• 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.

• MALSORI
• /
• no.45
• /
• pp.117-126
• /
• 2003

Decision tree-based state tying has been proposed in recent years as the most popular approach for clustering the states of context-dependent hidden Markov model-based speech recognition. The aims of state tying is to reduce the number of free parameters and predict state probability distributions of unseen models. But, when doing state tying, the size of a decision tree is very important for word independent recognition. In this paper, we try to construct optimized decision tree based on the average of feature vectors in state pool and the number of seen modes. We observed that the proposed optimal decision tree is effective in predicting the state probability distribution of unseen models.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.6
• /
• pp.552-558
• /
• 2002

Recently, based on the human speech recognition (HSR) model of Fletcher, the multi-band speech recognition has been intensively studied by many researchers. As a new automatic speech recognition (ASR) technique, the multi-band speech recognition splits the frequency domain into several sub-bands and recognizes each sub-band independently. The likelihood scores of sub-bands are weighted according to reliabilities of sub-bands and re-combined to make a final decision. This approach is known to be robust under noisy environments. When the noise is stationary a sub-band SNR can be estimated using the noise information in non-speech interval. However, if the noise is non-stationary it is not feasible to obtain the sub-band SNR. This paper proposes the inverse sub-band distance (ISD) weighting, where a distance of each sub-band is calculated by a stochastic matching of input feature vectors and hidden Markov models. The inverse distance is used as a sub-band weight. Experiments on 1500∼1800㎐ band-limited white noise and classical guitar sound revealed that the proposed method could represent the sub-band reliability effectively and improve the performance under both stationary and non-stationary band-limited noise environments.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.44 no.4 s.316
• /
• pp.36-44
• /
• 2007

In this paper, we implement the speech & face recognition system to support various ubiquitous sensor network application services such as switch control, authentication, etc. using wireless audio and image interface. The proposed system is consist of the H/W with audio and image sensor and S/W such as speech recognition algorithm using psychoacoustic model, face recognition algorithm using PCA (Principal Components Analysis) and LDPC (Low Density Parity Check). The proposed speech and face recognition systems are inserted in a HOST PC to use the sensor energy effectively. And improve the accuracy of speech and face recognition, we implement a FEC (Forward Error Correction) system Also, we optimized the simulation coefficient and test environment to effectively remove the wireless channel noises and correcting wireless channel errors. As a result, when the distance that between audio sensor and the source of voice is less then 1.5m FAR and FRR are 0.126% and 7.5% respectively. The face recognition algorithm step is limited 2 times, GAR and FAR are 98.5% and 0.036%.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.2
• /
• pp.254-259
• /
• 2011

For the emergency detecting in general CCTV environment of our daily life, the monitoring by only images through CCTV information occurs some problems especially in cost as well as man power. Therefore, in this paper, for detecting emergency state dynamically through CCTV as well as resolving some problems, we propose a detection and recognition method for emergency and non-emergency speech by GMM. The proposed method determine whether input speech is emergency or non-emergency speech by global GMM. If emergeny speech, local GMM is performed to classify the type of emergency speech. The proposed method is tested and verified by emergency and non-emergency speeches in various environmental conditions.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1994.06a
• /
• pp.1039-1045
• /
• 1994

The speech recognition systems using VQ have usually the problem decreasing recognition rate, MSVQ assigning the dissimilar vectors to a segment. In this paper, applying One-stage DMS/DP algorithm to the recognition experiments, we can solve these problems to what degree. Recognition experiment is peformed for Korean DDD area names with DMS model of 20 sections and word unit template. We carried out the experiment in speaker dependent and speaker independent, and get a recognition rates of 97.7% and 81.7% respectively.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.4
• /
• pp.478-484
• /
• 2009

Automatic speech recognition(ASR) is attractive technique in trend these day that seek convenient life. Although many approaches have been proposed for ASR but the performance is still not good in noisy environment. Now-a-days in the state of art in speech recognition, ASR uses not only the audio information but also the visual information. In this paper, We present a novel lip detection method for visual speech recognition in mobile environment. In order to apply visual information to speech recognition, we need to extract exact lip regions. Because eye-detection is more easy than lip-detection, we firstly detect positions of left and right eyes, then locate lip region roughly. After that we apply K-means clustering technique to devide that region into groups, than two lip corners and lip center are detected by choosing biggest one among clustered groups. Finally, we have shown the effectiveness of the proposed method through the experiments based on samsung AVSR database.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.5C
• /
• pp.627-631
• /
• 2004

An efficient algorithm for clustering of GPDFs(Gaussian Probability Density Functions) in a speech recognition model is proposed in this paper. The proposed algorithm is based on CNN with the divergence as its distance measure and is applied to a speech recognition. The algorithm is compared with conventional Dk-means(Divergence-based k-means) algorithm in CDHMM(Continuous Density Hidden Markov Model). The results show that it can reduce about 31.3％ of GPDFs over Dk-means algorithm without suffering any recognition performance. When compared with the case that no clustering is employed and full GPDFs are used, the proposed algorithm can save about 61.8％ of GPDFs while preserving the recognition performance.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.10
• /
• pp.461-470
• /
• 2023

While speech animation generation employing deep learning has been actively researched for English, there has been no prior work for Korean. Given the fact, this paper for the very first time employs supervised deep learning to generate Korean speech animation. By doing so, we find out the significant effect of deep learning being able to make speech animation research come down to speech recognition research which is the predominating technique. Also, we study the way to make best use of the effect for Korean speech animation generation. The effect can contribute to efficiently and efficaciously revitalizing the recently inactive Korean speech animation research, by clarifying the top priority research target. This paper performs this process: (i) it chooses blendshape animation technique, (ii) implements the deep-learning model in the master-servant pipeline of the automatic speech recognition (ASR) module and the facial action coding (FAC) module, (iii) makes Korean speech facial motion capture dataset, (iv) prepares two comparison deep learning models (one model adopts the English ASR module, the other model adopts the Korean ASR module, however both models adopt the same basic structure for their FAC modules), and (v) train the FAC modules of both models dependently on their ASR modules. The user study demonstrates that the model which adopts the Korean ASR module and dependently trains its FAC module (getting 4.2/5.0 points) generates decisively much more natural Korean speech animations than the model which adopts the English ASR module and dependently trains its FAC module (getting 2.7/5.0 points). The result confirms the aforementioned effect showing that the quality of the Korean speech animation comes down to the accuracy of Korean ASR.

• Journal of Biomedical Engineering Research
• /
• v.9 no.1
• /
• pp.1-10
• /
• 1988

In this study, the recognition experiments for Korean vowel are performed using peripheral auditory model. In addition, for the purpose of objective comparison, the recognition experiments are performed by extracting LPC cepstrum coefficients for the same speech data. The results are as follows. 1) The time and the frequency responses of the auditory model show that important features of input signal are involved in the responses of inner ear and auditory nerve. 2) The recognition results for Korean vowel show that the recognition rate by auditory model output is higher than the recognition rate by LPC cepstrum coefficients. 3) The adaptation phenomenon of auditory nerve provides useful characteristics for the discrimination of vowel signal.