Emotional Analysis and Synthesis of Human Voice Based on STRAIGHT

Abstract:

Speech synthesis is a hot research of artificial intelligence today, and urgent difficulty to overcome is how to make the machine more "emotional intelligence" for the human-computer interaction. With the STRAIGHT algorithm, this paper extracted the acoustic feature parameters of the speech signals and did statistical analysis, modified the characteristic parameters of the neutral sounds to synthesize emotional speeches, including happy, angry, frustration, then analyzed a frame of spectrum of synthetic emotional speeches through standard voices, voices added noise and voices de-nosing. The experimental results show that the method is feasible and the synthetic emotional speeches through voices de-nosing are better than voices added noise.

• Periodical: Applied Mechanics and Materials (Volumes 536-537)
• Pages: 105-110
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.536-537.105
• Online since: April 2014
• Authors: Ran Ran Chang, Xiao Qing Yu*, Ying Ying Yuan, Wang Gen Wan
• Keywords: Acoustic Feature Parameters, Emotional Speeches, Frame of Spectrum, Speech Synthesis, Straight

References

[1] Ning Wang. Emotional speech conversion by Pitch Target model and adjustment of the prosodic parameter. Soochow University, (2012).

[2] Zhang S, Xu Y, Jia J, et al. Analysis and Modeling of Affective Audio Visual Speech Based on PAD Emotion Space[C] Chinese Spoken Language Processing, 2008. ISCSLP'08. 6th International Symposium on. IEEE, 2008: 1-4.

DOI: 10.1109/chinsl.2008.ecp.82

[3] Li Zhao, communication. Speech signal processing [M]. Machinery Industry Press, Beijing, (2009).

[4] Method of personalized speech generation based on STRAIGHT algorithm[J]. Science and technology in Gansu, 2010 (004): 34-35.

[5] Zhang H, Yang Y. Fundamental frequency adjustment and formant transition based emotional speech synthesis[C]. Fuzzy Systems and Knowledge Discovery (FSKD), 2012 9th International Conference on. IEEE, 2012: 1797-1801. Brown, F., The title of the patent (if available),. British Patent 123456, July (2004).

DOI: 10.1109/fskd.2012.6234018

[6] Shue Y L, Keating P, Vicenik C, et al. VoiceSauce: A program for voice analysis[J]. Energy, 2010, 1(H2): H1-A1.

[7] Ren R, Miao Z. Emotional speech synthesis and its application to pervasive E-learning[C]. Ubi-Media Computing, 2008 First IEEE International Conference on. IEEE, 2008: 431-435.

DOI: 10.1109/umedia.2008.4570930

[8] Qin Y, Zhang X, Ying H. A hmm-based fuzzy affective model for emotional speech synthesis[C]. Signal Processing Systems (ICSPS), 2010 2nd International Conference on. IEEE, 2010, 3: V3-525-V3-528.

DOI: 10.1109/icsps.2010.5555658

[9] Wang M, Li Y, Lin M, et al. The development of a database of functional and emotional intonation in Chinese[C]. Speech Database and Assessments (Oriental COCOSDA), 2011 International Conference on. IEEE, 2011: 136-141.

DOI: 10.1109/icsda.2011.6085995

[10] Kawahara H, Morise M. Technical foundations of TANDEM-STRAIGHT, a speech analysis, modification and synthesis framework[J]. Sadhana, 2011, 36(5): 713-727.

DOI: 10.1007/s12046-011-0043-3