[an error occurred while processing this directive] [an error occurred while processing this directive]
Yang Zhang

Speech Processing and Modeling Based on the Source-filter Model

Yang Zhang, 4/1/2014, 4:30-5:30pm, BI 2369

Current model-based speech analysis tends to be incomplete - only a subset of the parameters of interest (e.g., only the pitch or vocal tract) are modeled, while the rest are disregarded. The drawback is that without joint modeling of parameters that are correlated, the analysis of speech parameters may be inaccurate or even incorrect. Under this motivation, we have proposed a model called PAT (Probabilistic Acoustic Tube), where pitch, vocal tract and energy are jointly modeled. This paper proposes an improved version of PAT model, named PAT2, where both signal and probabilistic modeling are tremendously renovated. Experimental results show its ability in decomposing speech into desirable parameters and its potential for speech synthesis.

[an error occurred while processing this directive]