首页>
外国专利>
Speech synthesis apparatus, speech synthesis method, speech synthesis program, speech synthesis model learning apparatus, speech synthesis model learning method, and speech synthesis model learning program
Speech synthesis apparatus, speech synthesis method, speech synthesis program, speech synthesis model learning apparatus, speech synthesis model learning method, and speech synthesis model learning program
Prevents speech degradation and unnatural phoneme duration. The speech synthesis apparatus according to the embodiment includes a storage unit, a creation unit, a determination unit, a generation unit, and a waveform generation unit. The storage unit stores, as statistical model information, an output distribution of acoustic feature parameters including pitch feature parameters and a duration distribution based on time parameters in each state of a statistical model having a plurality of states. The creation unit creates a statistical model sequence from the context information corresponding to the input text and the statistical model information. The determination unit determines the number of pitch waveforms in each state using the duration information based on the duration distribution of each state of each statistical model in the statistical model sequence and the pitch information based on the output distribution of the pitch feature parameters. The generation unit generates an output distribution sequence of acoustic feature parameters based on the number of pitch waveforms, and generates an acoustic feature parameter based on the output distribution sequence. The waveform generation unit generates a speech waveform from the generated acoustic feature parameter.
展开▼