Two discriminative methods for solving tone problems in Mandarin speech recognition are presented. First, discriminative training on the HMM （hidden Markov model） based tone models is proposed. Then an integration t...Two discriminative methods for solving tone problems in Mandarin speech recognition are presented. First, discriminative training on the HMM （hidden Markov model） based tone models is proposed. Then an integration technique of tone models into a large vocabulary continuous speech recognition system is presented. Discriminative model weight training based on minimum phone error criteria is adopted aiming at optimal integration of the tone models. The extended Baum Welch algorithm is applied to find the model-dependent weights to scale the acoustic scores and tone scores. Experimental results show that tone recognition rates and continuous speech recognition accuracy can be improved by the discriminatively trained tone model. Performance of a large vocabulary continuous Mandarin speech recognition system can be further enhanced by the discriminatively trained weight combinations due to a better interpolation of the given models.展开更多
Automatic speech recognition (ASR) is vital for very low-resource languages for mitigating the extinction trouble. Chaha is one of the low-resource languages, which suffers from the problem of resource insufficiency a...Automatic speech recognition (ASR) is vital for very low-resource languages for mitigating the extinction trouble. Chaha is one of the low-resource languages, which suffers from the problem of resource insufficiency and some of its phonological, morphological, and orthographic features challenge the development and initiatives in the area of ASR. By considering these challenges, this study is the first endeavor, which analyzed the characteristics of the language, prepared speech corpus, and developed different ASR systems. A small 3-hour read speech corpus was prepared and transcribed. Different basic and rounded phone unit-based speech recognizers were explored using multilingual deep neural network (DNN) modeling methods. The experimental results demonstrated that all the basic phone and rounded phone unit-based multilingual models outperformed the corresponding unilingual models with the relative performance improvements of 5.47% to 19.87% and 5.74% to 16.77%, respectively. The rounded phone unit-based multilingual models outperformed the equivalent basic phone unit-based models with relative performance improvements of 0.95% to 4.98%. Overall, we discovered that multilingual DNN modeling methods are profoundly effective to develop Chaha speech recognizers. Both the basic and rounded phone acoustic units are convenient to build Chaha ASR system. However, the rounded phone unit-based models are superior in performance and faster in recognition speed over the corresponding basic phone unit-based models. Hence, the rounded phone units are the most suitable acoustic units to develop Chaha ASR systems.展开更多
The use of hidden conditional random fields （HCRFs） for tone modeling is explored. The tone recognition performance is improved using HCRFs by taking advantage of intra-syllable dynamic, inter-syllable dynamic and d...The use of hidden conditional random fields （HCRFs） for tone modeling is explored. The tone recognition performance is improved using HCRFs by taking advantage of intra-syllable dynamic, inter-syllable dynamic and duration features. When the tone model is integrated into continuous speech recognition, the discriminative model weight training （DMWT） is proposed. Acoustic and tone scores are scaled by model weights discriminatively trained by the minimum phone error （MPE） criterion. Two schemes of weight training are evaluated and a smoothing technique is used to make training robust to overtraining problem. Experiments show that the accuracies of tone recognition and large vocabulary continuous speech recognition （LVCSR） can be improved by the HCRFs based tone model. Compared with the global weight scheme, continuous speech recognition can be improved by the discriminative trained weight combinations.展开更多
文摘Two discriminative methods for solving tone problems in Mandarin speech recognition are presented. First, discriminative training on the HMM （hidden Markov model） based tone models is proposed. Then an integration technique of tone models into a large vocabulary continuous speech recognition system is presented. Discriminative model weight training based on minimum phone error criteria is adopted aiming at optimal integration of the tone models. The extended Baum Welch algorithm is applied to find the model-dependent weights to scale the acoustic scores and tone scores. Experimental results show that tone recognition rates and continuous speech recognition accuracy can be improved by the discriminatively trained tone model. Performance of a large vocabulary continuous Mandarin speech recognition system can be further enhanced by the discriminatively trained weight combinations due to a better interpolation of the given models.
文摘Automatic speech recognition (ASR) is vital for very low-resource languages for mitigating the extinction trouble. Chaha is one of the low-resource languages, which suffers from the problem of resource insufficiency and some of its phonological, morphological, and orthographic features challenge the development and initiatives in the area of ASR. By considering these challenges, this study is the first endeavor, which analyzed the characteristics of the language, prepared speech corpus, and developed different ASR systems. A small 3-hour read speech corpus was prepared and transcribed. Different basic and rounded phone unit-based speech recognizers were explored using multilingual deep neural network (DNN) modeling methods. The experimental results demonstrated that all the basic phone and rounded phone unit-based multilingual models outperformed the corresponding unilingual models with the relative performance improvements of 5.47% to 19.87% and 5.74% to 16.77%, respectively. The rounded phone unit-based multilingual models outperformed the equivalent basic phone unit-based models with relative performance improvements of 0.95% to 4.98%. Overall, we discovered that multilingual DNN modeling methods are profoundly effective to develop Chaha speech recognizers. Both the basic and rounded phone acoustic units are convenient to build Chaha ASR system. However, the rounded phone unit-based models are superior in performance and faster in recognition speed over the corresponding basic phone unit-based models. Hence, the rounded phone units are the most suitable acoustic units to develop Chaha ASR systems.
文摘The use of hidden conditional random fields （HCRFs） for tone modeling is explored. The tone recognition performance is improved using HCRFs by taking advantage of intra-syllable dynamic, inter-syllable dynamic and duration features. When the tone model is integrated into continuous speech recognition, the discriminative model weight training （DMWT） is proposed. Acoustic and tone scores are scaled by model weights discriminatively trained by the minimum phone error （MPE） criterion. Two schemes of weight training are evaluated and a smoothing technique is used to make training robust to overtraining problem. Experiments show that the accuracies of tone recognition and large vocabulary continuous speech recognition （LVCSR） can be improved by the HCRFs based tone model. Compared with the global weight scheme, continuous speech recognition can be improved by the discriminative trained weight combinations.
