• 음성과학
• /
• 제10권2호
• /
• pp.27-33
• /
• 2003

Bimodal speech recognition based on lip reading has been studied as a representative method of speech recognition under noisy environments. There are three integration methods of speech and lip modalities as like direct identification, separate identification and dominant recording. In this paper we evaluate the robustness of lip reading methods under the assumption that lip parameters are estimated with errors. We show that the dominant recording approach is more robust than other methods through lip reading experiments.

• 대한음성학회지:말소리
• /
• 제43호
• /
• pp.179-188
• /
• 2002

Improving the recognition performance of connected digit telephone speech still remains a problem to be solved. As a basic study for it, this paper analyzes the variation of feature parameters of Korean digit telephone speech according to channel distortion. As a feature parameter for analysis and recognition MFCC is used. To analyze the effect of telephone channel distortion depending on each call, MFCCs are first obtained from the connected digit telephone speech for each phoneme included in the Korean digit. Then CMN, RTCN, and RASTA are applied to the MFCC as channel compensation techniques. Using the feature parameters of MFCC, MFCC+CMN, MFCC+RTCN, and MFCC+RASTA, variances of phonemes are analyzed and recognition experiments are done for each case. Experimental results are discussed with our findings and discussions

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2002년도 11월 학술대회지
• /
• pp.205-208
• /
• 2002

Bimodal speech recognition based on lip reading has been studied as a representative method of speech recognition under noisy environments. There are three integration methods of speech and lip modalities as like direct identification, separate identification and dominant recording. In this paper we evaluate the robustness of lip reading methods under the assumption that lip parameters are estimated with errors. We show that the dominant recording approach is more robust than other methods with lip reading experiments. Also, a measure of lip parameter degradation is proposed. This measure can be used in the determination of weighting values of video information.

• Journal of information and communication convergence engineering
• /
• 제1권4호
• /
• pp.209-212
• /
• 2003

In this paper, we proposed new speech feature parameter through parts-based feature extraction of speech spectrum using Non-Negative Matrix Factorization (NMF). NMF can effectively reduce dimension for multi-dimensional data through matrix factorization under the non-negativity constraints, and dimensionally reduced data should be presented parts-based features of input data. For speech feature extraction, we applied Mel-scaled filter bank outputs to inputs of NMF, than used outputs of NMF for inputs of speech recognizer. From recognition experiment result, we could confirm that proposed feature parameter is superior in recognition performance than mel frequency cepstral coefficient (MFCC) that is used generally.

• 음성과학
• /
• 제9권4호
• /
• pp.253-263
• /
• 2002

In this paper, we propose new algorithm of speaker recognition which identifies the speaker using the information obtained by the intensive speech feature analysis such as pitch, intensity, duration, and formant, which are crucial parameters of individual voice, for candidates of high percentage of wrong recognition in the existing speaker recognition algorithm. For testing the power of discrimination of individual parameter, DTW (Dynamic Time Warping) is used. We newly set the range of threshold which affects the power of discrimination in speech verification such that the candidates in the new range of threshold are finally discriminated in the next stage of sound parameter analysis. In the speaker verification test by using voice DB which consists of secret words of 25 males and 25 females of 8 kHz 16 bit, the algorithm we propose shows about 1% of performance improvement to the existing algorithm.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1990년도 하계학술대회 논문집
• /
• pp.47-50
• /
• 1990

Deafs cannot speak straight voice as normal people in lack of feedback of their pronunciation, therefore speech training is required. In this study, fundamental frequency, intensity, formant frequencies, vocal tract graphic and vocal tract area function, extracted from speech signal, are used as feature parameter. AR model, whose coefficients are extracted using inverse filtering. is used as speech generation model. In connect ion between vocal tract graphic and speech parameter, articulation distances and articulation distance functions in selected 15-intervals are determined by extracted vocal tract areas and formant frequencies.

• 한국음향학회지
• /
• 제4권1호
• /
• pp.9-15
• /
• 1985

In this paper, we describe a new algorithm for deciding whether a given segment of a speech signal is classified as voiced speech, unvoiced speech, or silence, based on parameters made on the signal. The measured parameters for the voiced-unvoiced classfication are the areas of each Zero crossing interval, which is given by multiplication of the magnitude by the inverse zero corssing rate of speech signals. The employed parameter for the unvoiced-silence classification, also, are each of positive area summation during four milisecond interval for the high frequency emphasized speech signals.

• 전기학회논문지
• /
• 제66권8호
• /
• pp.1265-1271
• /
• 2017

In this paper, the speech parameter fusion method is studied to improve the performance of the conventional emotion recognition system. For this purpose, the combination of the parameters that show the best performance by combining the cepstrum parameters and the various pitch parameters used in the conventional emotion recognition system are selected. Various pitch parameters were generated using numerical and statistical methods using pitch of speech. Performance evaluation was performed on the emotion recognition system using Gaussian mixture model(GMM) to select the pitch parameters that showed the best performance in combination with cepstrum parameters. As a parameter selection method, sequential feature selection method was used. In the experiment to distinguish the four emotions of normal, joy, sadness and angry, fifteen of the total 56 pitch parameters were selected and showed the best recognition performance when fused with cepstrum and delta cepstrum coefficients. This is a 48.9% reduction in the error of emotion recognition system using only pitch parameters.

• 대한전자공학회논문지
• /
• 제25권4호
• /
• pp.430-436
• /
• 1988

LSF(Line Spectral Frequency) derived from LPC has known as a very useful transmission parameter of speech signals, for it has a good linear interpolation characteristics and a low spectrum distortion at low bit rates coding. This paper presents that it is possible to extract directly the formant frequencies of speech signals from LSF parameter without application of FFT algorithm by comparing the distribution of LSF parameter with the frequency distribution of analysis filter. This paper suggests the advanced algorithm that results in improving the speed of convergence at analytic solution method. Also, for the flexibility of parameters, the process that transforms from LSF to LPC is presented.

• Journal of information and communication convergence engineering
• /
• 제1권4호
• /
• pp.205-208
• /
• 2003

Voice activity detection is a important problem in the speech recognition and speech communication. This paper introduces new feature parameter which are reconstructed by spectral entropy of information theory for robust voice activity detection in the noise environment, then analyzes and compares it with energy method of voice activity detection and performance. In experiments, we confirmed that spectral entropy and its reconstructed parameter are superior than the energy method for robust voice activity detection in the various noise environment.