A Noise Reduction Method Combined with HMM Composition for Speech Recognition in Noisy Environments
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
In this paper, a MSS-NOVO method that combines the HMM composition method with a noise reduction method is proposed for speech recognition in noisy environments. This combined method starts with noise reduction with modified spectral subtraction (MSS) to enhance the input noisy speech, then the noise and voice composition (NOVO) method is applied for making noise adapted models by using the noise in the non-utterance regions of the enhanced noisy speech. In order to evaluate the effectiveness of our proposed method, we compare MSS-NOVO method with other methods, i.e., SS-NOVO, MWF-NOVO. To set up the noisy speech for test, we add White noise to KLE 452 database with different SNRs range from 0dB to 15dB, at 5dB intervals. From the tests, MSS-NOVO method shows average improvement of 66.5% and 13.6% compared with the existing SS-NOVO method and MWF-NOVO method, respectively. Especially our proposed MSS-NOVO method shows a big improvement at low SNRs.
Abstract
In this paper, a MSS-NOVO method that combines the HMM composition method with a noise reduction method is proposed for speech recognition in noisy environments. This combined method starts with noise reduction with modified spectral subtraction (MSS) to enhance the input noisy speech, then the noise and voice composition (NOVO) method is applied for making noise adapted models by using the noise in the non-utterance regions of the enhanced noisy speech. In order to evaluate the effectiveness of our proposed method, we compare MSS-NOVO method with other methods, i.e., SS-NOVO, MWF-NOVO. To set up the noisy speech for test, we add White noise to KLE 452 database with different SNRs range from 0dB to 15dB, at 5dB intervals. From the tests, MSS-NOVO method shows average improvement of 66.5% and 13.6% compared with the existing SS-NOVO method and MWF-NOVO method, respectively. Especially our proposed MSS-NOVO method shows a big improvement at low SNRs.
참고문헌 (10)
- Y. Ephraim, "On the Application of Hidden Markov Models for Enhancing Noisy Speech", Proc. IEEE Trans. Acoust., Speech Signal Processing, 37, pp.1846~1856 (1989)
- J. S. Lim, "Ehanced and Bandwidth Compression of Noisy Speech", Proc. IEEE, 67(12), pp.1586~1604 (1979)
- M. J. Gales, "Robust Continuous Speech Recognition using Parallel Model Combination", Proc. IEEE trans. on Speech and Audio Processing, 4, pp.352~359 (1996)
- M. J. Gales, "Robust Speech Recognition in Additive and Convolutional Noise using Parallel Model Combination", Proc. Computer Speech and Language, pp.289~307 (1995)
- M. J. Gales, "An Improved Approach to the Hidden Markov Model Decomposition of Speech and Noise", Proc. ICASSP, pp.I-233~I-236 (1992)
- K. Satoshi, "Robust Speech Recognition Based on HMM Composition and Modified Wiener Filter", Proc. ICSLP, pp.2045~2048 (2004)
- S. Sakauchi, "Implementing and Evaluating of an Audio Teleconferencing Terminal with Noise and Echo Reduction", Proc. IWAENC, pp.191~194 (2003)
- M. Berouti, "Enhancement of Speech Corrupted by Acoustic Noise", Proc. ICASSP, pp.208~211 (1979)
- A. P. Varga, "Hidden Markov Model Decomposition of Speech and Noise", Proc. ICASSP, pp.845~848 (1990)
- Se-Jin Oh, "New State Clustering of Hidden Markov Network with Korean Phonological Rules for Speech Recognition", Proc. IEEE 4th workshop on Multimedia Signal Processing, pp.39~44 (2001)