Japanese Speech Synthesis Research Articles

Developing a bilingual communication aid for a Japanese ALS patient using voice conversion technique

A bilingual communication aid for a Japanese amyotrophic lateral sclerosis (ALS) patient has been developed. From our previous research, a corpus‐based speech synthesis method was ideal for synthesizing speech with voice quality identifiable as the patient's own. However, a recording of a large amount of speech, which is a burden for the patient, is required for such system. In this study, a voice conversion technique was applied so that a smaller amount of recording is needed for synthesis. An English speech synthesis system with the patient's voice was developed using Festival, a corpus‐based speech synthesizer with voice conversion technique. Two methods for Japanese speech synthesis were attempted using HTS toolkit. The first used an acoustic model built from all 503 recordings of the patient. The second used an acoustic model built from 503 wavefiles of which voice was converted to the patient's from a native speaker's. The latter method requires fewer recordings of the patient's. The result of the perceptual experiment showed that the voice synthesized with the latter was perceived to have a closer voice quality to the patient's natural speech. Last, GUI on windows was developed for the patient to synthesize speech by typing in the text.

Building an English speech synthetic voice using a voice transformation model from a Japanese male voice

This work reports development of an English speech synthetic voice using a voice transformation model for a Japanese amyotrophic lateral sclerosis patient as part of a project of developing a bilingual communication aid for this patient. The patient, who had a tracheotomy 3 years ago and had difficulty in speaking, wishes to speak in his own voice in his native language and in English. A Japanese speech synthesis system was developed using atr chatr 6 years ago and the authors have worked in developing a diphone‐based synthesis using festival speech synthesis system and festvox by having the patient read the diphone list. However, it was not an easy task for the patient to phonate and, moreover, to pronounce words in a foreign language. We therefore used a voice transformation model in festival to develop the patient’s English speech synthetic voice which enables text‐to‐speech synthesis. We trained using 30 sentences read by the patient and those synthesized with an existing festival diphone voice create...

Automatic synthesis unit generation for English speech synthesis based on multi-layered context oriented clustering

In this paper, we propose a new synthesis unit learning method aiming at multi-lingual speech synthesis and describe its application to English speech synthesis. The method termed Multi-Layered Context Oriented Clustering (ML-COC) is a generalized framework of the COC method which has been applied to Japanese speech synthesis. The conventional COC method produces a set of phonetic context dependent units through a cluster splitting process. In ML-COC, the notion of context is generalized and the factors other than phonetic context, such as stressing and syntactical boundaries, are taken into account to capture the richer phoneme variations of English. A synthesis unit generation experiment shows that ML-COC produces about three times as many synthesis units as the conventional COC (Single-Layered COC: SL-COC) method, and the average intra-cluster variance of ML-COC units is 20% lower than that of SL-COC. These results suggest that the ML-COC synthesis units reflect the phonological structure of English much more appropriately than do the SL-COC units. To validate the effectiveness of the ML-COC method, we conducted preference experiments using synthesized speech. The preference test exposed 10 subjects to 52 sentences. The ML-COC method was preferred over the conventional SL-COC method by a score of 70% to 30%.

The control of the articulatory parameters for the Japanese speech synthesis system by rule

The control of the articulatory parameters for the Japanese speech synthesis system by rule

The control of the prosodic features for the Japanese speech synthesis system by rule with editing functions

The control of the prosodic features for the Japanese speech synthesis system by rule with editing functions

The Japanese speech synthesis system with text editing and automatic prosodic control facilities

A Japanese speech synthesis system using a Japanese speech synthesizer by rule and software for text editing and automatic prosodic control has been developed. In the case of Japanese, there is a possibility that difference in accent type will cause differences in meaning, and that a word included in a compound word, such as a compound noun or verb, will have an accent type different from its original one. Therefore, the correct specification of the prosodic symbols is not so easy, even for people without any difficulty in hearing. The software for the text editing and for the automatic prosodic control inserts symbols for the prosodic control into the input text during the process of the text creation and editing in which the input kana string is converted to a kanji‐kana mixed sentence as in conventional Japanese word processors. On the other hand, the speech synthesizer uses phonemes as synthesis units and generates all acoustic parameters based on the 156 feature rules and 472 parameter rules. Since i...

Composite phoneme units for the speech synthesis of Japanese

Japanese speech synthesis techniques based on composite phoneme units are surveyed. Japanese is an open-syllable language, and there are no consonant clusters in its phonemic system. Japanese is therefore structured with simple and basic syllables of a CV-type, and these are widely used in Japanese speech synthesis-by-rule instead of single phonemes. Other composite syllabic units such as VCV or CVC are also used in Japanese speech synthesis to achieve coarticulatory characteristics. In this paper, a speech synthesis method using CVC units with excitation waveform elements is described as an attempt to improve the quality of synthetic speech.

Speech synthesis-by-rule of Japanese generated in the syntactic base

This report is the first attempt in Japanese speech synthesis generated in the syntactic base. While the authors have acoustic-phonetically analyzed an amount of speech data, they also have brough forth theoretical refinement to the rule system of Japanese phonology and syntax [J. D. McCawlay, The Phonological Compoment of a Grammar of Japanese (Mouton, The Hague, 1968); H. Yoshiba Ling. Analysis 7, 241–262 (1981)]. Both seek a generative model for the speech data and for verifying the theory that a speech synthesis-by-rule system is now in progress comprising phonological rules as well as other higher-level generations. It is shown that purely phonological interpretation of some of the forms yields ad hoc rules and complicates the system, and hence that by restructuring the syntactic/phonological organization remarkable simplification in the phonological rules can be attained. It is expected that this significant modification in the theory can bring constructive generalization and rearrangement to the synthesis-by-rule system of Japanese.