Long-Term Fundamental Frequency Modeling Based on Wavelet Packet Transform for Voice Conversion

He W, Zhao Y, Lin P, He Y, Feng Q. Long-Term Fundamental Frequency Modeling Based on Wavelet Packet Transform for Voice Conversion. J Audio Eng Soc. 2024;72(3):161-169. doi:10.17743/jaes.2022.0126

@article{He2024_22387,
  author = {He, Weijun and Zhao, Yongyong and Lin, Pei and He, Yuxin and Feng, Qi},
  title = {{Long-Term Fundamental Frequency Modeling Based on Wavelet Packet Transform for Voice Conversion}},
  journal = {Journal of the Audio Engineering Society},
  volume = {72},
  number = {3},
  pages = {161--169},
  year = {2024},
  month = mar,
  publisher = {Audio Engineering Society},
  doi = {10.17743/jaes.2022.0126},
  url = {https://doi.org/10.17743/jaes.2022.0126}
}

TY  - JOUR
TI  - Long-Term Fundamental Frequency Modeling Based on Wavelet Packet Transform for Voice Conversion
AU  - He, Weijun
AU  - Zhao, Yongyong
AU  - Lin, Pei
AU  - He, Yuxin
AU  - Feng, Qi
T2  - Journal of the Audio Engineering Society
J2  - J. Audio Eng. Soc.
VL  - 72
IS  - 3
SP  - 161
EP  - 169
PY  - 2024
DA  - 2024/03/06
DO  - 10.17743/jaes.2022.0126
UR  - https://doi.org/10.17743/jaes.2022.0126
PB  - Audio Engineering Society
LA  - en
AB  - Prosody conversion is an important part in voice conversion, where fundamental frequency (F0), which carries important speaker individuality information (e.g., tone, intonation, etc.), is regarded as one of the key prosodic features in the excitation model for speech synthesis. In a conventional approach based on continuous wavelet transform for modeling F0, analysis is carried out on a frame level and is prone to losing high-frequency information in the process of decomposition and reconstruction. In order to address this problem, the paper shows a representation of long-term fundamental frequency based on Wavelet Packet Transform (WPT). Specifically, the long-term F0 is decomposed usingWPT, and a joint vector is formed by combining the resulted average power spectrum. Furthermore, the method is applied in a voice conversion system. Voice conversion experiments are conducted on Chinese and English speech data to evaluate the performance of the proposed method. The results show that the proposed method is obviously better than the method based on wavelet transform in all conversion scenarios but performs a little worse than the method based on mean and variance in same-gender conversion scenario.
ER  -