잡음 환경에서의 음성 감정 인식을 위한 특징 벡터 처리
Feature Vector Processing for Speech Emotion Recognition in Noisy Environments
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
This paper proposes an efficient feature vector processing technique to guard the Speech Emotion Recognition (SER) system against a variety of noises. In the proposed approach, emotional feature vectors are extracted from speech processed by comb filtering. Then, these extracts are used in a robust model construction based on feature vector classification. We modify conventional comb filtering by using speech presence probability to minimize drawbacks due to incorrect pitch estimation under background noise conditions. The modified comb filtering can correctly enhance the harmonics, which is an important factor used in SER. Feature vector classification technique categorizes feature vectors into either discriminative vectors or non-discriminative vectors based on a log-likelihood criterion. This method can successfully select the discriminative vectors while preserving correct emotional characteristics. Thus, robust emotion models can be constructed by only using such discriminative vectors. On SER experiment using an emotional speech corpus contaminated by various noises, our approach exhibited superior performance to the baseline system.
Abstract
This paper proposes an efficient feature vector processing technique to guard the Speech Emotion Recognition (SER) system against a variety of noises. In the proposed approach, emotional feature vectors are extracted from speech processed by comb filtering. Then, these extracts are used in a robust model construction based on feature vector classification. We modify conventional comb filtering by using speech presence probability to minimize drawbacks due to incorrect pitch estimation under background noise conditions. The modified comb filtering can correctly enhance the harmonics, which is an important factor used in SER. Feature vector classification technique categorizes feature vectors into either discriminative vectors or non-discriminative vectors based on a log-likelihood criterion. This method can successfully select the discriminative vectors while preserving correct emotional characteristics. Thus, robust emotion models can be constructed by only using such discriminative vectors. On SER experiment using an emotional speech corpus contaminated by various noises, our approach exhibited superior performance to the baseline system.
참고문헌 (13)
- Ververidis, D., "Emotional speech recognition: resources, features, and methods", Speech Communication, 48(9), pp.1162~1181 (2006)
- Kwon, O., "Emotion recognition by speech signals", Proc. Int. Conf. on Eurospeech, pp.125~128 (2003)
- Tato, R., "Emotional space improves emotion recognition", Proc. Int. Conf. on ICSLP, pp.2029~2032 (2002)
- 정용주, "잡음음성인식을 위한 음성개선 방식들의 성능 비교", 말소리와 음성과학, 1(2), pp.9~14 (2009), 한국음성학회
- Huang, R., "Toward a speaker-independent real time affect detection system", Proc. Int. Conf. on Pattern Recognition (ICPR), pp.1204~1207 (2006)
- Frazier, R.H., "Enhancement of speech by adaptive filtering", Proc. Int. Conf. on ASSP, pp.251~253 (1976)
- 박정식, "MMSE Estimator 기반의 적응 콤 필터링을 이용한 잡음 제거", 말소리, 1(60), pp.181~190 (2006), 대한음성학회
- Malah, D., "Tracking speech-presence uncertainty to improve speech enhancement in nonstationary noise environments", Proc. Int. Conf. on Acoustics, Speech and Signal Processing, pp.201~204 (1999)
- Kwon, S., "Robust speaker identification based on selective use of feature vectors", Pattern Recognition Letters, 28, pp.85~89 (2007)
- Boll, S.F., "Suppression of acoustic noise in speech using spectral subtraction", IEEE Trans. on Acoustics, Speech and Signal Processing, 27(2), pp.113~120 (1979)
- Liberman, M., "Emotional prosody speech and transcripts, Linguistic Data Consortium (LDC)" (2002), University of Pennsylvania
- The NOISEX-92 study on the effect of additive noise on automatic speech recognition, "Varga, A.P.", DRA Speech Research Unit, ~ (1992)
- Sethu, V., "Speaker normalization for speech-based emotion detection", Proc. Int. Conf. on Digital Signal Processing (DSP), pp.611~614 (2007)