Monaural Speech Separation Based on Computational Auditory Scene Analysis and Objective Quality Assessment of Speech

Monaural speech separation is a very challenging problem in speech signal processing. It has been studied extensively, and many separation systems based on computational auditory scene analysis (CASA) have been proposed in the last two decades. Although the research on CASA has tended to introduce high-level knowledge into separation processes using primitive data-driven methods, the knowledge on speech quality still has not been combined with it. This makes the performance evaluation of CASA mainly focused on the signal-to-noise ratio (SNR) improvement. Actually, the quality of the separated speech is not directly related to its SNR. In order to solve this problem, we propose a new method which combines CASA with objective quality assessment of speech (OQAS). In the grouping process of CASA, we use OQAS as the guide to instruct the CASA system. With this combination, the performance of the speech separation can be improved not only in SNR, but also in mean opinion score (MOS). Our system is systematically evaluated and compared with previous systems, and it yields substantially better performance, especially for the subjective perceptual quality of separated speech.

I. Introduction

In a natural world, a speech signal is frequently accompanied by other sound sources upon reaching auditory systems, yet listeners are capable of holding conversations in a wide range of conditions. This phenomenon is well known as the “cocktail party” effect [1]. It is valuable to make a computer have the ability of a human being to segregate the object source from other interfering sources. An effective separation system can greatly facilitate many applications, including automatic speech recognition (ASR), speaker identification, audio retrieval, digital content management, etc. Therefore, the research on speech separation gradually catches the researchers' attentions, and it has become an increasingly popular topic in the field of signal processing.