RISS 검색 - 국내학술지논문 상세보기

다국어 초록 (Multilingual Abstract)

The main advantage of the statistical parametric speech synthesis is its flexibility in changing voice characteristics. A personalized text-to-speech(TTS) system can be implemented by combining a speech synthesis system and a voice transformation system, and it is widely used in many application areas. It is known that the fundamental frequency and the spectral envelope of speech signal can be independently modified to convert the voice characteristics. Also it is important to maintain naturalness of the transformed speech. In this paper, a speech synthesis system based on Hidden Markov Model(HMM-based speech synthesis, HTS) using the STRAIGHT vocoder is constructed and voice transformation is conducted by modifying the fundamental frequency and spectral envelope. The fundamental frequency is transformed in a scaling method, and the spectral envelope is transformed through frequency warping method to control the speaker’s vocal tract length. In particular, this study proposes a voice transformation method using the correlation between fundamental frequency and vocal tract length. Subjective evaluations were conducted to assess preference and mean opinion scores(MOS) for naturalness of synthetic speech. Experimental results showed that the proposed voice transformation method achieved higher preference than baseline systems while maintaining the naturalness of the speech quality.

목차 (Table of Contents)

Abstract
1. 서론
2. 기본주파수 및 성도길이 연관성 분석
3. 제안한 목소리변환 방법 및 실험결과
4. 결론

Abstract
1. 서론
2. 기본주파수 및 성도길이 연관성 분석
3. 제안한 목소리변환 방법 및 실험결과
4. 결론
참고문헌

참고문헌 (Reference)

1 Stylianou, Y., "Voice transformation: A survey" 3585-3588, 2009

2 Saheer, L., "Vocal tract length normalization for statistical parametric speech synthesis" 20 (20): 2134-2148, 2012

3 Sündermann, D., "VTLN-based voice conversion" 556-559, 2003

4 Tokuda, K., "Speech Synthesis Based on Hidden Markov Models" 1234-1252, 2013

5 Kawahara, H., "STRAIGHT, exploration of the other aspect of vocoder: Perceptually isomorphic decomposition of speech sounds" 27 : 349-353, 2006

6 Assmann, P. F., "Modeling the perception of frequency-shifted vowels" 425-428, 2002

7 Tokuda, K., "Mel-generalized cepstral analysis - A unified approach to speech spectral estimation" 1043-1046, 1994

8 Saheer, L., "Implementation of VTLN for Statistical Speech Synthesis" 224-229, 2010

9 Zen, H., "Details of the Nitech HMM-based speech synthesis system for Blizzard Challenge 2005" E90-D : 325-333, 2007