According to the statistics of Summer Institute of Linguistics, USA, there are about 7,000 languages in the world. Chinese, Hakka and Swedish are all the first 100 most popular languages. Chinese is spoken in Taiwan, Mainland China, Hong Kong and Macau. Hakka is the second popular dialect in Taiwan. The population is only less than that of Taiwanese. The ancestors of Hakka are from the Han people in Honan, China. Hakka culture has been cultivated by enormous migrations since the fourth century, and transformed to represent the tradition. Taiwan and Sweden are developed, free and democratic countries, with similar level of living standard. The ancestors of Sweden are from the Germanic peoples in Northern Europe. Swedish has been also evolved and transformed by massive migrations since the ninth century, sharing the analogous evolution route with Chinese and Hakka. Therefore, it is our objective to establish a trilingual speech recognition system to help verbal communication among languages in the global economic arena. This thesis investigates the design and implementation strategies for a trilingual speech recognition system for Chinese, Hakka and Swedish. Based on their pronunciation rules, the 404 Chinese, 204 Hakka and 369 Swedish common mono-syllables are selected as the major speech training and recognition methodology. A 2,699 two-syllable words database is recorded as the Chinese training corpus. The five rounds with four tones and six rounds with two tones training strategies are used for Hakka and Swedish respectively. Correct rates of 92.29%, 90.70% and 89.09% can be reached for the 82,000 Chinese, 3,900 Hakka and 3,750 Swedish phrase database respectively. Besides, a trilingual language-speech recognition system for 300 common words, composed of 100 words from each language, is developed. A 98.67% correct language-phrase recognition rate can be obtained. The average computation time for each system is within 2 seconds.

In this thesis, both Turkish and Tamil, a language spoken in southern India and Sri Lanka, are studied in addition to Mandarin Chinese. It is hoped that the history, culture, and economy behind each language can be acquainted, tasted and appreciated during the learning process. In the ancient Chinese Han and Tang Dynasties, the ¡§Silk Road¡¨ played the most magnificent role to connect among the Oriental China, the Western Turkey and the Southern India as the international trading corridor. In this modern era, Turkey and India are both the most important cotton exporting countries. Moreover, China, Turkey and India have been showing their potential to the newly emerging markets in the world. Therefore, a trilingual speech recognition system is developed and implemented to help us to learn Chinese, Turkish and Tamil, as well as to enhance our understanding to their history and culture. In this trilingual system, linear predicted cepstral coefficients, Mel-frequency cepstral coefficients, hidden Markov model and phonotactics are used as the two syllable feature models and the recognition model respectively. For the Chinese system, a 2,699 two-syllable words database is used as the training corpus. For the Turkish and Tamil systems, a database of 10 utterances per mono-syllable is established by applying their pronunciation rules. These 10 utterances are collected through reading 5 rounds of the same mono-syllables twice with tone 1 and tone 4. The correct rates of 88.30%, 84.21%, and 88.74% can be reached for the 82,000 Chinese, 30,795 Turkish, and 3,500 Tamil phrase databases respectively. The computation time for each system is within 1.5 seconds. Furthermore, a trilingual language-speech recognition system for 300 common words, composed of 100 words from each language, is developed. A 98% correct language-phrase recognition rate can be reached with the computation time less than 2 seconds.

A speech recognition system for Chinese names based on Karhunen Loeve transform (KLT), MFCC, hidden Markov model (HMM) and Viterbi algorithm is proposed in this thesis. KLT is the optimal transform in minimum mean square error and maximal energy packing sense to reduce data. HMM is a stochastic approach which characterizes many of the variability in speech signal by recording the state transitions. For the speaker-dependent case, the correct identification rate can be achieved 93.97% within 3 seconds in the laboratory environment.

A Mandarin speech recognition system for addresses based on MFCC, hidden Markov model (HMM) and Viterbi algorithm is proposed in this thesis. HMM is a doubly stochastic process describing the ways of pronunciation by recording the state transitions according to the time-varing properties of the speech signal. In order to simplify the system design and reduce the computational cost, the mono-syllable structure information in Mandarin is used by incorporating both mono-syllable recognizor and HMM for our system. For the speaker-dependent case, Mandarin address inputting can be accomplished within 60 seconds and 98% correct identification rate can be achieved in the laboratory environment.

A Mandarin speech recognition system for addresses in Taiwan, based on end-point detection, MFCC and HMM, is proposed and implemented in this thesis. It includes both phrase and monosyllable recognition tasks. For the phrase recognition part, we select the initial candidates before the final recognition stage to tremendously reduce the computational time. On the other side, for the monosyllable recognition part, we further refine the recognition details to improve the correct rate under easily confused circumstances. The final system can achieve 85% correct identification rate, and the address recognition can be completed within 2 seconds in the laboratory environment for speaker-dependent case.

A system of Chinese resume by speech construction is developed by the use of a novel segmentation mechanism and the classical Hidden Markov Model. The recognition system is based on both mono-syllable HMM's and speech-text alignment schemes. Experimental results indicate that the amount of training materials used for feature extraction can be greatly reduced, and the text content of the recorded speech training data can be different from those of the recognition tasks as well. Each phrase in the resume can be identified within one second, that is approximately the same as the graduate did last year. Furthermore, the user interface of the resume system has been redesigned and polished by the GTK toolkit in order to enable event-driven X-window operations.

A design of speech recognition system for Chinese names of historical figures around the world is proposed in this thesis. A speech database of approximately forty-six thousand Chinese names is collected and recorded twice for system evaluation. This system applies Mel-frequency cepstrum coefficients, monosyllable HMM¡¦s and speech-text alignment scheme to accomplish initial candidate selection. A Mandarin pitch identification mechanism is then followed to increase the correct rate and obtain the final answer. The experimental results indicate that a 90% correct identification rate can be achieved, under the condition that the first session recording material is used for training and the second one for testing. For the speaker dependent case, the correct name can be recognized within 1.5 seconds, using a PC with an Intel Celeron 2.4 GHz CPU and RedHat Linux 9.0 Operation System.

Based on Hidden Markov Models (HMM) with One-Stage Dynamic Programming Algorithm, a continuous-speech and speaker-independent Mandarin digit speech recognition system was designed in this work. In order to implement this architecture to fit the performance of hardware, various parameters of speech characteristics were defined to optimize the process. Finally, the ¡§State Duration¡¨ and the ¡§Tone Transition Property Parameter¡¨ were extracted from speech temporal information to improve the recognition rate. Via using the test database, experimental results show that this new ideal of one-stage dynamic programming algorithm , with ¡§state duration¡¨ and ¡§ tone transition property parameter¡¨ , will have 18% recognition rate increase when compare to the conventional one. For speaker-independent and connect-word recognition, this system will achieve recognition rate to 74%. For speaker-independent but isolate-word recognition, it will have recognition rate higher than 96%. Recognition rate of 92% is obtained as this system is applied to the connect-word speaker-dependent recognition.

A Mandarin keyword spotting system based on MFCC, discrete-time HMM and Viterbi algorithm with DTW is proposed in this thesis. Joining with a dialogue system, this keyword spotting platform is further refined to a prototype of natural speech patient registration system of Kaohsiung Veterans General Hospital. After the ID number is asked by the computer-dialogue attendant in the registration process, the user can finish all relevant works in one sentence. Functions of searching clinical doctors, making and canceling registration are all built in this system. In a laboratory environment, the correct rate of this speaker-independent patient registration system can reach 97% and all registration process can be completed within 75 seconds.

The objective of this thesis is to build a phrase recognition system under noisy environment that can be used in real-life. In this system, the noisy speech is first filtered by the enhanced spectral subtraction method to reduce the noise level. Then the MFCC with cepstral mean subtraction is applied to extract the speech features. Finally, hidden Markov model (HMM) is used in the last stage to build the probabilistic model for each phrase. A Mandarin microphone database of 514 company names that are in Taiwan¡¦s stock market is collected. A speaker independent noisy phrase recognition system is then implemented. This system has been tested under various noise environments and different noise strengths.