Takayoshi Yoshimura

Bio: Takayoshi Yoshimura is an academic researcher from Toyota. The author has contributed to research in topics: Speech synthesis & Hidden Markov model. The author has an hindex of 16, co-authored 37 publications receiving 2783 citations. Previous affiliations of Takayoshi Yoshimura include Nagoya Institute of Technology.

Speech parameter generation algorithms for HMM-based speech synthesis

Abstract: This paper derives a speech parameter generation algorithm for HMM-based speech synthesis, in which the speech parameter sequence is generated from HMMs whose observation vector consists of a spectral parameter vector and its dynamic feature vectors. In the algorithm, we assume that the state sequence (state and mixture sequence for the multi-mixture case) or a part of the state sequence is unobservable (i.e., hidden or latent). As a result, the algorithm iterates the forward-backward algorithm and the parameter generation algorithm for the case where the state sequence is given. Experimental results show that by using the algorithm, we can reproduce clear formant structure from multi-mixture HMMs as compared with that produced from single-mixture HMMs.

Simultaneous Modeling of Spectrum, Pitch and Duration in HMM-Based Speech Synthesis

Abstract: In this paper, we describe an HMM-based speech synthesis system in which spectrum, pitch and state duration are modeled simultaneously in a unified framework of HMM. In the system, pitch and state duration are modeled by multi-space probability distribution HMMs and multi-dimensional Gaussian distributions, respectively. The distributions for spectral parameter, pitch parameter and the state duration are clustered independently by using a decision-tree based context clustering technique. Synthetic speech is generated by using an speech parameter generation algorithm from HMM and a mel-cepstrum based vocoding technique. Through informal listening tests, we have confirmed that the proposed system successfully synthesizes natural-sounding speech which resembles the speaker in the training database.

Mixed Excitation for HMM-based Speech Synthesis

Abstract: This paper describes improvements on the excitation model of an HMM-based text-to-speech system. In our previous work, natural sounding speech can be synthesized from trained HMMs. However, it has a typical quality of “vocoded speech” since the system uses a traditional excitation model with either a periodic impulse train or white noise. In this paper, in order to reduce the synthetic quality, a mixed excitation model used in MELP is incorporated into the system. Excitation parameters used in mixed excitation are modeled by HMMs, and generated from HMMs by a parameter generation algorithm in the synthesis phase. The result of a listening test shows that the mixed excitation model significantly improves quality of synthesized speech as compared with the traditional excitation model.

Speaker interpolation for HMM-based speech synthesis system.

Abstract: This paper describes an approach to voice characteristics conversion for an HMM-based text-to-speech synthesis system using speaker interpolation.Although most text-to-speech synthesis systems which synthesize speech by concatenating speech units can synthesize speech with acceptable quality, they still cannot synthesize speech with various voice quality such as speaker individualities and emotions;In order to control speaker individualities and emotions, therefore, they need a large database, which records speech units with various voice characteristics in sythesis phase.On the other hand, our system synthesize speech with untrained speaker’s voice quality by interpolating HMM parameters among some representative speakers’ HMM sets.Accordingly, our system can synthesize speech with various voice quality without large database in synthesis phase.An HMM interpolation technique is derived from a probabilistic similarity measure for HMMs, and used to synthesize speech with untrained speaker’s voice quality by interpolating HMM parameters among some representative speakers’ HMM sets.The results of subjective experiments show that we can gradually change the voice quality of synthesized speech from one’s to the other’s by changing the interpolation ratio.

Duration modeling for HMM-based speech synthesis.

Abstract: This paper proposes a new approach to state duration modeling for HMM-based speech synthesis. A set of state durations of each phoneme HMM is modeled by a multi-dimensional Gaussian distribution, and duration models are clustered using a decision tree based context clustering technique. In the synthesis stage, state durations are determined by using the state duration models. In this paper, we take account of contextual factors such as stressrelated factors and locational factors in addition to phone identity factors. Experimental results show that we can synthesize good quality speech with natural timing, and the speaking rate can be varied easily.

Statistical Parametric Speech Synthesis

Abstract: This paper gives a general overview of techniques in statistical parametric speech synthesis. One of the instances of these techniques, called HMM-based generation synthesis (or simply HMM-based synthesis), has recently been shown to be very effective in generating acceptable speech synthesis. This paper also contrasts these techniques with the more conventional unit selection technology that has dominated speech synthesis over the last ten years. Advantages and disadvantages of statistical parametric synthesis are highlighted as well as identifying where we expect the key developments to appear in the immediate future.

贝叶斯滤波与平滑 (Bayesian filtering and smoothing)

Abstract: Filtering and smoothing methods are used to produce an accurate estimate of the state of a time-varying system based on multiple observational inputs (data). Interest in these methods has exploded in recent years, with numerous applications emerging in fields such as navigation, aerospace engineering, telecommunications, and medicine. This compact, informal introduction for graduate students and advanced undergraduates presents the current state-of-the-art filtering and smoothing methods in a unified Bayesian framework. Readers learn what non-linear Kalman filters and particle filters are, how they are related, and their relative advantages and disadvantages. They also discover how state-of-the-art Bayesian parameter estimation methods can be combined with state-of-the-art filtering and smoothing algorithms. The book’s practical and algorithmic approach assumes only modest mathematical prerequisites. Examples include MATLAB computations, and the numerous end-of-chapter exercises include computational assignments. MATLAB/GNU Octave source code is available for download at www.cambridge.org/sarkka, promoting hands-on work with the methods.

Speech parameter generation algorithms for HMM-based speech synthesis

Abstract: This paper derives a speech parameter generation algorithm for HMM-based speech synthesis, in which the speech parameter sequence is generated from HMMs whose observation vector consists of a spectral parameter vector and its dynamic feature vectors. In the algorithm, we assume that the state sequence (state and mixture sequence for the multi-mixture case) or a part of the state sequence is unobservable (i.e., hidden or latent). As a result, the algorithm iterates the forward-backward algorithm and the parameter generation algorithm for the case where the state sequence is given. Experimental results show that by using the algorithm, we can reproduce clear formant structure from multi-mixture HMMs as compared with that produced from single-mixture HMMs.

Voice Conversion Based on Maximum-Likelihood Estimation of Spectral Parameter Trajectory

Abstract: In this paper, we describe a novel spectral conversion method for voice conversion (VC). A Gaussian mixture model (GMM) of the joint probability density of source and target features is employed for performing spectral conversion between speakers. The conventional method converts spectral parameters frame by frame based on the minimum mean square error. Although it is reasonably effective, the deterioration of speech quality is caused by some problems: 1) appropriate spectral movements are not always caused by the frame-based conversion process, and 2) the converted spectra are excessively smoothed by statistical modeling. In order to address those problems, we propose a conversion method based on the maximum-likelihood estimation of a spectral parameter trajectory. Not only static but also dynamic feature statistics are used for realizing the appropriate converted spectrum sequence. Moreover, the oversmoothing effect is alleviated by considering a global variance feature of the converted spectra. Experimental results indicate that the performance of VC can be dramatically improved by the proposed method in view of both speech quality and conversion accuracy for speaker individuality.