• 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.

• The Journal of the Acoustical Society of Korea
• /
• v.29 no.2E
• /
• pp.100-106
• /
• 2010

Multiple-model speech recognizer has been shown to be quite successful in noisy speech recognition. However, its performance has usually been tested using the general speech front-ends which do not incorporate any noise adaptive algorithms. For the accurate evaluation of the effectiveness of the multiple-model frame in noisy speech recognition, we used the state-of-the-art front-ends and compared its performance with the well-known multi-style training method. In addition, we improved the multiple-model speech recognizer by employing N-best reference HMMs for interpolation and using multiple SNR levels for training each of the reference HMM.

• Journal of the Institute of Convergence Signal Processing
• /
• v.11 no.2
• /
• pp.137-142
• /
• 2010

Although multi-model speech recognizer has been shown to be quite successful in noisy speech recognition, the results were based on general speech front-ends which do not take into account noise adaptation techniques. In this paper, for the accurate evaluation of the multi-model based speech recognizer, we adopted a quite noise-robust speech front-end, AFE, which was proposed by the ETSI for the noisy DSR environment. For the performance comparison, the MTR which is known to give good results in the DSR environment has been used. Also, we modified the structure of the multi-model based speech recognizer to improve the recognition performance. N reference HMMs which are most similar to the input noisy speech are used as the acoustic models for recognition to cope with the errors in the selection of the reference HMMs and the noise signal variability. In addition, multiple SNR levels are used to train each of the reference HMMs to improve the robustness of the acoustic models. From the experimental results on the Aurora 2 databases, we could see better recognition rates using the modified multi-model based speech recognizer compared with the previous method.

• The Journal of the Acoustical Society of Korea
• /
• v.20 no.6
• /
• pp.40-45
• /
• 2001

In this paper, we implemented a multimodal system combining speech and lip information, and evaluated its performance. We designed speech recognizer using speech information and lip recognizer using image information. Both recognizers were based on HMM recognition engine. As a combining method we adopted the late integration method in which weighting ratio for speech and lip is 8:2. By the way, Our constructed multi-modal recognition system was ported on DARC system. That is, our system was used to control Comdio of DARC. The interrace between DARC and our system was done with TCP/IP socked. The experimental results of controlling Comdio showed that lip recognition can be used for an auxiliary means of speech recognizer by improving the rate of the recognition. Also, we expect that multi-model system will be successfully applied to o traffic information system and CNS (Car Navigation System).

• Phonetics and Speech Sciences
• /
• v.10 no.4
• /
• pp.111-119
• /
• 2018

This paper proposes a method to improve speech recognition performance by extracting various pronunciations of the pseudo-morpheme unit from an eojeol unit corpus and generating a new recognition unit considering pronunciation variations. In the proposed method, we first align the pronunciation of the eojeol units and the pseudo-morpheme units, and then expand the pronunciation dictionary by extracting the new pronunciations of the pseudo-morpheme units at the pronunciation of the eojeol units. Then, we propose a new recognition unit that relies on pronunciation by tagging the obtained phoneme symbols according to the pseudo-morpheme units. The proposed units and their extended pronunciations are incorporated into the lexicon and language model of the speech recognizer. Experiments for performance evaluation are performed using the Korean speech recognizer with a trigram language model obtained by a 100 million pseudo-morpheme corpus and an acoustic model trained by a multi-genre broadcast speech data of 445 hours. The proposed method is shown to reduce the word error rate relatively by 13.8% in the news-genre evaluation data and by 4.5% in the total evaluation data.

• Journal of KIISE:Computing Practices and Letters
• /
• v.13 no.5
• /
• pp.338-342
• /
• 2007

In this paper we propose a user adaptive post-processing method to improve the accuracy of speaker dependent, isolated word speech recognition, particularly for mobile devices. Our method considers the recognition result of the basic recognizer simply as a high-level speech feature and processes it further for correct recognition result. Our method learns correlation between the output of the basic recognizer and the correct final results and uses it to correct the erroneous output of the basic recognizer. A multi-layer perceptron model is built for each incorrectly recognized word with high frequency. As the result of experiments, we achieved a significant improvement of 41% in recognition accuracy (41% error correction rate).

• MALSORI
• /
• no.62
• /
• pp.97-112
• /
• 2007

The speech recognizer in general operates in noisy acoustical environments. Many research works have been done to cope with the acoustical variations. Among them, the multiple-HMM model approach seems to be quite effective compared with the conventional methods. In this paper, we consider a multiple-model approach combined with the model compensation method and investigate the necessary number of the HMM model sets through noisy speech recognition experiments. By using the data-driven Jacobian adaptation for the model compensation, the multiple-model approach with only a few model sets for each noise type could achieve comparable results with the re-training method.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.3
• /
• pp.273-278
• /
• 2004

In this paper, the recurrent neural networks (RNN) is applied to compensate for HMM recognition algorithm, which is commonly used as main recognizer. Among these recurrent neural networks, the multi-layer recurrent neural prediction model (MRNPM), which allows operating in real-time, is used to implement learning and recognition, and HMM and MRNPM are used to design a hybrid-type main recognizer. After testing the designed speech recognition algorithm with Korean number pronunciations (13 words), which are hardly distinct, for its speech-independent recognition ratio, about 5% improvement was obtained comparing with existing HMM recognizers. Based on this result, only optimal (recognition) codes were extracted in the actual DSP (TMS320C6711) environment, and the embedded speech recognition system was implemented. Similarly, the implementation result of the embedded system showed more improved recognition system implementation than existing solid HMM recognition systems.

• Journal of KIISE:Computing Practices and Letters
• /
• v.6 no.4
• /
• pp.403-410
• /
• 2000

In this paper, the development of a stock information retrieval system using speech recognition and its features are described. The system is based on DHMM (discrete hidden Markov model) and PLUs (phonelike units) are used as the basic unit for recognition. End-point detection and echo cancellation are included to facilitate speech input. Continuous speech recognizer is implemented to allow multi-word speech. Data collected over several months are analyzed.

• The Journal of the Acoustical Society of Korea
• /
• v.19 no.6
• /
• pp.41-46
• /
• 2000

In this paper, we implement the speech recognition system based on the continuous distribution HMM and Browser-embedded model using the Java. That is developed for the speech analysis, processing and recognition on the Web. Client sends server through the socket to the speech informations that extracting of end-point detection, MFCC, energy and delta coefficients using the Java Applet. The sewer consists of the HMM recognizer and trained DB which recognizes the speech and display the recognized text back to the client. Because of speech recognition system using the java is high error rate, the platform is independent of system on the network. But the meaning of implemented system is merged into multi-media parts and shows new information and communication service possibility in the future.