Learn More
—A digital signal processing technique for compensating both the I/Q mismatch and the DC offset in communication receivers is derived with an emphasis on direct-conversion ar-chitectures. The I/Q mismatch and DC offset are estimated in a least-squares sense using a training sequence. Also, a group of training sequences that minimizes the mean square error(More)
—This paper proposes a technique that jointly estimates the I/Q mismatch, dc offset, carrier frequency offset, and channel for receivers in frequency selective channels. The joint estimator is a data-aided technique that requires a training sequence and is derived based on the maximum likelihood (ML) criterion. The characteristics of the joint estimator are(More)
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(More)
In this paper, we present a large vocabulary , speaker independent speech recognition sys-tem(KT-STOCK) and describe its performance over the telephone network. KT-STOCK is a stock information retrieval system with which we can obtain the current price of a stock by saying a stock name among 710 stock names listed on the Korea stock exchange. The system is(More)
  • 1