著者

Kei Sawada Kei Hashimoto Keiichiro Oura Yoshihiko Nankaku Keiichi Tokuda

出版者

ACOUSTICAL SOCIETY OF JAPAN

雑誌

Acoustical Science and Technology (ISSN:13463969)

巻号頁・発行日

vol.39, no.2, pp.119-129, 2018-03-01 (Released:2018-03-01)

参考文献数

35

---

This paper proposes a method for constructing text-to-speech (TTS) systems for languages with unknown pronunciations. One goal of speech synthesis research is to establish a framework that can be used to construct TTS systems for any written language. Generally, language-specific knowledge is required to construct TTS systems for a new language. However, it is difficult to acquire language-specific knowledge in each new language. Therefore, constructing a TTS system for a new language entails huge costs. To address this problem, we investigate a framework for automatically constructing a TTS system from a target language database consisting of only speech data and corresponding Unicode texts. In the proposed method, pseudo phonetic information of the target language with unknown pronunciation is obtained by a speech recognizer of a rich-resource proxy language. Then, a grapheme-to-phoneme converter and a statistical parametric speech synthesizer are constructed based on the obtained pseudo phonetic information. The proposed method was applied to Japanese and was evaluated in terms of objective and subjective measures. Additionally, we challenged the construction of TTS systems for nine Indian languages using the proposed method, and TTS systems were evaluated in the Blizzard Challenge 2014 and 2015.

著者

Kei SAWADA Akira TAMAMORI Kei HASHIMOTO Yoshihiko NANKAKU Keiichi TOKUDA

出版者

The Institute of Electronics, Information and Communication Engineers

雑誌

IEICE TRANSACTIONS on Information and Systems (ISSN:09168532)

巻号頁・発行日

vol.E99-D, no.12, pp.3119-3131, 2016-12-01

---

This paper proposes a Bayesian approach to image recognition based on separable lattice hidden Markov models (SL-HMMs). The geometric variations of the object to be recognized, e.g., size, location, and rotation, are an essential problem in image recognition. SL-HMMs, which have been proposed to reduce the effect of geometric variations, can perform elastic matching both horizontally and vertically. This makes it possible to model not only invariances to the size and location of the object but also nonlinear warping in both dimensions. The maximum likelihood (ML) method has been used in training SL-HMMs. However, in some image recognition tasks, it is difficult to acquire sufficient training data, and the ML method suffers from the over-fitting problem when there is insufficient training data. This study aims to accurately estimate SL-HMMs using the maximum a posteriori (MAP) and variational Bayesian (VB) methods. The MAP and VB methods can utilize prior distributions representing useful prior information, and the VB method is expected to obtain high generalization ability by marginalization of model parameters. Furthermore, to overcome the local maximum problem in the MAP and VB methods, the deterministic annealing expectation maximization algorithm is applied for training SL-HMMs. Face recognition experiments performed on the XM2VTS database indicated that the proposed method offers significantly improved image recognition performance. Additionally, comparative experiment results showed that the proposed method was more robust to geometric variations than convolutional neural networks.

著者

Kazuhiro NAKAMURA Kei HASHIMOTO Yoshihiko NANKAKU Keiichi TOKUDA

出版者

The Institute of Electronics, Information and Communication Engineers

雑誌

IEICE TRANSACTIONS on Information and Systems (ISSN:09168532)

巻号頁・発行日

vol.E97-D, no.6, pp.1438-1448, 2014-06-01

---

This paper proposes a novel approach for integrating spectral feature extraction and acoustic modeling in hidden Markov model (HMM) based speech synthesis. The statistical modeling process of speech waveforms is typically divided into two component modules: the frame-by-frame feature extraction module and the acoustic modeling module. In the feature extraction module, the statistical mel-cepstral analysis technique has been used and the objective function is the likelihood of mel-cepstral coefficients for given speech waveforms. In the acoustic modeling module, the objective function is the likelihood of model parameters for given mel-cepstral coefficients. It is important to improve the performance of each component module for achieving higher quality synthesized speech. However, the final objective of speech synthesis systems is to generate natural speech waveforms from given texts, and the improvement of each component module does not always lead to the improvement of the quality of synthesized speech. Therefore, ideally all objective functions should be optimized based on an integrated criterion which well represents subjective speech quality of human perception. In this paper, we propose an approach to model speech waveforms directly and optimize the final objective function. Experimental results show that the proposed method outperformed the conventional methods in objective and subjective measures.

著者

Yosuke Uto Yoshihiko Nankaku Tomoki Toda Akinobu Lee Keiichi Tokuda

巻号頁・発行日

pp.2278-2281, 2006-09

---

This paper describes the voice conversion based on the Mixtures of Factor Analyzers (MFA) which can provide an efficient modeling with a limited amount of training data. As a typical spectral conversion method, a mapping algorithm based on the Gaussian Mixture Model (GMM) has been proposed. In this method two kinds of covariance matrix structures are often used : the diagonal and full covariance matrices. GMM with diagonal covariance matrices requires a large number of mixture components for accurately estimating spectral features. On the other hand, GMM with full covariance matrices needs sufficient training data to estimate model parameters. In order to cope with these problems, we apply MFA to voice conversion. MFA can be regarded as intermediate model between GMM with diagonal covariance and with full covariance. Experimental results show that MFA can improve the conversion accuracy compared with the conventional GMM.

著者

Akira TAMAMORI Yoshihiko NANKAKU Keiichi TOKUDA

出版者

The Institute of Electronics, Information and Communication Engineers

雑誌

IEICE TRANSACTIONS on Information and Systems (ISSN:09168532)

巻号頁・発行日

vol.E97-D, no.7, pp.1842-1854, 2014-07-01

---

In this paper, a novel statistical model based on 2-D HMMs for image recognition is proposed. Recently, separable lattice 2-D HMMs (SL2D-HMMs) were proposed to model invariance to size and location deformation. However, their modeling accuracy is still insufficient because of the following two assumptions, which are inherited from 1-D HMMs: i) the stationary statistics within each state and ii) the conditional independent assumption of state output probabilities. To overcome these shortcomings in 1-D HMMs, trajectory HMMs were proposed and successfully applied to speech recognition and speech synthesis. This paper derives 2-D trajectory HMMs by reformulating the likelihood of SL2D-HMMs through the imposition of explicit relationships between static and dynamic features. The proposed model can efficiently capture dependencies between adjacent observations without increasing the number of model parameters. The effectiveness of the proposed model was evaluated in face recognition experiments on the XM2VTS database.

著者

Yoshihiko Nankaku Kenichi Nakamura Tomoki Toda Keiichi Tokuda

巻号頁・発行日

2007-08

---

This paper proposes a spectral conversion technique based on a new statistical model which includes time-sequence matching. In conventional GMM-based approaches, the Dynamic Programming (DP) matching between source and target feature sequences is performed prior to the training of GMMs. Although a similarity measure of two frames, e.g., the Euclid distance is typically adopted, this might be inappropriate for converting the spectral features. The likelihood function of the proposed model can directly deal with two different length sequences, in which a frame alignment of source and target feature sequences is represented by discrete hidden variables. In the proposed algorithm, the maximum likelihood criterion is consistently applied to the training of model parameters, sequence matching and spectral conversion. In the subjective preference test, the proposed method is superior than the conventional GMM-based method.

著者

Akira TAMAMORI Yoshihiko NANKAKU Keiichi TOKUDA

出版者

The Institute of Electronics, Information and Communication Engineers

雑誌

IEICE TRANSACTIONS on Information and Systems (ISSN:09168532)

巻号頁・発行日

vol.E95-D, no.8, pp.2074-2083, 2012-08-01

---

This paper proposes a new generative model which can deal with rotational data variations by extending Separable Lattice 2-D HMMs (SL2D-HMMs). In image recognition, geometrical variations such as size, location and rotation degrade the performance. Therefore, the appropriate normalization processes for such variations are required. SL2D-HMMs can perform an elastic matching in both horizontal and vertical directions; this makes it possible to model invariance to size and location. To deal with rotational variations, we introduce additional HMM states which represent the shifts of the state alignments among the observation lines in a particular direction. Face recognition experiments show that the proposed method improves the performance significantly for rotational variation data.