Using GMM for voiced/voiceless segmentation and tone decision in Mandarin continuous speech recognition
نویسنده
چکیده
In this paper, methods of Gaussian Mixture Model (GMM) are presented for both silence/voiced/voiceless segmentation and tone decision in Mandarin continuous speech recognition system. GMM has been used for silence/voiced/voiceless segmentation before, but the feature parameters can be modified to improve both accuracy and speed. As a popular method in pattern recognition, GMM is first proposed for tone decision. The two GMMs used are proved to be capable and potential.
منابع مشابه
A New Algorithm for Noisy Speech Classification Based on GMM
Speech can be broadly categorized into voiceless, voiced, and mute signal, in which voiced speech can be further classified into vowel and voiced consonant. With the ever increasing demand of the speech synthesis applications, it is urgent to develop an effective classification method to differentiate vowel and voiced consonant signal since they are two distinct components that affect the natur...
متن کاملThe variations of Mandarin unaspirated
The variations of unaspirated stops /p/, /t/, /k/ were investigated in spontaneous speech with the aim of (1) describing the variations and (2) interpreting the variation for acoustic data in terms of articulation and environment. In this report, 56 sentences were selected through the read speech corpus. The variations of unaspirated stops were analysized and perception experiment was done. The...
متن کاملDecision tree based Mandarin tone model and its application to speech recognition
Tone is an essential language phenomenon for Mandarin Chinese language. Until now, we still do not know exactly how context affects tone pattern variation in continuous Mandarin speech. In this paper, we proposed a decision tree based approach to obtain the quantitative result of tone pattern variation in continuous Mandarin speech. Many possible factors other than tone of neighboring syllables...
متن کاملImproved Mandarin Speech Recognition by Lattice Rescoring with Enhanced Tone Models
Tone plays an important lexical role in spoken tonal languages like Mandarin Chinese. In this paper we propose a two-pass search strategy for improving tonal syllable recognition performance. In the first pass, instantaneous F0 information is employed along with corresponding cepstral information in a 2-stream HMM based decoding. The F0 stream, which incorporates both discrete voiced/unvoiced i...
متن کاملRobust F0 modeling for Mandarin speech recognition in noise
The F0 contour plays an important role in recognizing spoken tonal languages like Mandarin Chinese. However, the discontinuity of F0 between voiced and unvoiced transition has traditionally been a bottleneck in creating a succinct statistical tone model for automatic speech recognition applications. By applying successfully the Multi-Space Distribution (MSD) to tone modeling, we recently report...
متن کامل