An adaptive algorithm for mel-cepstral analysis of speech

@article{Fukada1992AnAA,
  title={An adaptive algorithm for mel-cepstral analysis of speech},
  author={Toshiaki Fukada and Keiichi Tokuda and Takao Kobayashi and Satoshi Imai},
  journal={[Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing},
  year={1992},
  volume={1},
  pages={137-140 vol.1}
}
  • T. Fukada, K. Tokuda, S. Imai
  • Published 23 March 1992
  • Engineering
  • [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing
The authors describe a mel-cepstral analysis method and its adaptive algorithm. In the proposed method, the authors apply the criterion used in the unbiased estimation of log spectrum to the spectral model represented by the mel-cepstral coefficients. To solve the nonlinear minimization problem involved in the method, they give an iterative algorithm whose convergence is guaranteed. Furthermore, they derive an adaptive algorithm for the mel-cepstral analysis by introducing an instantaneous… 

Figures and Tables from this paper

Mel-generalized cepstral analysis - a unified approach to speech spectral estimation

TLDR
A spectral estimation method which uses the spectral model represented by mel-generalized cepstral coefficients is proposed, which is demonstrated by an experiment of HMM-based isolated word recognition.

Adaptive mel cepstral analysis based on UELS method

  • S. Imai
  • Computer Science
    Proceedings of the IEEE 2000 Adaptive Systems for Signal Processing, Communications, and Control Symposium (Cat. No.00EX373)
  • 2000
TLDR
An adaptive mel cepstral analysis technique based on the UELS (unbiased estimation of log spectrum) method, which has fast convergence properties in comparison with the LMS algorithm is proposed.

Speech coding based on adaptive mel-cepstral analysis

TLDR
An ADPCM coder is proposed which uses a backward adaptive predictor based on the adaptive mel-cepstral analysis, and a pitch predictor is incorporated into the coder, and the speech quality is evaluated based on objective and subjective performance tests.

Integration of acoustic modeling and mel-cepstral analysis for HMM-based speech synthesis

TLDR
An approach to modeling speech waveforms as an integrative model is proposed and the possibility of improving synthesized speech is shown.

An algorithm for speech parameter generation from continuous mixture HMMs with dynamic features

TLDR
This paper proposes an algorithm for speech parameter generation from continuous mixture HMMs which include dynamic features, i.e., delta and delta-delta parameters of speech, and derives a fast algorithm on the analogy of the RLS algorithm for adaptive ltering.

STATISTICAL SPECTRAL ENVELOPE TRANSFORMATION APPLIED TO EMOTIONAL SPEECH

TLDR
A data driven voice transformation algorithm is used to alter the timbre of a neutral (non-emotional) voice in order to reproduce a particular emotional vocal timbre.

Mel-Cepstrum-Based Quantization Noise Shaping Applied to Neural-Network-Based Speech Waveform Synthesis

TLDR
Experiments showed that speech quality is significantly improved by the proposed mel-cepstrum-based quantization noise shaping method, which effectively masks the white noise introduced by the quantization typically used in neural-network-based speech waveform synthesis systems.

Considering Global Variance of the Log Power Spectrum Derived from Mel-Cepstrum in HMM-based Parametric Speech Synthesis

TLDR
Experimental results show that the parameter generation algorithm using LPS-GV model produces more natural acoustic features than the conventional GV modeling method when mel-cepstrum features are adopted.

A mel-cepstral analysis technique restoring high frequency components from low-sampling-rate speech

TLDR
This work proposes a melcepstral analysis technique that restores missing high frequency components from low-sampling-rate speech with a statistical approach and shows that the proposed method improved the quality of synthesized speech.

A Speech Parameter Generation Algorithm Considering Global Variance for HMM-Based Speech Synthesis

TLDR
A generation algorithm considering not only the HMM likelihood maximized in the conventional algorithm but also a likelihood for a global variance of the generated trajectory works as a penalty for the over-smoothing.
...

References

SHOWING 1-10 OF 13 REFERENCES

Adaptive filtering based on cepstral representation-adaptive cepstral analysis of speech

TLDR
It is shown that the adaptive cepstral analysis method based on an unbiased estimation of the log spectrum has fast convergence properties in comparison with the least-mean-square algorithm.

Mel Log Spectrum Approximation (MLSA) filter for speech synthesis

TLDR
A method of constructing the mel-log spectrum approximation (MLSA) filter, which has a relatively simple structure and a low coefficient sensitivity, together with a design example of MLSA filter for speech synthesis.

Complex Chebyshev approximation for IIR digital filters using an iterative WLS technique

  • Takao KobayashiS. Imai
  • Computer Science
    International Conference on Acoustics, Speech, and Signal Processing
  • 1990
TLDR
A technique for designing IIR (infinite impulse response) filters with a complex-valued frequency response is proposed, whose real and imaginary parts represent the log magnitude and phase errors, respectively, is minimized using an iterative weighted-least-squares technique in the frequency domain.

Adaptive Signal Processing

TLDR
This chapter discusses Adaptive Arrays and Adaptive Beamforming, as well as other Adaptive Algorithms and Structures, and discusses the Z-Transform in Adaptive Signal Processing.

: “ Spectral estimation of speech based on mel - cepstral representation

  • Integral Equations and Operator Theory
  • 1985

Spectral estimation of speech based on mel-cepstral representation

  • Ji4-A
  • 1991

A study of speech coding based on the adaptive mel-cepstral analysis

  • A study of speech coding based on the adaptive mel-cepstral analysis
  • 1991

Adaptive mel-cepstral analysis of speech

  • J74-A
  • 1991

Unbiased estimator of log spect r u m and its application to speech signal processing

  • Proc
  • 1988