ABSTRACT
See abstract in his paper
ABSTRACT
See abstract in his paper
ABSTRACT
In this paper, we study discriminant function based minimum recognition error rate pattern recognition approach. This ap-proach departs from the conventional paradigm which links a classification/recognition task to the problem of distribution esti-mation. Instead, it takes a discriminant function based statistical pattern recognition approach and the goodness of this approach to classification error rate minimization is established through a special loss function. It is meaningful even when the model correctness assumption is known not valid. The use of discrimi-nant function has a significant impact on classifier design, since in many realistic applications, such as speech recognition, the true distribution form of the source is rarely known precisely and without model correctness assumption, the classical optimality theory of the distribution estimation approach can not be applied directly. We discuss issues in this new classifier design paradigm and present various extensions of this approach for applications in speech processing.
ABSTRACT
See abstract in his paper
ABSTRACT
This talk gives an introduction to a recurrent
neural network (RNN) based prosody synthesis method for both Mandarin and Min-Nan
text-to-speech (TTS) conversions. The method uses a four-layer RNN to model
the dependency of output prosodic information and input linguistic information.
Main advantages of the method are the capability of learning many human’s
prosody pronunciation rules automatically and the relatively short time of system
development. Two variations of the baseline RNN prosody synthesis method are
also discussed. One uses an additional fuzzy-neural network to infer some fuzzy
rules of affections from high-level linguistic features for assisting in the
RNN prosody generation. The other uses additional statistical models of prosodic
parameter to remove some affecting factors of linguistic features for reducing
the load of the RNN.
ABSTRACT
See abstract in his paper