차량 잡음 환경에서 인위적 왜곡 음성을 이용한 Eigenspace-based MLLR에 기반한 고속 화자 적응
Fast Speaker Adaptation Based on Eigenspace-based MLLR Using Artificially Distorted Speech in Car Noise Environment
0
조회
0
다운로드
2
인용
0
참고문헌
초록
Abstract
This paper proposes fast speaker adaptation method using artificially distorted speech in telematics terminal under the car noise environment based on eigenspace-based maximum likelihood linear regression (ES-MLLR). The artificially distorted speech is built from adding the various car noise signals collected from a driving car to the speech signal collected from an idling car. Then, in every environment, the transformation matrix is estimated by ES-MLLR using the artificially distorted speech corresponding to the specific noise environment. In test mode, an online model is built by weighted sum of the environment transformation matrices depending on the driving condition. In 3k-word recognition task in the telematics terminal, we achieve a performance superior to ES-MLLR even using the adaptation data collected from the driving condition.
참고문헌 (9)
- Sanker, A, "A maximum-likelihood approach to stochastic matching for robust speech recognition", IEEE Trans. Speech and Audio Processing, 4(3), pp.190~202 (1996)
- Leggetter, C. J, "Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models", Computer Speech and Language, 9(1), pp.185~ (1995)
- Kuhn, R, "Eigenvoices for speaker adaptation", ICSLP, pp.1771~1774
- Chen, K. T, "Fast speaker adaptation using eigenspace-based maximum likelihood linear regression", ICSLP, pp.742~745 (2000)
- Song, H. J, "Simultaneous Estimation of Weights of Eigenvoices and Bias Compensation Vector for Rapid Speaker Adaptation", ICSLP, pp.2945~2948 (2004)
- 송화전, "Eigenspace-based MLLR에 기반한 고속 화자적응 및 환경 보상？", 말소리, 1(58), pp.35~44 (2006), 대한음성학회
- 김영국, "다양한 잡음 환경하에서 환경 군집화를 통한 화자 및 환경 동시 적응", 한국음향학회지, 28(6), pp.566~571 (2009), 한국음향학회
- ITU recommendation P.56, "Objective measurement of active speech level", "Mar., ~ (1993)
- 강병옥, "동적 잡음 처리를 위한 모델기반 Wiener 필터", 대한음성학회 가을학술대회, pp.104~107 (2007), 대한음성학회