Generating intonation from a mixed CART-HMM model for speech synthesis
نویسندگان
چکیده
This paper proposes two algorithms for generating intonation from a mixed CART-HMM intonation model for speech synthesis. Based either on a Viterbi search or on the Expectation-Maximization algorithm, the two generation algorithms are analyzed in terms of likelihood and F0 Root Mean Square Error. Listening tests are performed to subjectively evaluate the quality of the generated intonation.
منابع مشابه
Towards intonation control in unit selection speech synthesis
We propose to control intonation in unit selection speech synthesis with a mixed CART-HMM intonation model. The Finite State Machine (FSM) formulation is suited to incorporate the intonation model in the unit selection framework because it allows for combination of models with different unit types and handling competing intonative variants. Subjective experiments have been carried out to compar...
متن کاملVietnamese HMM-based speech synthesis with prosody information
Generating natural-sounding synthetic voice is an aim of all text to speech system. To meet the goal, many prosody features have been used in full-context labels of an HMMbased Vietnamese synthesizer. In the prosody specification, POS and Intonation information are considered not as important as positional information. The paper investigates the impact of POS and Intonation tagging on the natur...
متن کاملIntegration of Intonation in Trainable Speech Synthesis
Current developments in artificial speech synthesis place more emphasis on spectral continuities and diverse prosodic effects. The trainable HMM-based speech synthesis method has generated more continuous spectral structure than unit selection method in recent study, but the pitch contour generated by HMM-based method trends to be over-smoothed and lacks syllable variance in Chinese. In this pa...
متن کاملSimulating Intonation in Regional Varieties of Swedish
Within the research project SIMULEKT (Simulating Intonational Varieties of Swedish), our recent work includes two approaches to simulating intonation in regional varieties of Swedish. The first involves a method for modelling intonation using the SWING (SWedish INtonation Generator) tool, where annotated speech samples are resynthesised with rule-based intonation and audio-visually analysed wit...
متن کاملSynthesising intonational varieties of Swedish
Within the research project SIMULEKT (Simulating Intonational Varieties of Swedish), our recent work includes two approaches to simulating intonation in regional varieties of Swedish. The first involves a method for modeling intonation using the SWING (SWedish INtonation Generator) tool, where annotated speech samples are resynthesised with rule-based intonation and audio-visually analysed with...
متن کامل