Using explicit segmentation to improve HMM phone recognition
نویسندگان
چکیده
We show that many of the errors in a context-dependent phone recognition system are due to poor segmentation. We then suggest a method to incorporate explicit segmentation information directly into the HMM paradigm. The utility of explicit segmentation information is illustrated with experiments involving ve types of segmentation information and three methods of smoothing.
منابع مشابه
Using multi-level segmentation coefficients to improve HMM speech recognition
This paper presents a new kind of acoustic features for HMM speech recognition. These features try to capture phone{ specic segmentation information using multiple temporal resolutions. Experiments show that word accuracy can be improved by 7% when combining these features with traditional mel{cepstral coecients in a speaker{independent word recogniser. This improvement is mostly due to a reduc...
متن کاملA study of HMM-based automatic segmentations for Thai continuous speech recognition system
Speech segmentations have been widely using in many speech applications. In speech synthesis, the quality of produced speech depends on the accuracy of labeled acoustic inventory. In speech recognition, segmented utterances according to the labels are usually used as a starting point for training speech models. The segmentation is often manually encoded which is timeconsumption process and has ...
متن کاملAutomatic Speech Segmentation with Hmm
ABSTRACT: In this paper we review aspects of our automatic speech segmentation system that has been utilised in conjunction with our speech synthesis research. The speech segmentation system is based on a hidden Markov model phone recogniser using training strategies optimised for the segmentation task. Our research includes an analysis of the various aspects of the phone recogniser’s design an...
متن کاملHybrid CNN-HMM Model for Street View House Number Recognition
We present an integrated model for using deep neural networks to solve street view number recognition problem. We didn’t follow the traditional way of first doing segmentation then perform recognition on isolated digits, but formulate the problem as a sequence recognition problem under probabilistic treatment. Our model leverage a deep Convolutional Neural Network(CNN) to represent the highly v...
متن کاملAutomatic phonetic segmentation using boundary models
This study attempts to improve automatic phonetic segmentation within the HMM framework. Experiments were conducted to investigate the use of phone boundary models, the use of precise phonetic segmentation for training HMMs, and the difference between context-dependent and contextindependent phone models in terms of forced alignment performance. Results show that the combination of special one-...
متن کامل