发明名称 SPEECH SYNTHESIZER, SPEECH SYNTHESIS METHOD, AND SPEECH SYNTHESIS PROGRAM
摘要 PROBLEM TO BE SOLVED: To provide a speech synthesizer, a speech synthesis method and a speech synthesis program that can attain high resolution while suppressing an increase in processing amount.SOLUTION: A speech synthesizer 200 which synthesizes a speech waveform on the basis of input time-series sound source control information and spectrum characteristic information includes: a sine wave synthesis part 232 which synthesizes an amplitude-adjusted sine wave so as to simulate spectrum characteristics of an output target speech; a sub-band division waveform vector generation part 236 which generates one sub-band division waveform vector by combining together a sub-band division sound source waveform vector having its amplitude adjusted in a specific sub-band and a sine wave synthetic component having the sine wave synthesized; and a sub-band synthesis part 140 which synthesize the generated sub-band division waveform vector and the amplitude-adjusted sub-band division sound source waveform vector each into a single speech waveform.
申请公布号 JP2014109667(A) 申请公布日期 2014.06.12
申请号 JP20120263574 申请日期 2012.11.30
申请人 KDDI CORP 发明人 NISHIZAWA NOBUYUKI
分类号 G10L19/06;G10L19/02;G10L19/10 主分类号 G10L19/06
代理机构 代理人
主权项
地址