Vocal Effort Detection Based on Spectral Information Entropy Feature and Model Fusion
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
Vocal effort detection is important for both robust speech recognition and speaker recognition. In this paper,the spectral information entropy feature which contains more salient information regarding the vocal effortlevel is firstly proposed. Then, the model fusion method based on complementary model is presented torecognize vocal effort level. Experiments are conducted on isolated words test set, and the results show thespectral information entropy has the best performance among the three kinds of features. Meanwhile, therecognition accuracy of all vocal effort levels reaches 81.6%. Thus, potential of the proposed method isdemonstrated.
Abstract
Vocal effort detection is important for both robust speech recognition and speaker recognition. In this paper,the spectral information entropy feature which contains more salient information regarding the vocal effortlevel is firstly proposed. Then, the model fusion method based on complementary model is presented torecognize vocal effort level. Experiments are conducted on isolated words test set, and the results show thespectral information entropy has the best performance among the three kinds of features. Meanwhile, therecognition accuracy of all vocal effort levels reaches 81.6%. Thus, potential of the proposed method isdemonstrated.
참고문헌 (16)
- H. Traunmuller, "Acoustic effects of variation in vocal effort by men, women, and children", The Journal of the Acoustical Society of America, 107(6), pp.3438~3451 (2000)[DOI]
- P. Zelinka, "Automatic vocal effort detection for reliable speech recognition", Proceedings of IEEE International Workshop on Machine Learning for Signal Processing, pp.349~354 (2010)
- P. Zelinka, "Impact of vocal effort variability on automatic speech recognition", Speech Communication, 54(6), pp.732~742 (2012)[DOI]
- E. Shriberg, "Effects of vocal effort and speaking style on text-independent speaker verification", Proceedings of 9th Annual Conference of the International Speech Communication Association, pp.609~612 (2008)
- T. Raitio, "Analysis and synthesis of shouted speech", Proceedings of 14th Annual Conference of the International Speech Communication Association, pp.1544~1548 (2013)
- D. S. Brungart, "The influence of vocal effort on human speaker identification", Proceedings of the 7th European Conference on Speech Communication and Technology, pp.747~750 (2001)
- R. Saeidi, "Feature extraction using power-law adjusted linear prediction with application to speaker recognition under severe vocal effort mismatch", IEEE, 2016, pp.24(1), 42~53
- S. T. Jovicic, "Acoustic analysis of consonants in whispered speech", Journal of Voice, 22(3), pp.263~274 (2008)[DOI]
- S. Ghaffarzadegan, "UT-VOCAL EFFORT II: analysis and constrained-lexicon recognition of whispered speech", Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing, pp.2544~2548 (2014)
- S. J. Wenndt, "A study on the classification of whispered and normally phonated speech", Proceedings of 7th International Conference on Spoken Language Processing, pp.649~652 (2002)
- C. Zhang, "Advancements in whisper-island detection within normally phonated audio streams", Proceedings of 10th Annual Conference of the International Speech Communication Association, pp.860~863 (2009)
- M. A. Carlin, "Unsupervised detection of whispered speech in the presence of normal phonation", Proceedings of 9th International Conference on Spoken Language Processing, pp.1~4 (2006)
- M. Sarria-Paja, "Whispered speech detection in noise using auditory-inspired modulation spectrum features", IEEE Signal Processing Letters, 20(8), pp.783~786 (2013)[DOI]
- C. Zhang, "Analysis and classification of speech mode: whispered through shouted", Proceedings of 8th Annual Conference of the International Speech Communication Association, pp.2289~2292 (2007)
- H. Chao, "Multi-level detection of vocal effort based on vowel template matching", Journal of Beijing University of Posts and Telecommunications, 39(4), pp.98~102 (2016)
- "LibSVM: a Library for Support Vector Machines" (2016)[URL]