• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.44 no.1
• /
• pp.26-32
• /
• 2007

In sequential speaker classification, the lack of prior information about the speakers poses a challenge for model initialization. To address the challenge, a predetermined generic model set, called Sample Speaker Models, was previously proposed. This approach can be useful for accurate speaker modeling without requiring initial speaker data. However, an optimal method for sampling the models from a generic model pool is still required. To solve this problem, the Speaker Quantization method, motivated by vector quantization, is proposed. Experimental results showed that the new approach outperformed the random sampling approach with 25% relative improvement in error rate on switchboard telephone conversations.

• Annual Conference on Human and Language Technology
• /
• 1989.10a
• /
• pp.154-158
• /
• 1989

본 연구는 통제적 모델에 의한 연속 숫자음의 인식에 관한 것으로 4 연속 숫자음을 인식 대상으로하여 실험한다. 시스템은 크게 음향 음성 처리부 및 어휘 해석부 두 부분으로 나뉜다. 음향 음성 처리부에서는 입력 음성으로부터 특정 벡터인 12차의 LPC cepstrum 계수를 구하여, 프레임 레이블링과 소음소 레이블링 (phone labelling)을 한다. 프레임 레이블링인 베이스 분류법을 이용하였으며, 소음소 레이블링은 프레임 레이블과 사후확률 (posteriori probability)로 부터 이루어 졌다. 어휘 해석부분에서는 소음소 단위를 입력으로 받아 음운규칙을 통해 작성된 소음소 망을 거쳐 연속 숫자음 출력을 얻도록 했다. 본실험은 화자 3 명이 발음한 35 개의 4 연속 숫자음을 인식 대상으로 하였으며, 4 연속 숫자음을 평가단위로 80%의 인식율을 얻었고, 각 숫자음의 음절을 단위로 95%의 인식율을 얻어 제시한 알고리즘의 유효성을 입증하였다.

• The Journal of the Acoustical Society of Korea
• /
• v.13 no.1
• /
• pp.5-13
• /
• 1994

This paper presents a study on Neural Networks for Phoneme Recognition and performs the Phoneme Recognition using TDNN (Time Delay Neural Network). Also, this paper proposes training algorithm for speech recognition using neural nets that is a proper to large scale TDNN. Because Phoneme Recognition is indispensable for continuous speech recognition, this paper uses TDNN to get accurate recognition result of phonemes. And this paper proposes new training algorithm that can converge TDNN to an optimal state regardless of the number of phonemes to be recognized. The recognition experiment was performed with new training algorithm for TDNN that combines backpropagation and Cauchy algorithm using stochastic approach. The results of the recognition experiment for three phoneme classes for two speakers show the recognition rates of $98.1\%$. And this paper yielded that the proposed algorithm is an efficient method for higher performance recognition and more reduced convergence time than TDNN.