• The Journal of the Acoustical Society of Korea
• /
• v.6 no.3
• /
• pp.60-67
• /
• 1987

In this paper, a phoneme classification method for Korean speech recognition has been proposed and its performance has been studied. The phoneme classification has been done based on the phonemic features extracted by the prewindowed recursive least-square (PRLS) algorithm that is a kind of adaptive filter algorithms. Applying the PRLS algorithm to input speech signal, precise detection of phoneme boundaries has been made, Reference patterns of Korean phonemes have been generated by the ordinery vector quantization (VQ) of feature vectors obtained manualy from prototype regions of each phoneme. In order to obtain the performance of the proposed phoneme classification method, the method has been tested using spoken names of seven Korean cities which have eleven different consonants and eight different vowels. In the speaker-dependent phoneme classification, the accuracy is about $85\%$ considering simple phonemic rules of Korean language, while the accuracy of the speaker-independent case is far less than that of the speaker-dependent case.

• The Journal of the Acoustical Society of Korea
• /
• v.18 no.5
• /
• pp.35-43
• /
• 1999

In this paper, a new robust adaptive algorithm and a post-processing method are proposed to improve the performance of AEC without computational burden. Its step-size is normalized by the sum of the powers of the reference input signal and the desired signal. When the near-end speaker's speech and noise are applied into the microphone, the step-size becomes small and the misalignment of coefficients are reduced. To reduce the residual echoes, a new post-processing method, which is co-operated with the proposed noise-robust adaptive algorithm, is proposed in this paper. The method is based on the correlation of the desired signal and the estimation error signal. The residual echoes are attenuated as proportional to the correlation normalized with the power of desired signals. The normalized correlation plays a role as Wiener filter for residual echoes. In the double-talk situation, the estimation error signals, that are residual echoes, dominantly include the near-end speaker's speech and the normalized correlation closes to 1. Therefore, the near-end speaker's speech can be transmitted without being attenuated. When the desired signals consists of only the acoustic echoes, the residual echoes are mostly attenuated and canceled by the proposed post-processor. The computation of AEC using the proposed post-processor is comparable to NLMS algorithm.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.1
• /
• pp.96-107
• /
• 1996

A voice personality transformation algorithm using orthogonal vector space conversion is proposed in this paper. Voice personality transformation is the process of changing one person's acoustic features (source) to those of another person (target). In this paper, personality transformation is achieved by changing the LPC cepstrum coefficients, excitation spectrum and pitch contour. An orthogonal vector space conversion technique is proposed to transform the LPC cepstrum coefficients. The LPC cepstrum transformation is implemented by principle component decomposition by applying the Karhunen-Loeve transformation and minimum mean-square error coordinate transformation(MSECT). Additionally, we propose a pitch contour modification method to transform the prosodic characteristics of any speaker. To do this, reference pitch patterns for source and target speaker are firstly built up, and speaker's one. The experimental results show the effectiveness of the proposed algorithm in both subjective and objective evaluations.

• The Journal of the Acoustical Society of Korea
• /
• v.10 no.2
• /
• pp.23-28
• /
• 1991

This paper is a study on isolated word recognition by independent speaker, we propose DTW speech recognition system by modified dynamic averaging method as reference pattern. 57 city names are selected as recognition vocabulary and 2th LPC cepstrum coefficients are used as the feature parameter. In this paper, besides recognition experiment using modified dynamic averaging method as reference pattern, we perform recognition experiments using causal method, dynamic averaging method, linear averaging method and clustering method with the same data in the same conditions for comparison with it. Through the experiment result, it is proved that recogntion rate by DTW using modified dynamic averaging method is the best as 97.6 percent.

• Journal of the Korean Society of Industry Convergence
• /
• v.20 no.4
• /
• pp.285-297
• /
• 2017

This study proposed a new approach to develop an Intelligent control algorithm for cooperative working of human and robot based on voice recognition. In general case of speaker verification, Gaussian Mixture Model is used to model the feature vectors of reference speech signals. On the other hand, Dynamic Time Warping based template matching techniques were presented for the voice recognition about several years ago. We converge these two different concepts in a single method and then implement in a real time voice recognition enough to make reference model to satisfy 95% of recognition performance. In this paper it was illustrated the reliability of voice recognition by simulation and experiments for humanoid robot with 18 joints.

• Journal of Korea Multimedia Society
• /
• v.2 no.1
• /
• pp.99-108
• /
• 1999

In this paper, a new robust adaptive algorithm is proposed to improve the performance of AEC without computational burden. The proposed adaptive algorithm is based on NLMS algorithm, and its step-size is varied with the reference input signal power and the desired signal power. Its step-size is normalized by the sum of the powers of the reference input signal and the desired signal. When the near-end speaker's speech and noise are applied into the microphone, the step-size becomes small and the misalignment of coefficients are reduced. The convergence speed is comparable to NLMS algorithm at AEC application because the echo signals are attenuated about 10∼20 dBSPL. The characteristics of this algorithm is also analyzed and compared with conventional ones in this paper.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.2
• /
• pp.280-286
• /
• 2013

In this paper, a noise reduction system is proposed for the speech interface in intelligent TV applications. To reduce TV speaker sound which are very serious noises degrading recognition performance, a noise reduction algorithm utilizing the direct TV sound as the reference noise input is implemented. In the proposed algorithm, transfer functions are estimated to compensate for the difference between the direct TV sound and that recorded with the microphone installed on the TV frame. Then, the noise power spectrum in the received signal is calculated to perform Wiener filter-based noise cancellation. Additionally, a postprocessing step is applied to reduce remaining noises. Experimental results show that the proposed algorithm shows 88% recognition rate for isolated Korean words at 5 dB input SNR.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.19 no.3
• /
• pp.288-293
• /
• 2009

This study presents the active noise control of duct noise. The duct was excited by a steady-state harmonic and white noise force and the control was performed by one control speaker attached to surface of the duct. An adaptive controller based on filtered x LMS(FXLMS) algorithm was used and controller was defined by minimizing the square of the response of the error microphone. The assemble controller, which is called a hybrid ANC(active noise control) system, was combined with feedforward and feedback controller. The feedforward ANC attenuates primary noise that is correlated with the reference signal, while the feedback ANC cancels the narrowband components of the primary noise that are not observed by the reference sensor. Furthermore, in many ANC applications, the periodic components of noise are the most intense and the feedback ANC system has the effect of reducing the spectral peaks of the primary noise, thus easing the burden of the feedforward ANC filter.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.2 no.6
• /
• pp.29-37
• /
• 1994

Active noise control of random noise which propatate in the vehicle cabin as a form of spherical wave is the target of this study. In the previous study, the adaptive algorithm for adaptive controller is presented for the application in active noise control system. And for the preliminary study of adaptive active noise control in vehicle cabin as a real system, a computer simulation is performed on the effectiveness of the adaptive algorithm in the amplitude of the pressure fluctuation. This work studies the implementation of multi-channel feedforward adaptive algorithm for the reduction of the noise inside a vehicle cabin using a number of secondary sources derived by adaptive filtering of reference noise source. Multi-channel adaptive feedforward algorithm are verified in numerical simulation and semi-experimental justification of developed system is made on a domestic passenger car. In the results of semi-experimental study, the noise of specific region in the interior of automobile are reduced for the appreciabe sound pressure level in the operating engine rpm and finally this study suggests the capabilities of the real time active noise control in 3 dimensional acoustic fields.

• Phonetics and Speech Sciences
• /
• v.1 no.2
• /
• pp.75-84
• /
• 2009

The aim of this paper is to find an adequate method to study declination in Korean. In previous studies of declination in Korean, maximum and minimum pitch values in an accentual phrase were measured. But this method is inadequate when an accentual phrase is located at the intonational phrase. So in order to exclude the final tone of an intonational phrase, we propose to measure pitch values of the first and second tone in an accentual phrase when the tonal pattern of the accentual phrase is 'LHLH'. In this case, the line that connects every first tone of an accentual phrase is the baseline, and the line that connects every second tone of an accentual phrase is the topline. By a comparison of declination between focused and neutral utterances, we will show that the topline of declination is more direct to the speaker's plan than the baseline.