• Journal of Digital Convergence
• /
• v.11 no.6
• /
• pp.199-204
• /
• 2013

Speech recognition system is shall be composed model of learning from the inaccurate input speech. Similar phoneme models to recognize, because it leads to the recognition rate decreases. Therefore, in this paper, we propose a method of speech recognition optimal learning model configuration using the Bhattacharyya algorithm. Based on feature of the phonemes, HMM feature extraction method was used for the phonemes in the training data. Similar learning model was recognized as a model of exact learning using the Bhattacharyya algorithm. Optimal learning model configuration using the Bhattacharyya algorithm. Recognition performance was evaluated. In this paper, the result of applying the proposed system showed a recognition rate of 98.7% in the speech recognition.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.5
• /
• pp.515-522
• /
• 2021

It is hard to prepare sufficient training data for speech emotion recognition due to the difficulty of emotion labeling. In this paper, we apply transfer learning with large-scale training data for speech recognition on a transformer-based model to improve the performance of speech emotion recognition. In addition, we propose a method to utilize context information without decoding by multi-task learning with speech recognition. According to the speech emotion recognition experiments using the IEMOCAP dataset, our model achieves a weighted accuracy of 70.6 % and an unweighted accuracy of 71.6 %, which shows that the proposed method is effective in improving the performance of speech emotion recognition.

• 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.

• 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.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.6
• /
• pp.578-586
• /
• 2021

We propose a semi-supervised learning method based on Variational AutoEncoder (VAE) and Unsupervised Data Augmentation (UDA) to improve the performance of an end-to-end speech recognizer. In the proposed method, first, the VAE-based augmentation model and the baseline end-to-end speech recognizer are trained using the original speech data. Then, the baseline end-to-end speech recognizer is trained again using data augmented from the learned augmentation model. Finally, the learned augmentation model and end-to-end speech recognizer are re-learned using the UDA-based semi-supervised learning method. As a result of the computer simulation, the augmentation model is shown to improve the Word Error Rate (WER) of the baseline end-to-end speech recognizer, and further improve its performance by combining it with the UDA-based learning method.

• Journal of Digital Convergence
• /
• v.11 no.7
• /
• pp.209-214
• /
• 2013

Improve the recognition performance of speech recognition systems as a method for recognizing human listening skills were incorporated into the system. In noisy environments by separating the speech signal and noise, select the desired speech signal. but In terms of practical performance of speech recognition systems are factors. According to recognized environmental changes due to noise speech detection is not accurate and learning model does not match. In this paper, to improve the speech recognition feature extraction using gamma tone and learning model using acoustic model was proposed. The proposed method the feature extraction using auditory scene analysis for human auditory perception was reflected In the process of learning models for recognition. For performance evaluation in noisy environments, -10dB, -5dB noise in the signal was performed to remove 3.12dB, 2.04dB SNR improvement in performance was confirmed.

• Speech Sciences
• /
• v.10 no.1
• /
• pp.71-84
• /
• 2003

In the acoustic modeling for large vocabulary speech recognition, a sparse data problem caused by a huge number of context-dependent (CD) models usually leads the estimated models to being unreliable. In this paper, we develop a new clustering method based on the C45 decision-tree learning algorithm that effectively encapsulates the CD modeling. The proposed scheme essentially constructs a supervised decision rule and applies over the pre-clustered triphones using the C45 algorithm, which is known to effectively search through the attributes of the training instances and extract the attribute that best separates the given examples. In particular, the data driven method is used as a clustering algorithm while its result is used as the learning target of the C45 algorithm. This scheme has been shown to be effective particularly over the database of low unknown-context ratio in terms of recognition performance. For speaker-independent, task-independent continuous speech recognition task, the proposed method reduced the percent accuracy WER by 3.93% compared to the existing rule-based methods.

• Korean Journal of Cognitive Science
• /
• v.19 no.3
• /
• pp.297-310
• /
• 2008

Since speech acts implies speakers' intentions, it is essential to determine speakers' speech acts if we want to implement an intelligent dialogue system. We propose a two-step model for effectively determining speakers' speech acts. In the first step, the proposed model returns speech act candidates by using a neural network model based on machine learning and a predictivity model based on statistics, respectively. In the second step, using speech act candidates which are returned by the predictivity model, the proposed model filters out speech act candidates which are returned by the neural network model. Then, the proposed model selects a speech act with maximum output value among the unremoved speech act candidates. In the experiment on a schedule management domain, the proposed two-step modeling method showed better precisions than the previous methods only using a machine learning model or a probability model.

• Phonetics and Speech Sciences
• /
• v.11 no.4
• /
• pp.89-96
• /
• 2019

In this paper, we propose a deep learning architecture that can effectively detect speech segmentation in broadcast contents. We also propose a multi-scale time-dilated layer for learning the temporal changes of feature vectors. We implement several comparison models to verify the performance of proposed model and calculated the frame-by-frame F-score, precision, and recall. Both the proposed model and the comparison model are trained with the same training data, and we train the model using 32 hours of Korean broadcast data which is composed of various genres (drama, news, documentary, and so on). Our proposed model shows the best performance with F-score 91.7% in Korean broadcast data. The British and Spanish broadcast data also show the highest performance with F-score 87.9% and 92.6%. As a result, our proposed model can contribute to the improvement of performance of speech detection by learning the temporal changes of the feature vectors.

• 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.