Speaker Selective Beamformer with Keyword Mask Estimation

This paper addresses the problem of automatic speech recognition (ASR) of a target speaker in background speech. The novelty of our approach is that we focus on a wakeup keyword, which is usually used for activating ASR systems like smart speakers. The proposed method firstly utilizes a DNN-based ma...

Full description

Saved in:
Bibliographic Details
Published in2018 IEEE Spoken Language Technology Workshop (SLT) pp. 528 - 534
Main Authors Kida, Yusuke, Tran, Dung, Omachi, Motoi, Taniguchi, Toru, Fujita, Yuya
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.12.2018
Subjects
Array signal processing
background speech
Estimation
Microphone arrays
robust automatic speech recognition
speech enhancement
Speech processing
Speech recognition
Training
Wakeup keyword
Online AccessGet full text

Cover

More Information
Summary:This paper addresses the problem of automatic speech recognition (ASR) of a target speaker in background speech. The novelty of our approach is that we focus on a wakeup keyword, which is usually used for activating ASR systems like smart speakers. The proposed method firstly utilizes a DNN-based mask estimator to separate the mixture signal into the keyword signal uttered by the target speaker and the remaining background speech. Then the separated signals are used for calculating a beamforming filter to enhance the subsequent utterances from the target speaker. Experimental evaluations show that the trained DNN-based mask can selectively separate the keyword and background speech from the mixture signal. The effectiveness of the proposed method is also verified with Japanese ASR experiments, and we confirm that the character error rates are significantly improved by the proposed method for both simulated and real recorded test sets.
DOI:10.1109/SLT.2018.8639651