• Journal of Korea Multimedia Society
• /
• v.14 no.10
• /
• pp.1221-1228
• /
• 2011

The speech recognition system works well in general indoor environment. However, the recognition performance is dramatically decreased when the system is used in the real environment because of the several noises. In this paper we proposed CSFN-CMVN to improve the recognition performance of the existing CSFN(Cepstral distance based SFN). The CSFN-CMVN method is a combined method of cepstral normalization with CSFN that normalizes silence features using cepstral euclidean distance to classify speech/silence for better performance. From the test results using Aurora 2.0 DB, we could find out that our proposed CSFN-CMVN improves about 7% of more average word accuracy in all the test sets comparing with the typical silence features normalization SFN-I. We can also get improved accuracy of 6% and 5% respectively in compared tests with the conventional SFN-II and CSFN, showing the effectiveness of our proposed method.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.6
• /
• pp.655-660
• /
• 2005

This paper studied the feature parameters less affected by the emotional variation for the development of the robust speech recognition technologies. For this purpose, the effect of emotional variation on the speech recognition system and robust feature parameters of speech recognition system were studied using speech database containing various emotions. In this study, LPC cepstral coefficient, met-cepstral coefficient, root-cepstral coefficient, PLP coefficient, RASTA met-cepstral coefficient were used as a feature parameters. And CMS and SBR method were used as a signal bias removal techniques. Experimental results showed that the HMM based speaker independent word recognizer using RASTA met-cepstral coefficient :md its derivatives and CMS as a signal bias removal showed the best performance of $7.05\%$ word error rate. This corresponds to about a $52\%$ word error reduction as compare to the performance of baseline system using met - cepstral coefficient.

• The Journal of the Acoustical Society of Korea
• /
• v.29 no.4
• /
• pp.243-250
• /
• 2010

This paper proposes a spectral modeling of Korean traditional instrument, Haegeum, using cepstral analysis to naturally describe Haegeum sounds varying with time. To get a precise result of cepstral analysis, we set the frame size to 3 periods of input signal and more cepstral coefficients are used to extract formants. The performance is enhanced by flexibly controlling the cutoff frequency of bandpass filter depending on the resonances in the synthesis process of sinusoidal components and the deleting peaks remained in the residual signal. To detect the change of pitch, we divide the input frames into silence, attack, and sustain region and determine which region the current frame is involved in. Then, the proposed method readjusts the frame size according to the fundamental frequency in the case of the current frame is in attack region and corrects the extraction errors of the fundamental frequency for the frames in sustain region. With these processes, the synthesized sounds are much more similar to the originals. The evaluation result through the listening test by a Haegeum player says that the synthesized sounds are almost similar to originals (96~100 % similar to the original sounds).

• The Journal of the Acoustical Society of Korea
• /
• v.18 no.5
• /
• pp.12-20
• /
• 1999

In this paper, we compared speaker verification performance of the speech data collected in clean environment and in channel environment. For the improvement of the performance of speaker verification gathered in channel, we have studied on the efficient feature parameters in channel environment and on the preprocessing. Speech DB for experiment is consisted of Korean doublet of numbers, considering the text-prompted system. Speech features including LPCC(Linear Predictive Cepstral Coefficient), MFCC(Mel Frequency Cepstral Coefficient), PLP(Perceptually Linear Prediction), LSP(Line Spectrum Pair) are analyzed. Also, the preprocessing of filtering to remove channel noise is studied. To remove or compensate for the channel effect from the extracted features, cepstral weighting, CMS(Cepstral Mean Subtraction), RASTA(RelAtive SpecTrAl) are applied. Also by presenting the speech recognition performance on each features and the processing, we compared speech recognition performance and speaker verification performance. For the evaluation of the applied speech features and processing methods, HTK(HMM Tool Kit) 2.0 is used. Giving different threshold according to male or female speaker, we compare EER(Equal Error Rate) on the clean speech data and channel data. Our simulation results show that, removing low band and high band channel noise by applying band pass filter(150～3800Hz) in preprocessing procedure, and extracting MFCC from the filtered speech, the best speaker verification performance was achieved from the view point of EER measurement.

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.4
• /
• pp.57-63
• /
• 1997

In this paper, we study the efficient feature vector extraction method and front-end processing to improve the performance of the speech recognition system using KT(Korea Telecommunication) database collected through various telephone channels. First of all, we compare the recognition performances of the feature vectors known to be robust to noise and environmental variation and verify the performance enhancement of the recognition system using weighted cepstral distance measure methods. The experiment result shows that the recognition rate is increasedby using both PLP(Perceptual Linear Prediction) and MFCC(Mel Frequency Cepstral Coefficient) in comparison with LPC cepstrum used in KT recognition system. In cepstral distance measure, the weighted cepstral distance measure functions such as RPS(Root Power Sums) and BPL(Band-Pass Lifter) help the recognition enhancement. The application of the spectral subtraction method decrease the recognition rate because of the effect of distortion. However, RASTA(RelAtive SpecTrAl) processing, CMS(Cepstral Mean Subtraction) and SBR(Signal Bias Removal) enhance the recognition performance. Especially, the CMS method is simple but shows high recognition enhancement. Finally, the performances of the modified methods for the real-time implementation of CMS are compared and the improved method is suggested to prevent the performance degradation.

• 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.

• Korean Journal of Optics and Photonics
• /
• v.15 no.2
• /
• pp.123-129
• /
• 2004

This paper concerns auto vergence control of a parallel stereoscopic camera through geometrical analysis. In the construction of a parallel stereoscopic camera, we experimentally demonstrated linear relationship between the key object distance and the amount of vergence control. And we proposed a vergence control system for the stereoscopic camera using binocular disparity information. For the real-time calculation of disparity information, the Hybrid Cepstral filter algorithm, with input data acquired from the vertical projection data and from the down sampling data from the source images, was proposed for precision and high speed processing. With the disparity information algorithm and the vergence control of the parallel stereoscopic camera system, the stereoscopic images become more like those of the human eye.

• Speech Sciences
• /
• v.6
• /
• pp.163-179
• /
• 1999

For the set up, management and repair of a mobile communication system, continuous estimation of speech quality is required. Speech quality measurement can be conducted by listener's judgement in a subjective test such as MOS (Mean Opinion Score) test. However, this method is laborious, expensive and time-consuming, it is advisable to predict subjective speech quality via objective measures. This paper presents a robust objective speech quality measure, PLP-CMS (Perceptual Linear Predictive-Cepstral Mean Subtraction), which can predict subjective speech quality in mobile communication systems. PLP-CMS has a high correlation with subjective quality owing to PLP (Perceptual Linear Predictive) analysis and shows a robust performance not being influenced by PSTN (Public Switched Telephone Network) channel effects due to CMS (Cepstral Mean Subtraction). To prove the performance of our proposed algorithm, we carried out subjective and objective quality estimation on speech samples which are variously distorted in a real mobile communication system. As a result, we demonstrated that PLP-CMS has a higher correlation with subjective quality than PSQM (Perceptual Speech Quality Measure) and PLP-CD (Perceptual Linear Predictive-Cepstral Distance).

• The Journal of the Acoustical Society of Korea
• /
• v.13 no.1E
• /
• pp.71-81
• /
• 1994

In this paper, we propose a pseudo-cepstral representation of line spectrum pair(LSP) frequencies and evaluate speech recognition performance with cepstral lift using the pseudo-cepstrum. The pseudo-cepstrum corresponding to LSP frequencies is derived by approxmating the relationship between LPC-cepstrum and LSP frequencies. Three cepstral liftering procedures are applied to the pseudo-cepstrum to improve the performance of speech recognition. They are the root-power-sums ligter, the general exponential lifter, and the bandpass lifter. Then, the liftered psedudo-cepstra are warped into a mel-frequency scale to obtain feature vectors for speech recognition. Among the three lifters, the general exponential lifter results in the best performance on speech recognition. When we use the proposed pseudo-cepstra feature vectors for recognizing noisy speech, the signal-to-noise ratio (SNR) improvement of about 5~10dB LSP is obtained.

• Phonetics and Speech Sciences
• /
• v.8 no.2
• /
• pp.73-80
• /
• 2016

The purpose of this study was to analyze perceptual and spectral/cepstral measurements in patients with adductor spasmodic dysphonia(ADSD). Sixty participants with gender and age matched individuals(30 ADSD and 30 controls) were recorded in reading a sentence and sustained the vowel /a/. Acoustic data were analyzed acoustically by measuring CPP, L/H ratio, mean CPP F0 and CSID, and auditory-perceptual ratings were measured using GRBAS. The main results can be summarized as below: (a) the CSID for the connected speech was significantly higher than for the sustained vowel (b) the G, R and S for the connected speech were significantly higher than for the sustained vowel (c) Spectral/cepstral parameters were significantly correlated with the perceptual parameters, and (d) the ROC analysis showed that the threshold of 13.491 for the CSID achieved a good classification for ADSD, with 86.7% sensitivity and 96.7% specificity. Spectral and cepstral analysis for the connected speech is especially meaningful on cases where perceptual analysis and clinical evaluation alone are insufficient.