Takashi Hiekata

Two-stage blind source separation based on ICA and binary masking for real-time robot audition system

We newly propose a real-time two-stage blind source separation (BSS) for binaural mixed signals observed at the ears of humanoid robot, in which a single-input multiple-output (SIMO)-model-based independent component analysis (ICA) and binary mask processing are combined. SIMO-model-based ICA can separate the mixed signals, not into monaural source signals but into SIMO-model-based signals from independent sources as they are at the microphones. Thus, the separated signals of SIMO-model-based ICA can maintain the spatial qualities of each sound source, and this yields that binary mask processing can be applied to efficiently remove the residual interference components after SIMO-model-based ICA. The experimental results obtained with a human-like head reveal that the separation performance can be considerably improved by using the proposed method in comparison to the conventional ICA-based and binary-mask-based BSS methods.

Blind separation of acoustic signals combining SIMO-model-based independent component analysis and binary masking

A new two-stage blind source separation (BSS) method for convolutive mixtures of speech is proposed, in which a single-input multiple-output (SIMO)-model-based independent component analysis (ICA) and a new SIMO-model-based binary masking are combined. SIMO-model-based ICA enables us to separate the mixed signals, not into monaural source signals but into SIMO-model-based signals from independent sources in their original form at the microphones. Thus, the separated signals of SIMO-model-based ICA can maintain the spatial qualities of each sound source. Owing to this attractive property, our novel SIMO-model-based binary masking can be applied to efficiently remove the residual interference components after SIMO-model-based ICA. The experimental results reveal that the separation performance can be considerably improved by the proposed method compared with that achieved by conventional BSS methods. In addition, the real-time implementation of the proposed BSS is illustrated.

Blind Source Separation Combining Simo-Ica and Simo-Model-Based Binary Masking

A new two-stage blind source separation (BSS) for convolutive mixtures of speech is proposed, in which a single-input multiple-output (SIMO)-model-based ICA and a new SIMO-model-based binary mask processing are combined. SIMO-model-based ICA can separate the mixed signals, not into monaural source signals but into SIMO-model-based signals from independent sources as they are at the microphones. Thus, the separated signals of SIMO-model-based ICA can maintain the spatial qualities of each sound source. Owing to the attractive property, novel SIMO-model-based binary mask processing can be applied to efficiently remove the residual interference components after SIMO-model-based ICA. The experimental results reveal that the separation performance can be considerably improved by using the proposed method compared with the conventional BSS methods

High-Presence Hearing-Aid System using DSP-Based Real-Time Blind Source Separation Module

Real-time two-stage blind source separation (BSS) method for convolutive mixtures of speech is now being studied by the authors, in which a single-input multiple-output (SIMO)-model-based independent component analysis (ICA) and a SIMO-model-based binary masking are combined. In addition, we have developed a pocket-size real-time DSP module implementing the two-stage BSS method. In this paper, we introduce a high-presence hearing-aid system which can reduce the interference sound and reproduce the target sound while keeping the directivity, and realize the system with the real-time BSS module. To evaluate it, we carried out the objective and subjective experiments using 9 users. From these results, it is revealed that the decomposition performance and the directivity maintenance of the proposed system are superior to those of conventional methods.

Multiple ICA-based real-time blind source extraction applied to handy size microphone

A new blind source extraction method in widespread noise conditions is proposed, which is based on multiple frequency-domain independent component analysis (FDICA) combining projection back and spectral subtraction. In addition, We implement the proposed method to digital signal processor (DSP) for a more realistic real-time operation, and develop a new blind source extraction (BSE) microphone which can extract a target sound in real-time. In this paper, we illustrate and evaluate the proposed method and BSE microphone. And experimental results reveal that the extraction performance of the proposed method are superior to that of conventional methods, and we show the efficacy of microphone.

ICA and binary-mask-based blind source separation with small directional microphones

A new two-stage blind source separation (BSS) for convolutive mixtures of speech is proposed, in which a Single-Input Multiple-Output (SIMO)-model-based ICA and binary mask processing are combined. SIMO-model-based ICA can separate the mixed signals, not into monaural source signals but into SIMO-model-based signals from independent sources as they are at the microphones. Thus, the separated signals of SIMO-model-based ICA can maintain the spatial qualities of each sound source. Owing to the attractive property, binary mask processing can be applied to efficiently remove the residual interference components after SIMO-model-based ICA. The experimental results using small directional microphone array reveal that the separation performance can be considerably improved by using the proposed method in comparison to the conventional source separation methods.

Noise-robust hands-free speech recognition using SIMO-model-based blind source separation

This paper addresses a noise-robust hands-free speech recognition system in which Single-Input Multiple-Output (SIMO)-model-based blind source separation (BSS) is introduced to achieve a fluent human-machine interaction. The method consists of SIMO-ICA technique and SIMO-model-based binary masking, which can achieve a superior noise reduction with low distortion. In this paper, we investigate the distortion controllability of the two-stage BSS method. The experimental results reveal that the speech recognition rate can be considerably improved by using the two-stage method compared with the conventional BSS methods. In addition, a BSS-based hands-free spoken dialogue system is illustrated.

Blind separation of convolutive speech mixtures using SIMO-model-based ICA and binary mask processing

Summary form only given. A new two-stage blind source separation (BSS) for convolutive mixtures of speech is proposed, in which a single-input multiple-output (SIMO)-model-based ICA and binary mask processing are combined. SIMO-model-based ICA can separate the mixed signals, not into monaural source signals but into SIMO-model-based signals from independent sources as they are at the microphones. Thus, the separated signals of SIMO-model-based ICA can maintain the spatial qualities of each sound source. Owing to the attractive property, binary mask processing can be applied to efficiently remove the residual interference components after SIMO-model-based ICA. The experimental results reveal that the separation performance can be considerably improved by using the proposed method in comparison to the conventional source separation methods.