IEEE Transactions on Speech and Audio Processing · 2001 · 53 citations · 22 references
Language StudiesLinguisticsComputational LinguisticsNatural Language ProcessingPhoneticsAcoustic PhoneticsProsody ProcessingSpeech AcousticsSpeech SynthesisSpoken CorporaSuprasegmental PhoneticsPitch ModelingProsodic ModelingProsodic RepresentationProsody ModelingSuprasegmental Speech AnalysisText-to-speech Synthesis
The increasing availability of carefully designed and collected speech corpora opens up new possibilities for the statistical estimation of formal multivariate prosodic models. At Apple Computer, statistical prosodic modeling exploits the Victoria corpus, created to broadly support ongoing speech synthesis research and development. This corpus is composed of five constituent parts, each designed to cover a specific aspect of speech synthesis: polyphones, prosodic contexts, reiterant speech, function word sequences, and continuous speech. This paper focuses on the use of the Victoria corpus in the statistical estimation of duration and pitch models for Apple's next-generation text-to-speech system in Macintosh OS X. Duration modeling relies primarily on the subcorpus of prosodic contexts, which is instrumental to uncover empirical evidence in favor of a piecewise linear transformation in the well-known sums-of-products approach. Pitch modeling relies primarily on the subcorpus of reiterant speech, which makes possible the optimization of superpositional pitch models with more accurate underlying smooth contours. Experimental results illustrate the improved prosodic representation resulting from these new duration and pitch models.
22
The design for the wall street journal-based CSR corpus
Douglas B. Paul, Janet M. Baker · 1992 · 1.1K citations · Full text
TOBI: a standard for labeling English prosody
Kim Silverman, Mary E. Beckman, John F. Pitrelli et al. · 1992 · 1K citations
Physical principles for economies of skilled movements
W. L. Nelson · Biological Cybernetics · 1983 · 985 citations