After pointed the unreasonableness of the three basic assumptions contained in HMM, we introduce the theory and the advantage of Stochastic najectory Models (STMs) that possibly resolve these problems caused by HMM as...After pointed the unreasonableness of the three basic assumptions contained in HMM, we introduce the theory and the advantage of Stochastic najectory Models (STMs) that possibly resolve these problems caused by HMM assumptions. In STM, the acoustic observations of an acoustic unit are represented as clusters of trajectories in a parameter space.The trajectories are modelled by mixture of probability density functions of random sequence of states. After analyzing the characteristics of Chinese speech, the acoustic units for continuous Chinese speech recognition based on STM are discussed and phone-like units are suggested. The performance of continuous Chinese speech recognition based on STM is studied on VINICS system. The experimental results prove the efficiency of STM and the consistency of phone-like units.展开更多
As a sort of cognitive means and thinking mode,conceptual metaphor is widely applied to political discourses.Statesmen often publicize their political thoughts by using conceptual metaphors in their political discours...As a sort of cognitive means and thinking mode,conceptual metaphor is widely applied to political discourses.Statesmen often publicize their political thoughts by using conceptual metaphors in their political discourses so that the audience can understand their political ideas easily.Based on the Conceptual Metaphor Theory,this paper aims to analyze the conceptual metaphors in Xi Jinping's 2016 New Year address so as to summarize the types,functions and significance of conceptual metaphors in Chinese political discourses,in the hope of helping readers interpret political speeches better.展开更多
Through carefully studying the theory of speech acts and the literature concerning it,the author made some new findings which reflects in three aspects:the similarities and differences in Chinese and English in expres...Through carefully studying the theory of speech acts and the literature concerning it,the author made some new findings which reflects in three aspects:the similarities and differences in Chinese and English in expressing the same speech act,the relations between different types of speech acts and the correspondence between sentence sets and sets of speech acts.展开更多
National assessment of speech synthesis systems for Chinese has been regularly carried out since 1994 in China. New guidelines to the assessment activities which aim at promoting the assessment work to be standardizab...National assessment of speech synthesis systems for Chinese has been regularly carried out since 1994 in China. New guidelines to the assessment activities which aim at promoting the assessment work to be standardizable, automatizable (partially) and accessible to the public by computer network were set up in 1997. Two modules. the phonetic module and the linguistic module, are evaluated individually. The phonetic module is evaluated by using speech intelligibility tests at three levels:syllable, word and sentence, and speech natu-ralness tests (in MOS). As for the linguistic module, the text processing ability, which includes word segmentation, polyphonic characters, numerals, years, symbols and metrological units, is examined automatically.展开更多
Nonlinear dynamic method is used in studying Chinese spoken in normal speed, and the improved correlation dimension algorithm are made for the characterization of speech signal. The reconstructed phase space and corre...Nonlinear dynamic method is used in studying Chinese spoken in normal speed, and the improved correlation dimension algorithm are made for the characterization of speech signal. The reconstructed phase space and correlation dimension curves of unvoiced fricative consonants and vowels are also given. It is found that the correlation dimension algorithm can distinguish fricative from vowel because of the different mechanism between them. And the study shows that it can provide information for distinguishing four basic tones in mandarin.展开更多
A national assessment of the performance of speech synthesis systems for Chinese has been carried out yearly since 1994. The quality of synthetic speech of five different systems were evaluated and diagnosed by using ...A national assessment of the performance of speech synthesis systems for Chinese has been carried out yearly since 1994. The quality of synthetic speech of five different systems were evaluated and diagnosed by using speech intelligibility tests. 16 college students (8 male, 8 female) with no experience with synthetic speech were the listeners, they were asked to do open response task by pencilpaper. In addition, speech naturalness was mea-sured by Mean展开更多
Well developed continuous speech recognition and synthesis systems demand a high quality continuous speech database which is compact and valid, and whose scientific design would benefit from incorporating linguistic a...Well developed continuous speech recognition and synthesis systems demand a high quality continuous speech database which is compact and valid, and whose scientific design would benefit from incorporating linguistic and phonetic knowledge. It is argued that at the present stage the database should be limited to read speech. To describe those very complex variabilities in continuous speech, the following speech units are proposed: (1) 401syllables without tone; (2) 415 inter-syllabic diphones, (3) 3035 inter-syllabic triphones, (4) 781 inter-syllabic final-initial structures. The 17 basic sefltence patterns in standard Chinese are summarized to cover the most important prosodic phenomena. By using the automatic method,2393 sentences and 388 phrases are selected by above phonetic rules from a large corpus, which includes People’s Daily in recent years, TV play scripts and dictionary entries, as the reading text of continuous speech recognition database in standard Chinese. This set of sentences and pbrases covers 99.8% syllables without counting tones, 100% inter-syllable diphones, 99.6% inter-syllable triphones and 100% sentence patterns.展开更多
文摘After pointed the unreasonableness of the three basic assumptions contained in HMM, we introduce the theory and the advantage of Stochastic najectory Models (STMs) that possibly resolve these problems caused by HMM assumptions. In STM, the acoustic observations of an acoustic unit are represented as clusters of trajectories in a parameter space.The trajectories are modelled by mixture of probability density functions of random sequence of states. After analyzing the characteristics of Chinese speech, the acoustic units for continuous Chinese speech recognition based on STM are discussed and phone-like units are suggested. The performance of continuous Chinese speech recognition based on STM is studied on VINICS system. The experimental results prove the efficiency of STM and the consistency of phone-like units.
文摘As a sort of cognitive means and thinking mode,conceptual metaphor is widely applied to political discourses.Statesmen often publicize their political thoughts by using conceptual metaphors in their political discourses so that the audience can understand their political ideas easily.Based on the Conceptual Metaphor Theory,this paper aims to analyze the conceptual metaphors in Xi Jinping's 2016 New Year address so as to summarize the types,functions and significance of conceptual metaphors in Chinese political discourses,in the hope of helping readers interpret political speeches better.
文摘Through carefully studying the theory of speech acts and the literature concerning it,the author made some new findings which reflects in three aspects:the similarities and differences in Chinese and English in expressing the same speech act,the relations between different types of speech acts and the correspondence between sentence sets and sets of speech acts.
文摘National assessment of speech synthesis systems for Chinese has been regularly carried out since 1994 in China. New guidelines to the assessment activities which aim at promoting the assessment work to be standardizable, automatizable (partially) and accessible to the public by computer network were set up in 1997. Two modules. the phonetic module and the linguistic module, are evaluated individually. The phonetic module is evaluated by using speech intelligibility tests at three levels:syllable, word and sentence, and speech natu-ralness tests (in MOS). As for the linguistic module, the text processing ability, which includes word segmentation, polyphonic characters, numerals, years, symbols and metrological units, is examined automatically.
基金National Natural Science Foundation of China!(No. 19834040).
文摘Nonlinear dynamic method is used in studying Chinese spoken in normal speed, and the improved correlation dimension algorithm are made for the characterization of speech signal. The reconstructed phase space and correlation dimension curves of unvoiced fricative consonants and vowels are also given. It is found that the correlation dimension algorithm can distinguish fricative from vowel because of the different mechanism between them. And the study shows that it can provide information for distinguishing four basic tones in mandarin.
文摘A national assessment of the performance of speech synthesis systems for Chinese has been carried out yearly since 1994. The quality of synthetic speech of five different systems were evaluated and diagnosed by using speech intelligibility tests. 16 college students (8 male, 8 female) with no experience with synthetic speech were the listeners, they were asked to do open response task by pencilpaper. In addition, speech naturalness was mea-sured by Mean
文摘Well developed continuous speech recognition and synthesis systems demand a high quality continuous speech database which is compact and valid, and whose scientific design would benefit from incorporating linguistic and phonetic knowledge. It is argued that at the present stage the database should be limited to read speech. To describe those very complex variabilities in continuous speech, the following speech units are proposed: (1) 401syllables without tone; (2) 415 inter-syllabic diphones, (3) 3035 inter-syllabic triphones, (4) 781 inter-syllabic final-initial structures. The 17 basic sefltence patterns in standard Chinese are summarized to cover the most important prosodic phenomena. By using the automatic method,2393 sentences and 388 phrases are selected by above phonetic rules from a large corpus, which includes People’s Daily in recent years, TV play scripts and dictionary entries, as the reading text of continuous speech recognition database in standard Chinese. This set of sentences and pbrases covers 99.8% syllables without counting tones, 100% inter-syllable diphones, 99.6% inter-syllable triphones and 100% sentence patterns.