS) based trajectory regeneration algorithm is proposed to estimate the magnitude spectrum of each source. Time-derivatives of the spectrum, or the dynamic spectral information, is used as a constraint in solving the resultant weighted normal equations. Each estimated spectral trajectory, as a result, exhibits similar temporal variations as the original source. Asymptotically, we also prove that the regenerated trajectory yields the same time variations as the given dynamic information. When cascaded with our previously proposed harmonic filtering algorithm to separate mixed voiced signals, the new trajectory regeneration is shown to be very effective to reduce mean squared errors by 82.2% and 69.5%, relatively, with ideal and approximated dynamic information, respectively.