Using a Pitch-Synchronous Residual Codebook for Hybrid HMM/Frame Selection Speech Synthesis
This work addresses speech synthesis quality for applications like text-to-speech systems, but it is incremental as it builds on existing HMM/frame selection methods.
The paper tackled the problem of low-quality synthetic speech from statistical parametric synthesizers by constructing a more realistic source signal using a pitch-synchronous residual codebook, resulting in a relevant improvement in subjective quality compared to the basic technique.
This paper proposes a method to improve the quality delivered by statistical parametric speech synthesizers. For this, we use a codebook of pitch-synchronous residual frames, so as to construct a more realistic source signal. First a limited codebook of typical excitations is built from some training database. During the synthesis part, HMMs are used to generate filter and source coefficients. The latter coefficients contain both the pitch and a compact representation of target residual frames. The source signal is obtained by concatenating excitation frames picked up from the codebook, based on a selection criterion and taking target residual coefficients as input. Subjective results show a relevant improvement compared to the basic technique.