Frequency Domain Microphone Array Calibration and Beamforming for Automatic Speech Recognition

Jwu-Sheng HU  Chieh-Cheng CHENG  

Publication
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences   Vol.E88-A   No.9   pp.2401-2411
Publication Date: 2005/09/01
Online ISSN: 
DOI: 10.1093/ietfec/e88-a.9.2401
Print ISSN: 0916-8508
Type of Manuscript: PAPER
Category: Noise and Vibration
Keyword: 
beamformer,  microphone array,  calibration,  speech recognition,  speech enhancement,  

Full Text: PDF(1.9MB)
>>Buy this Article


Summary: 
This investigation proposed two array beamformers SPFDBB (Soft Penalty Frequency Domain Block Beamformer) and FDABB (Frequency Domain Adjustable Block Beamformer). Compared with the conventional beamformers, these frequency-domain methods can significantly reduce the computation power requirement in ASR (Automatic Speech Recognition) based applications. Like other reference signal based techniques, SPFDBB and FDABB minimize microphone's mismatch, desired signal cancellation caused by reflection effects and resolution due to the array's position. Additionally, these proposed methods are suitable for both near-field and far-field environments. Generally, the convolution relation between channel and speech source in time domain cannot be modeled accurately as a multiplication in the frequency domain with a finite window size, especially in ASR applications. SPFDBB and FDABB can approximate this multiplication by treating several frames as a block to achieve a better beamforming result. Moreover, FDABB adjusts the number of frames on-line to cope with the variation of characteristics in both speech and interference signals. A better performance was found to be achievable by combining these methods with an ASR mechanism.