• Title/Summary/Keyword: Segmental

Search Result 1,159, Processing Time 0.048 seconds

UA Tree-based Reduction of Speech DB in a Large Corpus-based Korean TTS (대용량 한국어 TTS의 결정트리기반 음성 DB 감축 방안)

  • Lee, Jung-Chul
    • Journal of the Korea Society of Computer and Information
    • /
    • v.15 no.7
    • /
    • pp.91-98
    • /
    • 2010

  • Large corpus-based concatenating Text-to-Speech (TTS) systems can generate natural synthetic speech without additional signal processing. Because the improvements in the natualness, personality, speaking style, emotions of synthetic speech need the increase of the size of speech DB, it is necessary to prune the redundant speech segments in a large speech segment DB. In this paper, we propose a new method to construct a segmental speech DB for the Korean TTS system based on a clustering algorithm to downsize the segmental speech DB. For the performance test, the synthetic speech was generated using the Korean TTS system which consists of the language processing module, prosody processing module, segment selection module, speech concatenation module, and segmental speech DB. And MOS test was executed with the a set of synthetic speech generated with 4 different segmental speech DBs. We constructed 4 different segmental speech DB by combining CM1(or CM2) tree clustering method and full DB (or reduced DB). Experimental results show that the proposed method can reduce the size of speech DB by 23% and get high MOS in the perception test. Therefore the proposed method can be applied to make a small sized TTS.

  • https://doi.org/10.9708/jksci.2010.15.7.091 인용 PDF KSCI

A Study on the selecting behavior of restaurant by segmental group based on foodservice motivation (외식동기에 기초한 세분집단별 외식점 선택행동에 관한 연구)

  • Kim, Young-Hee
    • Journal of Digital Convergence
    • /
    • v.20 no.4
    • /
    • pp.159-168
    • /
    • 2022

  • This study was conducted to classify segmental group based on the factors of foodservice motivation and then conducted a survey for one month from July 15 to August 14, 2021 to analyze the influence of demographic characteristics, usage behavior, and motivation on eating out choice behavior. A total of 310 copies were used for empirical analysis. The result is as follows. First, males showed higher task type than females, and females showed higher number of change type, gastronomic type, and fit type. Second, in demographic characteristics, all groups showed strong motivation for foodservice in married people aged 31-40 and 41-50. Third, in the restaurant selecting behavior difference between the segmental groups according to the motivation for foodservice the most preferred menu was korean food for fit type, gourmet type, duty type and western food was the highest in the change type. Fourth, in the ordering method of difference in restaurant selecting behavior among segmental groups, all four groups showed higher order type than unlimited type or buffets type. The limitations of this study are limited to the food field and analysis should be done, but the results of the study on specific food items have not been obtained. Therefore, it is hoped that the future research will be conducted by designating specific food fields.

  • https://doi.org/10.14400/JDC.2022.20.4.159 인용 PDF KSCI