A waveform generation model-based approach for segregation of monaural mixed sound

Abstract

The present paper describes a novel method for segregating monaural concurrent sounds. In a real environment, there exist several types of sounds, including periodic, aperiodic and impulsive sounds, and several sounds will usually occur simultaneously. Recognition of the sounds requires the ability to model various types of sounds and segregate the concurrent sounds. The proposed method adopts a waveform generation model consisting of an auto-regressive process and a hidden Markov model (AR-HMM) as a template model and achieves segregation of monaural concurrent sounds based on the mixed AR-HMMs. Experiments were conducted to confirm the feasibility of the proposed method using five Japanese vowel sounds and ten types of non-speech sounds. The experimental results indicate that the proposed method is effective for the segregation of various types of sounds.