CheapTrick, a spectral envelope estimator for high-quality speech synthesis

Abstract A spectral envelope estimation algorithm is presented to achieve high-quality speech synthesis. The concept of the algorithm is to obtain an accurate and temporally stable spectral envelope. The algorithm uses fundamental frequency (F0) and consists of F0-adaptive windowing, smoothing of the power spectrum, and spectral recovery in the quefrency domain. Objective and subjective evaluations were carried out to demonstrate the effectiveness of the proposed algorithm. Results of both evaluations indicated that the proposed algorithm can obtain a temporally stable spectral envelope and synthesize speech with higher sound quality than speech synthesized with other algorithms.

[1]  Masataka Goto,et al.  A spectral envelope estimation method based on F0-adaptive multi-frame integration analysis , 2012, SAPA@INTERSPEECH.

[2]  Heiga Zen,et al.  Statistical parametric speech synthesis using deep neural networks , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[3]  Hideki Kawahara,et al.  v.morish'09: A Morphing-Based Singing Design Interface for Vocal Melodies , 2009, ICEC.

[4]  Amro El-Jaroudi,et al.  Discrete all-pole modeling , 1991, IEEE Trans. Signal Process..

[5]  Tomoki Toda,et al.  Improvements of the One-to-Many Eigenvoice Conversion System , 2010, IEICE Trans. Inf. Syst..

[6]  Hideki Kawahara,et al.  Restructuring speech representations using a pitch-adaptive time-frequency smoothing and an instantaneous-frequency-based F0 extraction: Possible role of a repetitive structure in sounds , 1999, Speech Commun..

[7]  Eric Moulines,et al.  Estimation of the spectral envelope of voiced sounds using a penalized likelihood approach , 2001, IEEE Trans. Speech Audio Process..

[8]  A. Noll.  Short‐Time Spectrum and “Cepstrum” Techniques for Vocal‐Pitch Detection , 1964 .

[9]  A. Oppenheim.  Speech analysis-synthesis system based on homomorphic filtering. , 1969, The Journal of the Acoustical Society of America.

[10]  Hideki Kawahara,et al.  Temporally variable multi-aspect auditory morphing enabling extrapolation without objective and perceptual breakdown , 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

[11]  Thomas F. Quatieri,et al.  Speech analysis/Synthesis based on a sinusoidal representation , 1986, IEEE Trans. Acoust. Speech Signal Process..

[12]  Keiichi Tokuda,et al.  Statistical approach to vocal tract transfer function estimation based on factor analyzed trajectory HMM , 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

[13]  Takashi Nose,et al.  Statistical Parametric Speech Synthesis Based on Gaussian Process Regression , 2014, IEEE Journal of Selected Topics in Signal Processing.

[14]  HIDEKI KAWAHARA,et al.  Technical foundations of TANDEM-STRAIGHT, a speech analysis, modification and synthesis framework , 2011 .

[15]  M. Mathews,et al.  Pitch Synchronous Analysis of Voiced Sounds , 1961 .

[16]  Heiga Zen,et al.  Statistical Parametric Speech Synthesis , 2007, IEEE International Conference on Acoustics, Speech, and Signal Processing.

[17]  Roland Badeau,et al.  Weighted maximum likelihood autoregressive and moving average spectrum modeling , 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

[18]  Hideki Kawahara,et al.  Tandem-STRAIGHT: A temporally stable power spectral representation for periodic signals and applications to interference-free spectrum, F0, and aperiodicity estimation , 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

[19]  Eric Moulines,et al.  Pitch-synchronous waveform processing techniques for text-to-speech synthesis using diphones , 1989, Speech Commun..

[20]  Hideki Kenmochi,et al.  Singing synthesis as a new musical instrument , 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[21]  L. H. Anauer,et al.  Speech Analysis and Synthesis by Linear Prediction of the Speech Wave , 2000 .

[22]  M. Unser.  Sampling-50 years after Shannon , 2000, Proceedings of the IEEE.