• The Journal of the Acoustical Society of Korea
• /
• v.14 no.5
• /
• pp.51-57
• /
• 1995

In this paper, we study a noise-robust feature extraction method of speech signal based on auditory modeling. The auditory model consists of a basilar membrane, a hair cell model and spectrum output stage. Basilar membrane model describes a response characteristic of membrane according to vibration in speech wave, and is represented as a band-pass filter bank. Hair cell model describes a neural transduction according to displacements of the basilar membrane. It responds adaptively to relative values of input and plays an important role for noise-robustness. Spectrum output stage constructs a mean rate spectrum using the average firing rate of each channel. And we extract feature vectors using a mean rate spectrum. Simulation results show that when auditory-based feature extraction is used, the speech recognition performance in noisy environments is improved compared to other feature extraction methods.

• Journal of Korea Society of Industrial Information Systems
• /
• v.7 no.3
• /
• pp.9-14
• /
• 2002

In this paper we propose a method for performance enhancement of speech recognizer under noisy conditions. The parallel combination model which is presented at the PMC method using multiple Gaussian-distributed mixtures have been adapted to the variation of each mixture. The CDHMM(continuous observation density HMM) which has multiple Gaussian distributed mixtures are combined by the proposed PMC method. Also, the EM(expectation maximization) algorithm is used for adapting the model mean parameter in order to reduce the variation of the mixture density. The result of simulation, the proposed PMC adaptation method show better performance than the conventional PMC method.

• Journal of Advanced Marine Engineering and Technology
• /
• v.32 no.5
• /
• pp.768-774
• /
• 2008

In many areas of speech signal processing such as automatic speech recognition and packet based voice communication technique, VAD (voice activity detection) plays an important role in the performance of the overall system. In this paper, we present a new feature parameter for VAD which is the product of energy of the signal and the difference of two types of entropies. For this end, we first define a Mel filter-bank based entropy and calculate its difference from the conventional entropy in frequency domain. The difference is then multiplied by the spectral energy of the signal to yield the final feature parameter which we call PEED (product of energy and entropy difference). Through experiments. we could verify that the proposed VAD parameter is more efficient than the conventional spectral entropy based parameter in various SNRs and noisy environments.

• Speech Sciences
• /
• v.15 no.1
• /
• pp.75-83
• /
• 2008

The interior of an automobile is a very noisy environment with both stationary cruising noise and the reverberated music or speech coming out from the audio system. For robust speech recognition in a car environment, it is necessary to extract a driver's voice command well by removing those background noises. Since we can handle the music and speech signals from an audio system in a car, the reverberated music and speech sounds can be removed using an acoustic echo canceller. In this paper, we implement an acoustic echo canceller with robust double-talk detection algorithm using TMS-320C6711 DSK. First we developed the echo canceller on the PC for verifying the performance of echo cancellation, then implemented it on the TMS320C6711 DSK. For processing of one speech sample with 8kHz sampling rate and 256 filter taps of the echo canceller, the implemented system used only 0.035ms and achieved the ERLE of 20.73dB.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.38 no.3
• /
• pp.61-67
• /
• 2001

In this paper, a method that apply LP algorithm to image for speech recognition is suggested, using both speech and image information for recogniton of korean numeral speech. The input speech signal is pre-emphasized with parameter value 0.95, analyzed for B th LP coefficients using Hamming window, autocorrelation and Levinson-Durbin algorithm. Also, a gray image signal is analyzed for 2-dimensional LP coefficients using autocorrelation and Levinson-Durbin algorithm like speech. These parameters are used for input parameters of neural network using back-propagation algorithm. The recognition experiment was carried out at each noise level, three numeral speechs, '3','5', and '9' were enhanced. Thus, in case of recognizing speech with 2-dimensional LP parameters, it results in a high recognition rate, a low parameter size, and a simple algorithm with no additional feature extraction algorithm.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2006.05a
• /
• pp.481-484
• /
• 2006

Pitch period detection algorithms are applied to various speech signal processing fields such as speech recognition, speaker identification, speech analysis and synthesis. Furthermore, many pitch detection algorithms of time and frequency domain have been studied until now. AMDF(average magnitude difference function) ,which is one of pitch period detection algorithms, chooses a time interval from the valley point to the valley point as the pitch period. AMDF has a fast computation capacity, but in selection of valley point to detect pitch period, complexity of the algorithm is increased. In order to apply pitch period detection algorithms to the real world, they have robust prosperities against generated noise in the subway environment etc. In this paper we proposed the modified AMDF algorithm which detects the global minimum valley point as the pitch period of speech signals and used speech signals of noisy environments as test signals.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.5
• /
• pp.555-567
• /
• 2019

Speech recognition rate is lowered even in a noisy environment, and it is difficult for a person with a speech disability or an inconvenient language to use it in a social life. In addition to improving the inconvenience of using the language, 280 words were selected using the word selection method which was improved when the word was selected considering the pronunciation characteristics of the language impaired. The MEMS development device used in the experiment was made considering material, lead wire type, length and direction. We improved the speech recognition rate by using the developed word selection method and the MEMS device developed to improve the speech recognition rate due to incorrect pronunciation and severe noise. The new method of selecting words and the mems device were improved and the results were included.

• The Journal of the Acoustical Society of Korea
• /
• v.29 no.4
• /
• pp.278-285
• /
• 2010

The difference between training and test environments is one of the major performance degradation factors in noisy speech recognition and many silence feature normalization methods were proposed to solve this inconsistency. Conventional silence feature normalization method represents higher classification performance in higher SNR, but it has a problem of performance degradation in low SNR due to the low accuracy of speech/silence classification. On the other hand, cepstral distance represents well the characteristic distribution of speech/silence (or noise) in low SNR. In this paper, we propose a Cepstral distance and Log-energy based Silence Feature Normalization (CLSFN) method which uses both log-energy and cepstral euclidean distance to classify speech/silence for better performance. Because the proposed method reflects both the merit of log energy being less affected with noise in high SNR and the merit of cepstral distance having high discrimination accuracy for speech/silence classification in low SNR, the classification accuracy will be considered to be improved. The experimental results showed that our proposed CLSFN presented the improved recognition performances comparing with the conventional SFN-I/II and CSFN methods in all kinds of noisy environments.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.05a
• /
• pp.711-714
• /
• 2009

잡음환경 하의 회화에서 잡음량을 줄이고 신호처리 시스템의 성능을 향상시키기 위해서는 잡음량에 따라서 적응적으로 처리되는 신호처리 시스템이 필요하다. 또한 잡음이 중첩된 음성으로부터 잡음을 제거하기 위해서는 잡음의 크기에 따라서 음성 처리 시스템의 파라미터를 변경하는 것이 양호한 음질의 음성을 재생하는데 바람직하다. 따라서 본 논문에서는 음성 속에 포함되는 잡음량을 인식하는 방법으로 선형예측계수를 구하여 시간지연신경회로망(Time-delay neural network: TDNN)의 입력으로 사용하여 학습시키는 잡음량을 인식하는 방법을 제안한다. 본 잡음량 인식은 다양한 배경잡음에 의하여 열화된 3종류의 음성이 TDNN에 의하여 학습되어진다. 본 실험에서는 Aurora2 데이터베이스를 사용하여 여러 잡음에 대하여 양호한 인식결과를 확인할 수 있었다.

• Journal of KIISE:Software and Applications
• /
• v.31 no.4
• /
• pp.403-410
• /
• 2004

Bimodal speech recognition systems have been proposed for enhancing recognition rate of ASR under noisy environments. Visual feature extraction is very important to develop these systems. To extract visual features, it is necessary to detect exact lip position. This paper proposed the method that detects a lip position using color similarity model and SVM. Face/Lip color distribution is teamed and the initial lip position is found by using that. The exact lip position is detected by scanning neighbor area with SVM. By experiments, it is shown that this method detects lip position exactly and fast.