Tone Recognition Based on Multi-layer Perceptron with Application for Continuous Mandarin Speech Recognition

Abstract

Some multi-layer perceptron (MLP) based tone recognition schemes for continuous Mandarin speech are discussed in this paper. The basic MLP scheme using both local and contextual features is first employed for tone recognition. The modular MLP scheme is then introduced to increase the discriminability of the basic MLP tone recognizer. Moreover, we also investigate how to incorporate tone recognizer into large vocabulary continuous speech recognition. A two-pass, post-processing scheme is proposed to utilize the recognized tones in rescoring the recognized N-best strings. The effectiveness of these schemes was confirmed by simulations on a mobile ring back tone (RBT) service with automatic speech recognition function. It has been found from the experimental results that weighted tone information can yield 6% relative improvement of the recognition rate.