Experimental Georgian Speech Synthesizer Part 1 Structure of Synthesizer
Experimental Georgian Speech Synthesizer Part 1 Structure of Synthesizer
摘要
The term ＂Experimental＂ in the title means, that the synthesizer is constructed as tool to conduct experiments, for investigating the influence of environment of unit on sounding of it. Synthesizer as tool for testing of hypotheses and results of experiments, satisfy three conditions： independence from the selection of unit for the synthesis （word or any part of it）; taking into account the environment of unit （left and right hand contexts and position of unit）; independence from the content of base. Such synthesizer is a good tool for studying many aspects of speech and removes the problem of selection. We can vary the unit and other parameters, described in paper, by the same synthesizer, synthesize the same text and listen to the results directly. This paper describes the formal structure of experimental Georgian speech synthesizer.
参考文献20
-
1G. Chichua, K. Pkhakadze, Geotextreader System, Center for Georgian Language Technologies, Georgian Technical University [Online], 2013, http://voice.dmind.net/, www.zeotextrader.com.
-
2S. J. Young, G. Evermann, M. Gales, T. Hain, D. Kershaw, X. Liu, et al., The HTK Book. For HTK version, 2006, p. 359.
-
3T. Masuko, HMM-based speech synthesis and its application, Ph.D. Thesis, Tokyo Institute of Technology, 2002.
-
4K. Tokuda, T. Yoshimura, T. Masuko, T. Kobayashi, T. Kitamura, Speech parameter generation algorithms for HMM-based speech synthesis, in: Proc. oflCASSP, 2000, pp. 1315-1318.
-
5A. P. Breen, P. Jackson, Non-uniform unit section and the similarity metric within bt's laureate tts system, in: Proceedings of the Third International Workshop on Speech Synthesis, Jenolan Caves, 1998.
-
6J. H. Page, A. P. Breen, The laureate text to speech system-architecture and applications, in Speech Technology for Telecommunications, Chapman and Hall, 1998.
-
7A. W. Black, P. Taylor, Automatically clustering similar units for unit selection in speech synthesis, Centre for Speech Technology Research, University of Edinburgh, 1997.
-
8A. J. Hant, A. W. Black, Unit selection in a concatenative speech synthesis system using a large speech database, in: Proceedings of the International Conference on Speech and Language Processing, 1996, pp. 373-376.
-
9A. W. Black, P. A. Tailor, A framework for generating prosody high level linguistics descriptions, in: Spring Meeting, Acoustical Society of Japan, 1994.
-
10N. lwahashi, N. Kaiki, Y. Sagisaka, A speech segment selection for concatenative synthesis based on spectral distortion minimization, Transactions of Institute of Electronics, Information and Communication Engineers, 76 (1993) 1942-1948.
-
1陈普锋,张海英,叶甜春.A 1.5 V 7.656 GHz PLL with I/Q outputs for a UWB synthesizer[J].Journal of Semiconductors,2010,31(6):78-82.
-
2田良.直接数字合成器专用集成电路的性能及应用[J].国外电子测量技术,1996,15(5):14-17. 被引量：2
-
3中兴信息[J].邮电设计技术,2007(6):28-28.
-
4王献甫.海外同行[J].空中交通管理,2009(1):64-64.
-
5Mobile Communications Division TeleInfo Institute CATR of MII.全球3G纵览(月报)[J].世界电信,2005,18(7):56-57.
-
6会议与展览会[J].机械制造文摘（焊接分册）,2001,0(4):2-3.
-
7李玉.格鲁吉亚误读美国信号[J].环球财经,2008(9):36-36.
-
8陈普锋,李志强,王小松,张海英,叶甜春.A 6-9 GHz 5-band CMOS synthesizer for MB-OFDM UWB[J].Journal of Semiconductors,2010,31(7):72-78. 被引量：1
-
9市场快讯[J].网络电信,2007,9(5):75-78.
-
10罗阳,郑正奇.5．8GHz频率合成器的设计[J].电子技术（上海）,2008,0(9):10-12.
