위상 정보를 고려한 로그멜 영역에서의 2단계 선험 SNR 추정
Two-step a priori SNR Estimation in the Log-mel Domain Considering Phase Information
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
The decision directed (DD) approach is widely used to determine a priori SNR from noisy speech signals. In conventional speech enhancement systems with a DD approach, a priori SNR is estimated by using only the magnitude components and consequently follows a posteriori SNR with one frame delay. We propose a phase-dependent two-step a priori SNR estimator based on the minimum mean square error (MMSE) in the log-mel spectral domain so that we can consider both magnitude and phase information, and it can overcome the performance degradation caused by one frame delay. From the experimental results, the proposed estimator is shown to improve the output SNR of enhanced speech signals by 2.3 dB compared to the conventional DD approach-based system.
Abstract
The decision directed (DD) approach is widely used to determine a priori SNR from noisy speech signals. In conventional speech enhancement systems with a DD approach, a priori SNR is estimated by using only the magnitude components and consequently follows a posteriori SNR with one frame delay. We propose a phase-dependent two-step a priori SNR estimator based on the minimum mean square error (MMSE) in the log-mel spectral domain so that we can consider both magnitude and phase information, and it can overcome the performance degradation caused by one frame delay. From the experimental results, the proposed estimator is shown to improve the output SNR of enhanced speech signals by 2.3 dB compared to the conventional DD approach-based system.
참고문헌 (8)
- Ephraim, Y, "Speech enhancement using a minimum mean-square error short-time spectral amplitude estimator", IEEE Trans. Acoustics, Speech and Signal Processing, 32, pp.1109~1121 (1984)
- Loizou, P. C, "Speech Enhancement", pp.97~289 (2007), CRC Pr I Llc
- Alam, M. J, "Speech enhancement based on novel two-step a priori SNR estimators", Proc. Interspeech, pp.565~568 (2008)
- Faubel, F, "A phaseaveraged model for the relationship between noisy speech, clean speech and noise in the log-mel domain", Proc. Interspeech, pp.553~556 (2008)
- Paliwal, K. K, "Usefulness of phase in speech processing", Proc. IPSJ Spoken Language Processing Workshop, Gifu, Japan, pp.1~6 (2003)
- Lee, Y.-K, "Single-channel speech separation using zero-phase models", IEEE International Symposium on Consumer Electronics, pp.1~5 (2010)
- Accardi, A. J, "A modular approach to speech enhancement with an application to speech coding", Proc. IEEE Int. Conf. Acoustic, Speech, and Signal Processing, 통권 : 1, pp.201~204 (1999)
- "Speech Separation and Recognition Competition" (2010)[URL]