• 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).

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.2
• /
• pp.145-152
• /
• 2003

In this paper, assuming that the score of speech utterance is the product of HMM log likelihood and HMM weight, we propose a new method that HMM weights are adapted iteratively like the general MCE training. The proposed method adjusts HMM weights for better performance using delta coefficient defined in terms of misclassification measure. Therefore, the parameter estimation and the Viterbi algorithms of conventional 1:.um can be easily applied to the proposed model by constraining the sum of HMM weights to the number of HMMs in an HMM set. Comparing with the general segmental MCE training approach, computing time decreases by reducing the number of parameters to estimate and avoiding gradient calculation through the optimal state sequence. To evaluate the performance of HMM-based speech recognizer by weighting HMM likelihood, we perform Korean isolated digit recognition experiments. The experimental results show better performance than the MCE algorithm with state weighting.

• MALSORI
• /
• no.60
• /
• pp.109-123
• /
• 2006

Since computing the log-likelihood of Gaussian mixture density is a major computational burden for the speech recognizer based on the continuous HMM, several techniques have been proposed to reduce the number of mixtures to be used for recognition. In this paper, we propose a modified Bucket Box Intersection (BBI) algorithm, in which two relative thresholds are employed: one is the relative threshold in the conventional BBI algorithm and the other is used to reduce the number of the Gaussian boxes which are intersected by the hyperplanes at the boxes' edges. The experimental results show that the proposed algorithm reduces the number of Gaussian mixtures by 12.92% during the recognition phase with negligible performance degradation compared to the conventional BBI algorithm.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.2
• /
• pp.131-136
• /
• 2020

Wake Up Word (WUW) is a short utterance used to convert speech recognizer to recognition mode. The WUW defined by the user who actually use the speech recognizer is called user-defined WUW. In this paper, to recognize user-defined WUW, we construct traditional Gaussian Mixture Model-Hidden Markov Model (GMM-HMM), Linear Discriminant Analysis (LDA)-GMM-HMM and LDA-Deep Neural Network (DNN)-HMM based system and compare their performances. Also, to improve recognition accuracy of the WUW system, a threshold method is applied to each model, which significantly reduces the error rate of the WUW recognition and the rejection failure rate of non-WUW simultaneously. For LDA-DNN-HMM system, when the WUW error rate is 9.84 %, the rejection failure rate of non-WUW is 0.0058 %, which is about 4.82 times lower than the LDA-GMM-HMM system. These results demonstrate that LDA-DNN-HMM model developed in this paper proves to be highly effective for constructing user-defined WUW recognition system.

• MALSORI
• /
• no.59
• /
• pp.53-68
• /
• 2006

We report the evaluation results of the Korean speech recognition platform called ECHOS. The platform has an object-oriented and reusable architecture so that researchers can easily evaluate their own algorithms. The platform has all intrinsic modules to build a large vocabulary speech recognizer: Noise reduction, end-point detection, feature extraction, hidden Markov model (HMM)-based acoustic modeling, cross-word modeling, n-gram language modeling, n-best search, word graph generation, and Korean-specific language processing. The platform supports both lexical search trees and finite-state networks. It performs word-dependent n-best search with bigram in the forward search stage, and rescores the lattice with trigram in the backward stage. In an 8000-word continuous speech recognition task, the platform with a lexical tree increases 40% of word errors but decreases 50% of recognition time compared to the HTK platform with flat lexicon. ECHOS reduces 40% of recognition errors through incorporation of cross-word modeling. With the number of Gaussian mixtures increasing to 16, it yields word accuracy comparable to the previous lexical tree-based platform, Julius.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.8 no.2
• /
• pp.359-364
• /
• 2004

In this paper, we implemented real-time speaker undependent speech recognizer that is robust in noise environment using DSP(Digital Signal Processor). Implemented system is composed of TMS320C32 that is floating-point DSP of Texas Instrument Inc. and CODEC for real-time speech input. Speech feature parameter of the speech recognizer used robust feature parameter in noise environment that is transformed feature space of MFCC(met frequency cepstral coefficient) using ICA(Independent Component Analysis) on behalf of MFCC. In recognition result in noise environment, we hew that recognition performance of ICA feature parameter is superior than that of MFCC.

• Journal of Institute of Control, Robotics and Systems
• /
• v.16 no.12
• /
• pp.1137-1142
• /
• 2010

This paper studied the speech parameters less affected by the human emotion for the development of the robust speech recognition system. For this purpose, the effect of emotion on the speech recognition system and robust speech parameters of speech recognition system were studied using speech database containing various emotions. In this study, mel-cepstral coefficient, delta-cepstral coefficient, RASTA mel-cepstral coefficient and frequency warped mel-cepstral coefficient were used as feature parameters. And CMS (Cepstral Mean Subtraction) method were used as a signal bias removal technique. Experimental results showed that the HMM based speaker independent word recognizer using vocal tract length normalized mel-cepstral coefficient, its derivatives and CMS as a signal bias removal showed the best performance of 0.78% word error rate. This corresponds to about a 50% word error reduction as compare to the performance of baseline system using mel-cepstral coefficient, its derivatives and CMS.

• The Journal of the Acoustical Society of Korea
• /
• v.23 no.3E
• /
• pp.85-90
• /
• 2004

This paper presents two kinds of new approaches, one of which is concerned with recognition of emotional speech such as anger, happiness, normal, sadness, or surprise. The other is concerned with emotion recognition in speech. For the proposed speech recognition system handling human speech with emotional states, total nine kinds of prosodic features were first extracted and then given to prosodic identifier. In evaluation, the recognition results on emotional speech showed that the rates using proposed method increased more greatly than the existing speech recognizer. For recognition of emotion, on the other hands, four kinds of prosodic parameters such as pitch, energy, and their derivatives were proposed, that were then trained by discrete duration continuous hidden Markov models(DDCHMM) for recognition. In this approach, the emotional models were adapted by specific speaker's speech, using maximum a posteriori(MAP) estimation. In evaluation, the recognition results on emotional states showed that the rates on the vocal emotions gradually increased with an increase of adaptation sample number.

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.2
• /
• pp.49-57
• /
• 1997

In this paper, we propose the stochastic pronunciation lexicon model for large vocabulary continuous speech recognition system. We can regard stochastic lexicon as HMM. This HMM is a stochastic finite state automata consisting of a Markov chain of subword states and each subword state in the baseform has a probability distribution of subword units. In this method, an acoustic representation of a word can be derived automatically from sample sentence utterances and subword unit models. Additionally, the stochastic lexicon is further optimized to the subword model and recognizer. From the experimental result on 3000 word continuous speech recognition, the proposed method reduces word error rate by 23.6% and sentence error rate by 10% compare to methods based on standard phonetic representations of words.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.5
• /
• pp.696-700
• /
• 2007

A new method that improves the performance of the phonetic transcription based speech recognition system is presented with the speaker-independent phonetic recognizer. Since SI phoneme HMM based speech recognition system uses only the phoneme transcription of the input sentence, the storage space could be reduced greatly. However, the performance of the system is worse than that of the speaker dependent system due to the phoneme recognition errors generated from using SI models. A new training method that iteratively estimates the phonetic transcription and transformation vectors is presented to reduce the mismatch between the training utterances and a set of SI models using speaker adaptation techniques. For speaker adaptation the stochastic matching methods are used to estimate the transformation vectors. The experiments performed over actual telephone line shows that a reduction of about 45% in the error rates could be achieved as compared to the conventional method.