Publications by Yoshinori Shiga

This thesis addresses the problem of quality degradation in speech produced by parameter-based speech synthesis, within the framework of an articulatory-acoustic forward mapping. I first investigate current problems in speech parameterisation, and point out the fact that conventional parameterisation inaccurately extracts the vocal tract response due to interference from the harmonic structure of voiced speech. To overcome this problem, I introduce a method for estimating filter responses more precisely from periodic signals. The method achieves such estimation in the frequency domain by approximating all the harmonics observed in several frames based on a least squares criterion. It is shown that the proposed method is capable of estimating the response more accurately than widely-used frame-by-frame parameterisation, for simulations using synthetic speech and for an articulatory-acoustic mapping using actual speech. I also deal with the source-filter separation problem and independent control of the voice source characteristic during speech synthesis. I propose a statistical approach to separating out the vocal-tract filter response from the voice source characteristic using a large articulatory database. The approach realises such separation for voiced speech using an iterative approximation procedure under the assumption that the speech production process is a linear system composed of a voice source and a vocal-tract filter, and that each of the components is controlled independently by different sets of factors. Experimental results show that controlling the source characteristic greatly improves the accuracy of the articulatory-acoustic mapping, and that the spectral variation of the source characteristic is evidently influenced by the fundamental frequency or the power of speech. The thesis provides more accurate acoustical approximation of the vocal tract response, which will be beneficial in a wide range of speech technologies, and lays the groundwork in speech science for a new type of corpus-based statistical solution to the source-filter separation problem.

In this paper we examine a method for separating out the vocal-tract filter response from the voice source characteristic using a large articulatory database. The method realises such separation for voiced speech using an iterative approximation procedure under the assumption that the speech production process is a linear system composed of a voice source and a vocal-tract filter, and that each of the components is controlled independently by different sets of factors. Experimental results show that the spectral variation is evidently influenced by the fundamental frequency or the power of speech, and that the tendency of the variation may be related closely to speaker identity. The method enables independent control over the voice source characteristic in our articulation-to-speech synthesis.

This paper presents an articulatory-acoustic mapping where detailed spectral envelopes are estimated. During the estimation, the harmonics of a range of F0 values are derived from the spectra of multiple voiced speech signals vocalized with similar articulator settings. The envelope formed by these harmonics is represented by a cepstrum, which is computed by fitting the peaks of all the harmonics based on the weighted least square method in the frequency domain. The experimental result shows that the spectral envelopes are estimated with the highest accuracy when the cepstral order is 48-64 for a female speaker, which suggests that representing the real response of the vocal tract requires high-quefrency elements that conventional speech synthesis methods are forced to discard in order to eliminate the pitch component of speech.

This paper introduces a novel articulatory-acoustic mapping in which detailed spectral envelopes are estimated based on the cepstrum, inclusive of the high-quefrency elements which are discarded in conventional speech synthesis to eliminate the pitch component of speech. For this estimation, the method deals with the harmonics of multiple voiced-speech spectra so that several sets of harmonics can be obtained at various pitch frequencies to form a spectral envelope. The experimental result shows that the method estimates spectral envelopes with the highest accuracy when the cepstral order is 48-64, which suggests that the higher order coeffcients are required to represent detailed envelopes reflecting the real vocal-tract responses.

A new approach is presented for estimating voice source and vocal-tract filter characteristics based on an articulatory database. From the viewpoint of acoustics, in order to estimate the transfer function of a system, both the input and output of the system need to be observed. In the case of the source-filter separation problem, however, only the output (i.e. speech) is observable, and the response of the system (vocal tract) and the input (voice source) must be estimated simultaneously. The estimation is hence theoretically impossible, and consequently the estimation problem is generally solved approximately by applying rather oversimplified models. The proposed approach separates these two characteristics under the assumption that each of the characteristics is controlled independently by a different set of factors. The separation is achieved by iterative approximation based on the above assumption using a large speech corpus including electro-magnetic articulograph data. The proposed approach enables the independent control of the source and filter characteristics, and thus contributes toward improving speech quality in speech synthesis.

This paper proposes a novel approach for estimating the spectral envelope of voiced speech independently of its harmonic structure. Because of the quasi-periodicity of voiced speech, its spectrum indicates harmonic structure and only has energy at frequencies corresponding to integral multiples of F0. It is hence impossible to identify transfer characteristics between the adjacent harmonics. In order to resolve this problem, Multi-frame Analysis (MFA) is introduced. The MFA estimates a spectral envelope using many portions of speech which are vocalised using the same vocal-tract shape. Since each of the portions usually has a different F0 and ensuing different harmonic structure, a number of harmonics can be obtained at various frequencies to form a spectral envelope. The method thereby gives a closer approximation to the vocal-tract transfer function.

This paper presents a new approach for estimating voice source and vocal tract filter characteristics of voiced speech. When it is required to know the transfer function of a system in signal processing, the input and output of the system are experimentally observed and used to calculate the function. However, in the case of source-filter separation we deal with in this paper, only the output (speech) is observed and the characteristics of the system (vocal tract) and the input (voice source) must simultaneously be estimated. Hence the estimate becomes extremely difficult, and it is usually solved approximately using oversimplified models. We demonstrate that these characteristics are separable under the assumption that they are independently controlled by different factors. The separation is realised using an iterative approximation along with the Multi-frame Analysis method, which we have proposed to find spectral envelopes of voiced speech with minimum interference of the harmonic structure.

This paper proposes a new method that determines segmental duration for text-to-speech conversion based on the movement of articulatory organs which compose an articulatory model. The articulatory model comprises four time-variable articulatory parameters representing the conditions of articulatory organs whose physical restriction seems to significantly influence the segmental duration. The parameters are controlled according to an input sequence of phonetic symbols, following which segmental duration is determined based on the variation of the articulatory parameters. The proposed method is evaluated through an experiment using a Japanese speech database that consists of 150 phonetically balanced sentences. The results indicate that the mean square error of predicted segmental duration is approximately 15[ms] for the closed set and 15-17[ms] for the open set. The error is within 20[ms], the level of acceptability for distortion of segmental duration without loss of naturalness, and hence the method is proved to effectively predict segmental duration.