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
This paper presents a method of tone recognition for Mandarin speech by using combination of wavelet transform and hidden Markov modeling techniques. A pitch detector based on singularity detection and multi-resolutio...This paper presents a method of tone recognition for Mandarin speech by using combination of wavelet transform and hidden Markov modeling techniques. A pitch detector based on singularity detection and multi-resolution analysis of wavelet transform is employed for estimation of pitch periods, and hidden Markov modeling with partition Gaussian mixtures probability density function is used for the tone recognition. The algorithm can provide recognition accuracy of 97.22% and 94.47% for speaker-dependent and speaker-independent tone recognition, respectively.展开更多
In 1981 Taiwan entered a period of intense construction, meaning that today many buildings are more than 30 years old. Lack of maintenance has led to frequent safety incidents involving external walls. This study focu...In 1981 Taiwan entered a period of intense construction, meaning that today many buildings are more than 30 years old. Lack of maintenance has led to frequent safety incidents involving external walls. This study focuses on a deterioration diagnostic model for external wall tiles of aged buildings, using both stage 1 and stage 2 diagnostic methods. The visual test results are categorized based on impact on public safety, and renovation strategies are proposed. Stage 1 diagnosis mainly adopted the DER visual inspection deterioration assessment method. For enhance the accuracy, this research adopted the Infrared Thermal Imaging detection method to double confirm the visual inspection results. After producing an external wall tile Condition Indicator (CI). For stage 1 diagnostic results that fall in a gray area, stage 2 diagnosis was carried out using a tap tone test, followed by fast Fourier transform and pattern recognition to analyze the tapping results. Finally, the study provides a deterioration evaluation criteria for external wall tiles replacement recommendations and a standard operating procedure for deterioration diagnosis. The study also recommends directions for future amendment of regulations, and provides a basis of reference for the government in determining urban renewal, renovation and maintenance strategies.展开更多
In this paper, we propose a method for characterizing a musical signal by extracting a set of harmonic descriptors reflecting the maximum information contained in this signal. We focus our study on a signal of orienta...In this paper, we propose a method for characterizing a musical signal by extracting a set of harmonic descriptors reflecting the maximum information contained in this signal. We focus our study on a signal of oriental music characterized by its richness in tone that can be extended to 1/4 tone, taking into account the frequency and time characteristics of this type of music. To do so, the original signal is slotted and analyzed on a window of short duration. This signal is viewed as the result of a combined modulation of amplitude and frequency. For this result, we apply short-term the non-stationary sinusoidal modeling technique. In each segment, the signal is represented by a set of sinusoids characterized by their intrinsic parameters: amplitudes, frequencies and phases. The modeling approach adopted is closely related to the slot window;therefore great importance is devoted to the study and the choice of the kind of the window and its width. It must be of variable length in order to get better results in the practical implementation of our method. For this purpose, evaluation tests were carried out by synthesizing the signal from the estimated parameters. Interesting results have been identified concerning the comparison of the synthesized signal with the original signal.展开更多
A method for online dispersion monitoring by adding a single in-band subcarrier tone isintroduced.According to the theoretical analysis,the dispersion monitor and measurement range aredetermined by the specific freque...A method for online dispersion monitoring by adding a single in-band subcarrier tone isintroduced.According to the theoretical analysis,the dispersion monitor and measurement range aredetermined by the specific frequency of the subcarrier tone.By using simulation tools,figures aboutrelationship between power of subcarrier tone and transmission distance in ideal condition are shown.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.
基金Supported by the National Natural Science Foundatiuon of China
文摘This paper presents a method of tone recognition for Mandarin speech by using combination of wavelet transform and hidden Markov modeling techniques. A pitch detector based on singularity detection and multi-resolution analysis of wavelet transform is employed for estimation of pitch periods, and hidden Markov modeling with partition Gaussian mixtures probability density function is used for the tone recognition. The algorithm can provide recognition accuracy of 97.22% and 94.47% for speaker-dependent and speaker-independent tone recognition, respectively.
文摘In 1981 Taiwan entered a period of intense construction, meaning that today many buildings are more than 30 years old. Lack of maintenance has led to frequent safety incidents involving external walls. This study focuses on a deterioration diagnostic model for external wall tiles of aged buildings, using both stage 1 and stage 2 diagnostic methods. The visual test results are categorized based on impact on public safety, and renovation strategies are proposed. Stage 1 diagnosis mainly adopted the DER visual inspection deterioration assessment method. For enhance the accuracy, this research adopted the Infrared Thermal Imaging detection method to double confirm the visual inspection results. After producing an external wall tile Condition Indicator (CI). For stage 1 diagnostic results that fall in a gray area, stage 2 diagnosis was carried out using a tap tone test, followed by fast Fourier transform and pattern recognition to analyze the tapping results. Finally, the study provides a deterioration evaluation criteria for external wall tiles replacement recommendations and a standard operating procedure for deterioration diagnosis. The study also recommends directions for future amendment of regulations, and provides a basis of reference for the government in determining urban renewal, renovation and maintenance strategies.
文摘In this paper, we propose a method for characterizing a musical signal by extracting a set of harmonic descriptors reflecting the maximum information contained in this signal. We focus our study on a signal of oriental music characterized by its richness in tone that can be extended to 1/4 tone, taking into account the frequency and time characteristics of this type of music. To do so, the original signal is slotted and analyzed on a window of short duration. This signal is viewed as the result of a combined modulation of amplitude and frequency. For this result, we apply short-term the non-stationary sinusoidal modeling technique. In each segment, the signal is represented by a set of sinusoids characterized by their intrinsic parameters: amplitudes, frequencies and phases. The modeling approach adopted is closely related to the slot window;therefore great importance is devoted to the study and the choice of the kind of the window and its width. It must be of variable length in order to get better results in the practical implementation of our method. For this purpose, evaluation tests were carried out by synthesizing the signal from the estimated parameters. Interesting results have been identified concerning the comparison of the synthesized signal with the original signal.
文摘A method for online dispersion monitoring by adding a single in-band subcarrier tone isintroduced.According to the theoretical analysis,the dispersion monitor and measurement range aredetermined by the specific frequency of the subcarrier tone.By using simulation tools,figures aboutrelationship between power of subcarrier tone and transmission distance in ideal condition are shown.
