• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.49 no.3
• /
• pp.81-88
• /
• 2012

In this paper, we propose a novel speech enhancement algorithm for effective noise suppression in various noisy environments. In the proposed method, to result in improved decision performance for speech and noise segments, local speech absence probability (LSAP, local SAP) based on Teager energy of noisy speech is used as the feature parameter for voice activity detection (VAD) in each frequency subband instead of conventional LSAP. In addition, The presented method utilizes global SAP (GSAP) derived in each frame as the weighting parameter for the modification of the adopted TE operator to improve the performance of TE operator. Performances of the proposed algorithm are evaluated by objective test under various environments and better results compared with the conventional methods are obtained.

• Proceedings of the IEEK Conference
• /
• 2002.07a
• /
• pp.690-693
• /
• 2002

According to the growth of communication biz, embedded market rapidly developing in domestic and overseas. Embedded system can be used in various way such as wire and wireless communication equipment or information products. There are lots of developing performance applying speech recognition to embedded system, for instance, PDA, PCS, CDMA-2000 or IMT-2000. This study implement minimum memory of speech recognition engine and DB for apply real time embedded system. The implement measure of speech recognition equipment to fit on embedded system is like following. At first, DC element is removed from Input voice and then a compensation of high frequency was achieved by pre-emphasis with coefficients value, 0.97 and constitute division data as same size as 256 sample by lapped shift method. Through by Levinson - Durbin Algorithm, these data can get linear predictive coefficient and again, using Cepstrum - Transformer attain feature vectors. During HMM training, We used Baum-Welch reestimation Algorithm for each words training and can get the recognition result from executed likelihood method on each words. The used speech data is using 40 speech command data and 10 digits extracted form each 15 of male and female speaker spoken menu control command of Embedded system. Since, in many times, ARM CPU is adopted in embedded system, it's peformed porting the speech recognition engine on ARM core evaluation board. And do the recognition test with select set 1 and set 3 parameter that has good recognition rate on commander and no digit after the several tests using by 5 proposal recognition parameter sets. The recognition engine of recognition rate shows 95%, speech commander recognizer shows 96% and digits recognizer shows 94%.

• 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.

• The Journal of the Acoustical Society of Korea
• /
• v.26 no.5
• /
• pp.207-213
• /
• 2007

In this research, we propose an efficient Speech/Music discrimination method that uses spectrum analysis and neural network. The proposed method extracts the duration feature parameter(MSDF) from a spectral peak track by analyzing the spectrum, and it was used as a feature for Speech/Music discriminator combined with the MFSC. The neural network was used as a Speech/Music discriminator, and we have reformed various experiments to evaluate the proposed method according to the training pattern selection, size and neural network architecture. From the results of Speech/Music discrimination, we found performance improvement and stability according to the training pattern selection and model composition in comparison to previous method. The MSDF and MFSC are used as a feature parameter which is over 50 seconds of training pattern, a discrimination rate of 94.97% for speech and 92.38% for music. Finally, we have achieved performance improvement 1.25% for speech and 1.69% for music compares to the use of MFSC.

• The Journal of the Acoustical Society of Korea
• /
• v.14 no.3
• /
• pp.49-60
• /
• 1995

This paper is a study on the design and implementation of the Korean Text-to-Speech system which is used for a small and simple system. In this paper, a parameter synthesis method is chosen for speech syntheiss method, we use PARCOR(PARtial autoCORrelation) coefficient which is one of the LPC analysis. And we use phoneme for synthesis unit which is the basic unit for speech synthesis. We use PARCOR, pitch, amplitude as synthesis parameter of voice, we use residual signal, PARCOR coefficients as synthesis parameter of unvoice. In this paper, we could obtain the 60% intelligibility by using the residual signal as excitation signal of unvoiced sound. The result of synthesis experiment, synthesis of a word unit is available. The controlling of phoneme duration is necessary for synthesizing of a sentence unit. For setting up the synthesis system, PC 486, a 70[Hz]-4.5[KHz] band pass filter for speech input/output, amplifier, and TMS320C30 DSP board was used.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38C no.2
• /
• pp.213-218
• /
• 2013

One of the most popular approaches to parameter adaptation in hidden Markov model (HMM) based systems is the maximum likelihood linear regression (MLLR) technique. In our previous study, we proposed factored MLLR (FMLLR) where each MLLR parameter is defined as a function of a control vector. We presented a method to train the FMLLR parameters based on a general framework of the expectation-maximization (EM) algorithm. Using the proposed algorithm, supplementary information which cannot be included in the models is effectively reflected in the adaptation process. In this paper, we apply the FMLLR algorithm to a pitch sequence as well as spectrum parameters. In a series of experiments on artificial generation of expressive speech, we evaluate the performance of the FMLLR technique and also compare with other approaches to parameter adaptation in HMM-based speech synthesis.

• The Journal of the Acoustical Society of Korea
• /
• v.14 no.3
• /
• pp.90-96
• /
• 1995

A new method for autoregressive parameter estimation from noisy observation sequence is presented. This method, termed the AP method, is a result of an attempt to make use of the adaptive predictor which is a simple and reliable way of parameter estimation. It is shown theoretically that, for noisy input, the parameter vector computed from the prediction sequence is closer to that of the original sequence than the noisy input sequence is, under the spectral distortion criterion. Simulation results with the Kalman filter as a noise reduction filter and real speech data supported the theory. Roughly speaking, the performance of the parameter set obtained by the AP method is better than noisy one but worse than the EM iteration results. When the simplicity is considered, it could provide a useful alternative to more complicated parameter estimation methods in some applications.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• v.9 no.2
• /
• pp.473-476
• /
• 2005

This paper is proposed a robust various feature parameters in noise. Feature parameter MFCC(Mel Frequency Cepstral Coefficient) used in conventional speech recognition shows good performance. But, parameter transformed feature space that uses PCA(Principal Component Analysis)and ICA(Independent Component Analysis) that is algorithm transformed parameter MFCC's feature space that use in old for more robust performance in noise is compared with the conventional parameter MFCC's performance. The result shows more superior performance than parameter and MFCC that feature parameter transformed by the result ICA is transformed by PCA.

• MALSORI
• /
• no.65
• /
• pp.81-91
• /
• 2008

In this paper, we propose a new variable bit-rate speech coder based on the waveform interpolation concept. After the coder extracted all parameters, the amounts of the distortions between the current and the predicted parameters which are estimated by extrapolation using past two parameters are measured for all parameters. A parameter would not be transmitted unless the distortion exceeds the preset threshold. At the decoder side, the non-transmitted parameter is reconstructed by extrapolation with past two parameters used to synthesize signals. In this way, we can reduce 26% of the total bit rate while retaining the speech quality degradation below 0.1 PESQ score.

• Phonetics and Speech Sciences
• /
• v.15 no.2
• /
• pp.53-59
• /
• 2023

Detection of children with autism spectrum disorder (ASD) based on speech has relied on predefined feature sets due to their ease of use and the capabilities of speech analysis. However, clinical impressions may not be adequately captured due to the broad range and the large number of features included. This paper demonstrates that the knowledge-driven speech features (KDSFs) specifically tailored to the speech traits of ASD are more effective and efficient for detecting speech of ASD children from that of children with typical development (TD) than a predefined feature set, extended Geneva Minimalistic Acoustic Standard Parameter Set (eGeMAPS). The KDSFs encompass various speech characteristics related to frequency, voice quality, speech rate, and spectral features, that have been identified as corresponding to certain of their distinctive attributes of them. The speech dataset used for the experiments consists of 63 ASD children and 9 TD children. To alleviate the imbalance in the number of training utterances, a data augmentation technique was applied to TD children's utterances. The support vector machine (SVM) classifier trained with the KDSFs achieved an accuracy of 91.25%, surpassing the 88.08% obtained using the predefined set. This result underscores the importance of incorporating domain knowledge in the development of speech technologies for individuals with disorders.