• The Journal of the Acoustical Society of Korea
• /
• v.28 no.5
• /
• pp.471-476
• /
• 2009

In this paper, we apply a discriminative weight training to a support vector machine (SVM) based speech/music classification for the selectable mode vocoder (SMV) of 3GPP2. In our approach, the speech/music decision rule is expressed as the SVM discriminant function by incorporating optimally weighted features of the SMV based on a minimum classification error (MCE) method which is different from the previous work in that different weights are assigned to each the feature of SMV. The performance of the proposed approach is evaluated under various conditions and yields better results compared with the conventional scheme in the SVM.

• Journal of the Ergonomics Society of Korea
• /
• v.10 no.1
• /
• pp.3-10
• /
• 1991

The teach pendant and keyboard have been used as an input device of control command in human-robot sustem. But, many problems occur in case that the usef is a novice. So, speech recognition system is required to communicate between a human and the robot. In this study, Korean voice commands, eitht robot commands, and ten digits based on the broad phonetic analysis are described. Applying broad phonetic analysis, phonemes of voice commands are divided into phoneme groups, such as plosive, fricative, affricative, nasal, and glide sound, having similar features. And then, the feature parameters and their ranges to detect phoneme groups are found by minimax method. Classification rules are consisted of combination of the feature parameters, such as zero corssing rate(ZCR), log engery(LE), up and down(UD), formant frequency, and their ranges. Voice commands were recognized by the classification rules. The recognition rate was over 90 percent in this experiment. Also, this experiment showed that the recognition rate about digits was better than that about robot commands.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1995.10b
• /
• pp.85-91
• /
• 1995

This paper presents a system which recognizes the Korean Sign Language(KSL) and translates into normal Korean speech. A sign language is a method of communication for the deaf-mute who uses gestures, especially both hands and fingers. Since the human hands and fingers are not the same in physical dimension, the same form of a gesture produced by two signers with their hands may not produce the same numerical values when obtained through electronic sensors. In this paper, we propose a dynamic gesture recognition method based on feature analysis for efficient classification of hand motions, and on a fuzzy min-max neural network for on-line pattern recognition.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.3
• /
• pp.293-303
• /
• 2002

This paper implements optimized Time Scale Modification (TSM) system using ITU G.729 speech decoder and Dual SOLA algorithm. The proposed system assume 8 Kz sampling rate, 80 samples/frame input speech from the ITU G.729 speech Decoder and the TSM (Time Scale Modification) feature of Dual SOLA produces the high quality output speech that was slow-down or speed up as a user's choice. Especially, the proposed Optimized Dual SOLA base on various simulations and theoretical analysis, and the additional interpolation procedure of the speech makes it possible to setup high performance integrated TSM system at the maximum time scale modification rate. The system performance is analyzed and verified with various input speech and playback speed.

• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.1
• /
• pp.59-64
• /
• 2015

In this paper, we found the usefulness of the deep belief network (DBN) in the fields of brain-computer interface (BCI), especially in relation to imagined speech. In recent years, the growth of interest in the BCI field has led to the development of a number of useful applications, such as robot control, game interfaces, exoskeleton limbs, and so on. However, while imagined speech, which could be used for communication or military purpose devices, is one of the most exciting BCI applications, there are some problems in implementing the system. In the previous paper, we already handled some of the issues of imagined speech when using the International Phonetic Alphabet (IPA), although it required complementation for multi class classification problems. In view of this point, this paper could provide a suitable solution for vowel classification for imagined speech. We used the DBN algorithm, which is known as a deep learning algorithm for multi-class vowel classification, and selected four vowel pronunciations:, /a/, /i/, /o/, /u/ from IPA. For the experiment, we obtained the required 32 channel raw electroencephalogram (EEG) data from three male subjects, and electrodes were placed on the scalp of the frontal lobe and both temporal lobes which are related to thinking and verbal function. Eigenvalues of the covariance matrix of the EEG data were used as the feature vector of each vowel. In the analysis, we provided the classification results of the back propagation artificial neural network (BP-ANN) for making a comparison with DBN. As a result, the classification results from the BP-ANN were 52.04%, and the DBN was 87.96%. This means the DBN showed 35.92% better classification results in multi class imagined speech classification. In addition, the DBN spent much less time in whole computation time. In conclusion, the DBN algorithm is efficient in BCI system implementation.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.5
• /
• pp.461-467
• /
• 2020

In noisy and multi-speaker environments, the performance of speech recognition is unavoidably lower than in a clean environment. To improve speech recognition, in this paper, the signal of the speaker of interest is extracted from the mixed speech signals with multiple speakers. The VoiceFilter model is used to effectively separate overlapped speech signals. In this work, clustering by Probabilistic Linear Discriminant Analysis (PLDA) similarity score was employed to detect the speech signal of the interested speaker, which is used as the reference speaker to VoiceFilter-based separation. Therefore, by utilizing the speaker feature extracted from the detected speech by the proposed clustering method, this paper propose a speaker diarization system using only the mixed speech without an explicit reference speaker signal. We use phone-dataset consisting of two speakers to evaluate the performance of the speaker diarization system. Source to Distortion Ratio (SDR) of the operator (Rx) speech and customer speech (Tx) are 5.22 dB and -5.22 dB respectively before separation, and the results of the proposed separation system show 11.26 dB and 8.53 dB respectively.

• The KIPS Transactions:PartB
• /
• v.15B no.2
• /
• pp.123-130
• /
• 2008

Automatic lipreading is to recognize speech by observing the movement of a speaker's lips. It has received attention recently as a method of complementing performance degradation of acoustic speech recognition in acoustically noisy environments. One of the important issues in automatic lipreading is to define and extract salient features from the recorded images. In this paper, we propose a feature extraction method by using a new filtering technique for obtaining improved recognition performance. The proposed method eliminates frequency components which are too slow or too fast compared to the relevant speech information by applying a band-pass filter to the temporal trajectory of each pixel in the images containing the lip region and, then, features are extracted by principal component analysis. We show that the proposed method produces improved performance in both clean and visually noisy conditions via speaker-independent recognition experiments.

• Journal of the Institute of Electronics Engineers of Korea TE
• /
• v.37 no.5
• /
• pp.62-70
• /
• 2000

In this study, speech recognition for Korean digit is performed using filter bank which is programmed discrete HMM and DTW. Spectral analysis reveals speech signal features which are mainly due to the shape of the vocal tract. And spectral feature of speech are generally obtained as the exit of filter banks, which properly integrated a spectrum at defined frequency ranges. A set of 8 band pass filters is generally used since it simulates human ear processing. And defined frequency ranges are 320-330, 450-460, 640-650, 840-850, 900-1000, 1100-1200, 2000-2100, 3900-4000Hz and then sampled at 8kHz of sampling rate. Frame width is 20ms and period is 10ms. Accordingly, we found that the recognition rate of DTW is better than HMM for Korean digit speech in the experimental result. Recognition accuracy of Korean digit speech using filter bank is 93.3% for the 24th BPF, 89.1% for the 16th BPF and 88.9% for the 8th BPF of hardware realization of voice dialing system.

• The Journal of the Acoustical Society of Korea
• /
• v.24 no.1E
• /
• pp.16-20
• /
• 2005

A novel scheme to measure the speaker information in speech signal is proposed. We develope the theory of quantitative measurement of the speaker characteristics in the information theoretic point of view, and connect it to the classification error rate. Homomorphic analysis based features, such as mel frequency cepstral coefficient (MFCC), linear prediction cepstral coefficient (LPCC), and linear frequency cepstral coefficient (LFCC) are studied to measure speaker specific information contained in those feature sets by computing mutual information. Theories and experimental results provide us quantitative measure of speaker information in speech signal.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.30B no.2
• /
• pp.51-58
• /
• 1993

This paper describes the development of a speaker-dependent isolated word recognizer as applied to voice dialing in a car noise environment. for this purpose, several methods to improve performance under such condition are evaluated using database collected in a small car moving at 100km/h The main features of the recognizer are as follow: The endpoint detection error can be reduced by using the magnitude of the signal which is inverse filtered by the AR model of the background noise, and it can be compensated by using variants of the DTW algorithm. To remove the noise, an autocorrelation subtraction method is used with the constraint that residual energy obtainable by linear predictive analysis should be positive. By using the noise rubust distance measure, distortion of the feature vector is minimized. The speech recognizer is implemented using the Motorola DSP56001(24-bit general purpose digital signal processor). The recognition database is composed of 50 Korean names spoken by 3 male speakers. The recognition error rate of the system is reduced to 4.3% using a single reference pattern for each word and 1.5% using 2 reference patterns for each word.