• Proceedings of the Acoustical Society of Korea Conference
• /
• 1998.08a
• /
• pp.35-38
• /
• 1998

웹 브라우저 상에서 한국어 음성인식을 이용한 정보검색 시스템에 대한 것이다. 이 시스템의 특징은 웹 브라우저 상에서 보여지는 Hypertext Word를 인식할 수 있는 거승로 기존의 웹 브라우저를 마우스 click 대신 음성인식을 이용하여 사용할 수 있다는 것이다. 웹 브라우저를 통해서 보여지는 고정되지 않고 계속 하여 변화하는 인식후보를 인식하기 위해 당 연구실에서 개발한 가변 어휘 인식기를 사용하였다. 시스템은 windows 95/NT 환경에서 개발되었으며, 사용자가 새로운 인터페이스를 배울 필요 없이 바로 사용할 수 있도록 사용자 편의성 부분도 고려하여 개발되었다. 개발된 시스템은 독립 환경, 독립 화자에 대해 실험한 결과 130여개의 단어에 대해 편균 90% 정도의 인식성능을 보인다.

• Journal of KIISE:Software and Applications
• /
• v.36 no.3
• /
• pp.179-186
• /
• 2009

This paper proposes a target speech extraction which restores speech signal of a target speaker form noisy convolutive mixture of speech and an interference source. We assume that the target speaker is known and his/her utterances are available in the training time. Incorporating the additional information extracted from the training utterances into the separation, we combine convolutive blind source separation(CBSS) and non-negative decomposition techniques, e.g., probabilistic latent variable model. The nonnegative decomposition is used to learn a set of bases from the spectrogram of the training utterances, where the bases represent the spectral information corresponding to the target speaker. Based on the learned spectral bases, our method provides two postprocessing steps for CBSS. Channel selection step finds a desirable output channel from CBSS, which dominantly contains the target speech. Reconstruct step recovers the original spectrogram of the target speech from the selected output channel so that the remained interference source and background noise are suppressed. Experimental results show that our method substantially improves the separation results of CBSS and, as a result, successfully recovers the target speech.

• The Journal of the Acoustical Society of Korea
• /
• v.23 no.3
• /
• pp.235-241
• /
• 2004

This paper studied the pattern recognition algorithm and feature parameters for speaker and context independent emotion recognition. In this paper, KNN algorithm was used as the pattern matching technique for comparison, and also VQ and GMM were used for speaker and context independent recognition. The speech parameters used as the feature are pitch. energy, MFCC and their first and second derivatives. Experimental results showed that emotion recognizer using MFCC and its derivatives showed better performance than that using the pitch and energy parameters. For pattern recognition algorithm. GMM-based emotion recognizer was superior to KNN and VQ-based recognizer.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.9C
• /
• pp.884-890
• /
• 2003

In this paper, we studied the speaker adaptation methods that improve the speaker independent recognition system. For the independent speakers, we compared the results between bigram and back-off bigram, MAP and MLLR. Cause back-off bigram applys unigram and back-off weighted value as bigram probability value, it has the effect adding little weighted value to bigram probability value. We did an experiment using total 39-feature vectors as featuring voice parameter with 12-MFCC, log energy and their delta and delta-delta parameter. For this recognition experiment, We constructed a system made by CHMM and tri-phones recognition unit and bigram and back-off bigrams language model.

• The Journal of the Acoustical Society of Korea
• /
• v.23 no.5
• /
• pp.383-389
• /
• 2004

In this paper. we propose the bias compensation methods and the eigenvoice method using the mean of dimensional eigenvoice to improve the performance of rapid speaker adaptation based on eigenvoice under mismatch between training and test environment. Experimental results for vocabulary-independent word recognition task (using PBW 452 DB) show that the proposed methods yield improvements for small adaptation data. We obtained about 22∼30% relative improvement by the bias compensation methods as amount of adaptation data varied from 1 to 50, and obtained 41% relative improvement in error rate by the eigenvoice method using the mean of dimensional eigenvoice with only single adaptation word.

• Journal of KIISE
• /
• v.44 no.12
• /
• pp.1252-1257
• /
• 2017

In dialogues, speakers' intentions can be represented by sets of an emotion, a speech act, and a predicator. Therefore, dialogue systems should capture and process these implied characteristics of utterances. Many previous studies have considered such determination as independent classification problems, but others have showed them to be associated with each other. In this paper, we propose an integrated model that simultaneously determines emotions, speech acts, and predicators using a convolution neural network. The proposed model consists of a particular abstraction layer, mutually independent informations of these characteristics are abstracted. In the shared abstraction layer, combinations of the independent information is abstracted. During training, errors of emotions, errors of speech acts, and errors of predicators are partially back-propagated through the layers. In the experiments, the proposed integrated model showed better performances (2%p in emotion determination, 11%p in speech act determination, and 3%p in predicator determination) than independent determination models.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.2
• /
• pp.137-142
• /
• 2020

Many studies based on I-vector have been conducted in a variety of environments, from text-dependent short-utterance to text-independent long-utterance. In this paper, we propose a speaker verification system employing a combination of I-vector with Probabilistic Linear Discriminant Analysis (PLDA) and speaker embedding of Long Short Term Memory (LSTM) with attention mechanism in far-field and noisy environments. The LSTM model's Equal Error Rate (EER) is 15.52 % and the Attention-LSTM model is 8.46 %, improving by 7.06 %. We show that the proposed method solves the problem of the existing extraction process which defines embedding as a heuristic. The EER of the I-vector/PLDA without combining is 6.18 % that shows the best performance. And combined with attention-LSTM based embedding is 2.57 % that is 3.61 % less than the baseline system, and which improves performance by 58.41 %.

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.6
• /
• pp.25-35
• /
• 1997

Most of speech analysis methods developed up to date are based on second order statistics, and one of the biggest drawback of these methods is that they show dramatical performance degradation in noisy environments. On the contrary, the methods using higher order statistics(HOS), which has the property of suppressing Gaussian noise, enable robust feature extraction in noisy environments. In this paper we propose a text-independent speaker identification system using higher order statistics and compare its performance with that using the conventional second-order-statistics-based method in both white and colored noise environments. The proposed speaker identification system is based on the vector quantization approach, and employs HOS-based voiced/unvoiced detector in order to extract feature parameters for voiced speech only, which has non-Gaussian distribution and is known to contain most of speaker-specific characteristics. Experimental results using 50 speaker's database show that higher-order-statistics-based method gives a better identificaiton performance than the conventional second-order-statistics-based method in noisy environments.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.1
• /
• pp.48-53
• /
• 2003

Eigenvoice method is known to be adequate for fast speaker adaptation, but it hardly shows additional improvement with increased amount of adaptation data. In this paper, to deal with this problem, we propose a modified method estimating the weights of eigenvoices in each feature vector dimension. We also propose an adaptation mode selection scheme that one method with higher performance among several adaptation methods is selected according to the amount of adaptation data. We used POW DB to construct the speaker independent model and eigenvoices, and utterances(ranging from 1 to 50) from PBW 452 DB and the remaining 400 utterances were used for adaptation and evaluation, respectively. With the increased amount of adaptation data, proposed dimensional eigenvoice method showed higher performance than both conventional eigenvoice method and MLLR. Up to 26% of word error rate was reduced by the adaptation mode selection between eigenvoice and dimensional eigenvoice methods in comparison with conventional eigenvoice method.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.39 no.2
• /
• pp.116-127
• /
• 2002

A new approach to improve the speaker adaptation algorithm by means of the variable number of observation density functions for CDHMM speech recognizer has been proposed. The proposed method uses the observation density function with more than one mixture in each state to represent speech characteristics in detail. The number of mixtures in each state is determined by the number of frames and the determinant of the variance, respectively. The each MAP Parameter is extracted in every mixture determined by these two methods. In addition, the state segmentation method requiring speaker adaptation can segment the adapting speech more Precisely by using speaker-independent model trained from sufficient database as a priori knowledge. And the state duration distribution is used lot adapting the speech duration information owing to speaker's utterance habit and speed. The recognition rate of the proposed methods are significantly higher than that of the conventional method using one mixture in each state.