• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.40 no.8
• /
• pp.782-791
• /
• 1991

In the fields of pattern recognition such as speech recognition, several new techniques using Artifical Neural network Models have been proposed and implemented. In particular, the Multilayer Perception Model has been shown to be effective in static speech pattern recognition. But speech has dynamic or temporal characteristics and the most important point in implementing speech recognition systems using Artificial Neural Network Models for continuous speech is the learning of dynamic characteristics and the distributed cues and contextual effects that result from temporal characteristics. But Recurrent Multilayer Perceptron Model is known to be able to learn sequence of pattern. In this paper, the results of applying the Recurrent Model which has possibilities of learning tedmporal characteristics of speech to phoneme recognition is presented. The test data consist of 144 Vowel+ Consonant + Vowel speech chains made up of 4 Korean monothongs and 9 Korean plosive consonants. The input parameters of Artificial Neural Network model used are the FFT coefficients, residual error and zero crossing rates. The Baseline model showed a recognition rate of 91% for volwels and 71% for plosive consonants of one male speaker. We obtained better recognition rates from various other experiments compared to the existing multilayer perceptron model, thus showed the recurrent model to be better suited to speech recognition. And the possibility of using Recurrent Models for speech recognition was experimented by changing the configuration of this baseline model.

• Speech Sciences
• /
• v.14 no.2
• /
• pp.115-126
• /
• 2007

There have been many research efforts to improve the performance of the speech recognizer in noisy conditions. Among them, the model compensation method and the speech enhancement approach have been used widely. In this paper, we propose to combine the two different approaches to further enhance the recognition rates in the noisy speech recognition. For the speech enhancement, the minimum mean square error-short time spectral amplitude (MMSE-STSA) has been adopted and the parallel model combination (PMC) and Jacobian adaptation (JA) have been used as the model compensation approaches. From the experimental results, we could find that the hybrid approach that applies the model compensation methods to the enhanced speech produce better results than just using only one of the two approaches.

• Journal of Digital Convergence
• /
• v.16 no.11
• /
• pp.335-340
• /
• 2018

Commercialized speech recognition systems that have an accuracy recognition rates are used a learning model from a type of speaker dependent isolated data. However, it has a problem that shows a decrease in the speech recognition performance according to the quantity of data in noise environments. In this paper, we proposed the vector quantization based speech recognition performance improvement using maximum log likelihood in Gaussian distribution. The proposed method is the best learning model configuration method for increasing the accuracy of speech recognition for similar speech using the vector quantization and Maximum Log Likelihood with speech characteristic extraction method. It is used a method of extracting a speech feature based on the hidden markov model. It can improve the accuracy of inaccurate speech model for speech models been produced at the existing system with the use of the proposed system may constitute a robust model for speech recognition. The proposed method shows the improved recognition accuracy in a speech recognition system.

• Speech Sciences
• /
• v.11 no.2
• /
• pp.247-257
• /
• 2004

There has been many research efforts to overcome the problems of speech recognition in the noisy conditions. Among them, the model-based compensation methods such as the parallel model combination (PMC) and vector Taylor series (VTS) have been found to perform efficiently compared with the previous speech enhancement methods or the feature-based approaches. In this paper, a data-driven model compensation approach that adapts the HMM(hidden Markv model) parameters for the noisy speech recognition is proposed. Instead of assuming some statistical approximations as in the conventional model-based methods such as the PMC, the statistics necessary for the HMM parameter adaptation is directly estimated by using the Baum-Welch algorithm. The proposed method has shown improved results compared with the PMC for the noisy speech recognition.

• Speech Sciences
• /
• v.13 no.2
• /
• pp.75-84
• /
• 2006

Various methods have been proposed to overcome the problem of speech recognition in the noisy conditions. Among them, the model compensation methods like the parallel model combination (PMC) and Jacobian adaptation (JA) have been found to perform efficiently. The JA is quite effective when we have hidden Markov models (HMMs) already trained in a similar condition as the target environment. In a previous work, we have proposed an improved method for the JA to make it more robust against the changing environments in recognition. In this paper, we further improved its performance by compensating the delta-mean vectors and covariance matrices of the HMM and investigated its feasibility in the multi-model structure for the noisy speech recognition. From the experimental results, we could find that the proposed improved the robustness of the JA and the multi-model approach could be a viable solution in the noisy speech recognition.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.10
• /
• pp.1-7
• /
• 2021

Recently, since most of the research on correcting speech recognition errors is based on English, there is not enough research on Korean speech recognition. Compared to English speech recognition, however, Korean speech recognition has many errors due to the linguistic characteristics of Korean language, such as Korean Fortis and Korean Liaison, thus research on Korean speech recognition is needed. Furthermore, earlier works primarily focused on editorial distance algorithms and syllable restoration rules, making it difficult to correct the error types of Korean Fortis and Korean Liaison. In this paper, we propose a context-sensitive post-processing model of speech recognition using a LSTM-based sequence-to-sequence model and Bahdanau attention mechanism to correct Korean speech recognition errors caused by the pronunciation. Experiments showed that by using the model, the speech recognition performance was improved from 64% to 77% for Fortis, 74% to 90% for Liaison, and from 69% to 84% for average recognition than before. Based on the results, it seems possible to apply the proposed model to real-world applications based on speech recognition.

• Speech Sciences
• /
• v.15 no.2
• /
• pp.55-65
• /
• 2008

Recently, the multi-model based speech recognizer has been used quite successfully for noisy speech recognition. For the selection of the reference HMM (hidden Markov model) which best matches the noise type and SNR (signal to noise ratio) of the input testing speech, the estimation of the SNR value using the VAD (voice activity detection) algorithm and the classification of the noise type based on the GMM (Gaussian mixture model) have been done separately in the multi-model framework. As the SNR estimation process is vulnerable to errors, we propose an efficient method which can classify simultaneously the SNR values and noise types. The KL (Kullback-Leibler) distance between the single Gaussian distributions for the noise signal during the training and testing is utilized for the classification. The recognition experiments have been done on the Aurora 2 database showing the usefulness of the model compensation method in the multi-model based speech recognizer. We could also see that further performance improvement was achievable by combining the probability density function of the MCT (multi-condition training) with that of the reference HMM compensated by the D-JA (data-driven Jacobian adaptation) in the multi-model based speech recognizer.

• MALSORI
• /
• no.51
• /
• pp.151-165
• /
• 2004

For educational and research purposes, a Korean speech recognition platform is designed. It is based on an object-oriented architecture and can be easily modified so that researchers can readily evaluate the performance of a recognition algorithm of interest. This platform will save development time for many who are interested in speech recognition. The platform includes the following modules: Noise reduction, end-point detection, met-frequency cepstral coefficient (MFCC) and perceptually linear prediction (PLP)-based feature extraction, hidden Markov model (HMM)-based acoustic modeling, n-gram language modeling, n-best search, and Korean language processing. The decoder of the platform can handle both lexical search trees for large vocabulary speech recognition and finite-state networks for small-to-medium vocabulary speech recognition. It performs word-dependent n-best search algorithm with a bigram language model in the first forward search stage and then extracts a word lattice and restores each lattice path with a trigram language model in the second stage.

• The Journal of the Acoustical Society of Korea
• /
• v.27 no.4
• /
• pp.191-199
• /
• 2008

In this paper, we propose a MWF-PMC noise processing method which enhances the input speech by using Mel-warped Wiener Filtering (MWF) at pre-processing stage and compensates the recognition model by using PMC (Parallel Model Combination) at post-processing stage for speech recognition in noisy environments. The PMC uses the residual noise extracted from the silence region of enhanced speech at pre-processing stage to compensate the clean speech model and thus this method is considered to improve the performance of speech recognition in noisy environments. For recognition experiments we dew.-sampled KLE PBW (Phoneme Balanced Words) 452 word speech data to 8kHz and made 5 different SNR levels of noisy speech, i.e., 0dB. 5dB, 10dB, 15dB and 20dB, by adding Subway, Car and Exhibition noise to clean speech. From the recognition results, we could confirm the effectiveness of the proposed MWF-PMC method by obtaining the improved recognition performances over all compared with the existing combined methods.

• Phonetics and Speech Sciences
• /
• v.2 no.3
• /
• pp.141-148
• /
• 2010

In this paper, voice activity detection (VAD) for dual-channel noisy speech recognition is proposed in which spatial cues are employed. In the proposed method, a probability model for speech presence/absence is constructed using spatial cues obtained from dual-channel input signal, and a speech activity interval is detected through this probability model. In particular, spatial cues are composed of interaural time differences and interaural level differences of dual-channel speech signals, and the probability model for speech presence/absence is based on a Gaussian kernel density. In order to evaluate the performance of the proposed VAD method, speech recognition is performed for speech segments that only include speech intervals detected by the proposed VAD method. The performance of the proposed method is compared with those of several methods such as an SNR-based method, a direction of arrival (DOA) based method, and a phase vector based method. It is shown from the speech recognition experiments that the proposed method outperforms conventional methods by providing relative word error rates reductions of 11.68%, 41.92%, and 10.15% compared with SNR-based, DOA-based, and phase vector based method, respectively.