• Journal of KIISE
• /
• v.42 no.11
• /
• pp.1372-1379
• /
• 2015

This paper presents an analysis of feature extraction methods used for distinguishing the speech of patients with cleft palates and people with normal palates. This research is a basic study on the development of a software system for automatic recognition and restoration of speech disorders, in pursuit of improving the welfare of speech disabled persons. Monosyllable voice data for experiments were collected for three groups: normal speech, cleft palate speech, and simulated clef palate speech. The data consists of 14 basic Korean consonants, 5 complex consonants, and 7 vowels. Feature extractions are performed using three well-known methods: LPC, MFCC, and PLP. The pattern recognition process is executed using the acoustic model GMM. From our experiments, we concluded that the MFCC method is generally the most effective way to identify speech distortions. These results may contribute to the automatic detection and correction of the distorted speech of cleft palate patients, along with the development of an identification tool for levels of speech distortion.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.8
• /
• pp.105-113
• /
• 1996

In this paper, a new korean digita speech recognition technique was proposed using muktolayer perceptron (MLP). In spite of its weakness in dynamic signal recognition, MLP was adapted for this model, cecause korean syllable could give static features. It is so simle in its structure and fast in its computing that MLP was used to the suggested system. MLP's input vectors was transformed using karhunen-loeve transformation (KLT), which compress signal successfully without losin gits separateness, but its physical properties is changed. Because the suggested technique could extract static features while it is not affected from the changes of syllable lengths, it is effectively useful for korean numeric recognition system. Without decreasing classification rates, we can save the time and memory size for computation using KLT. The proposed feature extraction technique extracts same size of features form the tow same parts, front and end of a syllable. This technique makes frames, where features are extracted, using unique size of windows. It could be applied for continuous speech recognition that was not easy for the normal neural network recognition system.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.8 no.4
• /
• pp.219-225
• /
• 2013

This paper presents a method using Maximum-Likelihood Linear Regression (MLLR) adaptation to improve recognition performance of Limabeam algorithm for speech recognition using microphone array. From our investigation on Limabeam algorithm, we can see that the performance of filtering optimization depends strongly on the supporting optimal state sequence and this sequence is created by using Viterbi algorithm trained with HMM model. So we propose an approach using MLLR adaptation for the recognition of speech uttered in a new environment to obtain better optimal state sequence that support for the filtering parameters' optimal step. Experimental results show that the system embedded with MLLR adaptation presents the word correct recognition rate 2% higher than that of original calibrate Limabeam and also present 7% higher than that of Delay and Sum algorithm. The best recognition accuracy of 89.4% is obtained when we use 4 microphones with 5 utterances for adaptation.

• The Journal of the Acoustical Society of Korea
• /
• v.18 no.2
• /
• pp.3-10
• /
• 1999

This paper describes the development and evaluation of a Korean address input system employing automatic speech recognition technique as user interface for input Korean address. Address consists of cities, provinces and counties. The system works on a window 95 environment of personal computer with built-in soundcard. In the speech recognition part, the Continuous density Hidden Markov Model(CHMM) for making phoneme like units(PLUs) and One Pass Dynamic Programming(OPDP) algorithm is used for recognition. For address recognition, Finite State Automata(FSA) suitable for Korean address structure is constructed. To achieve an acceptable performance against the variation of speakers, microphones, and environmental noises, Maximum a posteriori(MAP) estimation is implemented in adaptation. And to improve the recognition speed, fast search method using variable pruning threshold is newly proposed. In the evaluation tests conducted for the 100 connected words uttered by 3 males the system showed above average 96.0% of recognition accuracy for connected words after adaption and recognition speed within 2 seconds, showing the effectiveness of the system.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.7
• /
• pp.611-614
• /
• 2001

Voice is one of the most efficient communication media and it includes several kinds of factors about speaker, context emotion and so on. Human emotion is expressed is expressed in the speech, the gesture, the physiological phenomena(the breath, the beating of the pulse, etc). In this paper, the emotion recognition method model using neuro-fuzzy in order to have cognizance of emotion from voice signal is presented and simulated.

• 제어로봇시스템학회:학술대회논문집
• /
• 1988.10b
• /
• pp.1037-1040
• /
• 1988

In this study, we performed the recognition test on Korean vowel using peripheral auditory model. In addition, for the purpose of objective comparision, the recognition test is performed by extracting LPC cepstrum coefficients from the same data. And the same speech data are mixed with the Guaussian white noise quantitatively, then we repeated the same test, too. So we verified that this auditory model has a adaptability on noise.

• The Journal of the Acoustical Society of Korea
• /
• v.14 no.3
• /
• pp.61-70
• /
• 1995

In this paper, the PLP cepstrum which is close to human perceptual characteristics was extracted through the spread time area to get the temperal feature. Phonemes were recognized by artificial neural network similar to the learning method of human. The phoneme strings were matched by Markov models which well suited for sequence. Phoneme recognition for the continuous Korean speech had been done using speech blocks in which speech frames were gathered with unequal numbers. We parameterized the blocks using 7th order PLPs, PTP, zero crossing rate and energy, which neural network used as inputs. The 100 data composed of 10 Korean sentences which were taken from the speech two men pronounced five times for each sentence were used for the the recognition. As a result, maximum recognition rate of 94.4% was obtained. The sentence was recognized using Markov models generated by the phoneme strings recognized from earlier results the recognition for the 200 data which two men sounded 10 times for each sentence had been carried out. The sentence recognition rate of 92.5% was obtained.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.37 no.5
• /
• pp.54-63
• /
• 2000

In this paper, we implemented cyber character that can do speech recognition, speech synthesis, Motion tracking and 3D animation. For speech recognition, we used Discrete-HMM algorithm with K-means 128 level vector quantization and MFCC feature vector. For speech synthesis, we used demi-syllables TD-PSOLA algorithm. For PC based Motion tracking, we present Fast Optical Flow like Method. And for animating 3D model, we used vertex interpolation with DirectSD retained mode. Finally, we implemented cyber character integrated above systems, which game calculating by the multiplication table with user and the cyber character always look at user using of Motion tracking system.

• Phonetics and Speech Sciences
• /
• v.13 no.1
• /
• pp.45-51
• /
• 2021

End-to-end (E2E) automatic speech recognition (ASR) has achieved promising performance gains with the introduced self-attention network, Transformer. However, due to training time and the number of hyperparameters, finding the optimal hyperparameter set is computationally expensive. This paper investigates the impact of hyperparameters in the Transformer network to answer two questions: which hyperparameter plays a critical role in the task performance and training speed. The Transformer network for training has two encoder and decoder networks combined with Connectionist Temporal Classification (CTC). We have trained the model with Wall Street Journal (WSJ) SI-284 and tested on devl93 and eval92. Seventeen hyperparameters were selected from the ESPnet training configuration, and varying ranges of values were used for experiments. The result shows that "num blocks" and "linear units" hyperparameters in the encoder and decoder networks reduce Word Error Rate (WER) significantly. However, performance gain is more prominent when they are altered in the encoder network. Training duration also linearly increased as "num blocks" and "linear units" hyperparameters' values grow. Based on the experimental results, we collected the optimal values from each hyperparameter and reduced the WER up to 2.9/1.9 from dev93 and eval93 respectively.

• The Journal of the Acoustical Society of Korea
• /
• v.24 no.4E
• /
• pp.144-151
• /
• 2005

We evaluate the performance of emotion recognition via speech signals when a plain speaker talks to an entertainment robot. For each frame of a speech utterance, we extract the frame-based features: pitch, energy, formant, band energies, mel frequency cepstral coefficients (MFCCs), and velocity/acceleration of pitch and MFCCs. For discriminative classifiers, a fixed-length utterance-based feature vector is computed from the statistics of the frame-based features. Using a speaker-independent database, we evaluate the performance of two promising classifiers: support vector machine (SVM) and hidden Markov model (HMM). For angry/bored/happy/neutral/sad emotion classification, the SVM and HMM classifiers yield $42.3\%\;and\;40.8\%$ accuracy, respectively. We show that the accuracy is significant compared to the performance by foreign human listeners.