KT-STS: a speech translation system for hotel reservation and a continuous speech recognition system for speech translation

In this paper, we present KT-STS(Korea Telecom Speech Translation System) and a continuous speech recognition system for speech translation. KT-STS is an experimental speech-to-speech translation system which translates a spoken utterance in Korean into one in Japanese. The system has been designed around the task of hotel reservation (dialogues between a Korean customer and a hotel reservation desk in Japan). It consists of Korean speech recognition , Korean-to-Japanese machine translation and Korean speech synthesis. The Korean speech recognition system is an HMM(hidden Markov model)-based speaker-independent, continuous speech rec-ognizer which can recognize about 300 word vocabularies. We have achieved the word recognition rate of 94.5% and the sentence recognition rate of 81.2%. For machine tranlation, we use dependency grammar and direct transfer method. And Korean speech synthesis is also implemented. KT-STS runs in nearly real time on the SPARC20 workstation with one TMS320C30 DSP board. We had an international joint experiment in which our system was connected with another system developed by KDD in Japan using the leased line.