The Speech Processing Laboratory at National Taiwan University was founded by Lin-shan Lee in 1981, and has been under his direction since then. The work started with low bit rate speech coding and speech scrambling, and focused on Chinese spoken language processing considering structural features of Chinese language since 1983. The research areas in the latter include: Chinese text-to-speech synthesis, Mandarin speech recognition and dictation systems, Chinese language processing, Mandarin speech understanding, dialogue systems and speech-based information retrieval. The representative prototype systems developed at the laboratory are named "Golden Mandarin series". Starting 1997 there have been more works on subjects equally applicable to all languages rather than specially for Mandarin Chinese..
<![if !supportEmptyParas]> <![endif]>
The research work of the laboratory in recent years is summarized below:
<![if !supportLists]> 1. <![endif]> Acoustic Recognition: tone modeling and recognition, unit selection and acoustic modeling, keyword spotting, handling noise and channel effect, speaker adaptation, speaker verification, etc.
<![if !supportLists]> 2. <![endif]> Linguistic Processing: language modeling, Chinese word classification, analysis with respect to different subject domains, model adaptation, semantic analysis and language understanding, PAT-tree-based approaches, segment pattern and key phrase extraction, document classification, etc.
<![if !supportLists]> 3. <![endif]> Integrated Acoustic/Linguistic Processing: pronunciation modeling and lexicon adaptation, spontaneous and telephone speech processing, syllable-based one-pass search, prosody modeling, speech understanding, dialogue modeling and analysis, speech-based retrieval models and features, etc.
<![if !supportLists]> 4. <![endif]> Academic Prototype Systems: dictation systems, text-to-speech systems, dialogue systems, speech-based information retrieval systems, etc.
<![if !supportLists]> 5. <![endif]> Directions towards Network Environment: client-server architecture, speech human-network interface, network resource adapted lexicon and language model, network corpora processing, distributed speech processing under wireless environment, etc.
The work of the laboratory is primarily performed by graduate students in Electrical Engineering, Computer Science and Communications Engineering at National Taiwan University. More than 80 Master and Ph.D. theses have been produced. Close collaboration or even join work has been developed with the Chinese Natural Language Processing Laboratory and Knowledge and Information Retrieval Laboratory of Institute of Information Science, Academia Sinica and the Speech and Phonetics Laboratory of Institute of Linguistics, Academia Sinica. The work of the laboratory has been sponsored by both government organizations and industry. Currently the two major government projects are "Chinese Spoken Language Processing under Wireless Environment" and "Wireless Multi-media over IP: Technologies and Applications", both started in year 2000.