• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.12
• /
• pp.2793-2799
• /
• 2013

This paper proposes an effective feature compensation method to improve speech recognition performance in time-varying background noise condition. The proposed method employs principal component analysis to improve the variational model composition method. The proposed method is employed to generate multiple environmental models for the PCGMM-based feature compensation scheme. Experimental results prove that the proposed scheme is more effective at improving speech recognition accuracy in various SNR conditions of background music, compared to the conventional front-end methods. It shows 12.14% of average relative improvement in WER compared to the previous variational model composition method.

• Proceedings of the KSPS conference
• /
• 2003.10a
• /
• pp.149-152
• /
• 2003

In this paper, data-driven temporal filter methods[1] are investigated for robust feature extraction. A principal component analysis technique is applied to the time trajectories of feature sequences of training speech data to get appropriate temporal filters. We did recognition experiments on the Korean connected digit telephone speech database released by SITEC, with data-driven temporal filters. Experimental results are discussed with our findings.

• Phonetics and Speech Sciences
• /
• v.3 no.2
• /
• pp.71-78
• /
• 2011

In this paper, we propose an approach which constructs classifier ensembles of various channel compensation and feature enhancement methods. CMN and CMVN are used as channel compensation methods. PCA, kernel PCA, greedy kernel PCA, and kernel multimodal discriminant analysis are used as feature enhancement methods. The proposed ensemble system is constructed with the combination of 15 classifiers which include three channel compensation methods (including 'without compensation') and five feature enhancement methods (including 'without enhancement'). Experimental results show that the proposed ensemble system gives highest average speaker identification rate in various environments (channels, noises, and sessions).

• Phonetics and Speech Sciences
• /
• v.6 no.4
• /
• pp.79-90
• /
• 2014

An intonation curve stylization was used for an acoustical analysis of English speech. For the analysis, acoustical feature values were extracted from 1,848 utterances produced with normal and fast speech rate by 28 (12 women and 16 men) native speakers of English. Men are found to speak faster than women at normal speech rate but no difference is found between genders at fast speech rate. Analysis of pitch point features has it that fast speech has greater Pt (pitch point movement time), Pr (pitch point pitch range), and Pd (pitch point distance) but smaller Ps (pitch point slope) than normal speech. Men show greater Pt, Pr, and Pd than women. Analysis of sentence level features reveals that fast speech has smaller Sr (sentence level pitch range), Sd (sentence duration), and Max (maximum pitch) but greater Ss (sentence slope) than normal speech. Women show greater Sr, Ss, Sp (pitch difference between the first pitch point and the last), Sd, MaxNr (normalized Max), and MinNr (normalized Min) than men. As speech rate increases, women speak with greater Ss and Sr than men.

• 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.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2013.05a
• /
• pp.1443-1444
• /
• 2013

• Phonetics and Speech Sciences
• /
• v.7 no.4
• /
• pp.9-16
• /
• 2015

In this paper, several experiments are performed according to deep neural network (DNN) based features for the performance comparison of speaker verification (SV) systems. To this end, input features for a DNN, such as mel-frequency cepstral coefficient (MFCC), linear-frequency cepstral coefficient (LFCC), and perceptual linear prediction (PLP), are first compared in a view of the SV performance. After that, the effect of a DNN training method and a structure of hidden layers of DNNs on the SV performance is investigated depending on the type of features. The performance of an SV system is then evaluated on the basis of I-vector or probabilistic linear discriminant analysis (PLDA) scoring method. It is shown from SV experiments that a tandem feature of DNN bottleneck feature and MFCC feature gives the best performance when DNNs are configured using a rectangular type of hidden layers and trained with a supervised training method.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.3
• /
• pp.367-374
• /
• 2022

In this paper, correlation analysis between speech characteristics and the dose of antipsychotic drugs was performed. To investigate the pattern of speech characteristics of ExtraPyramidal Symptoms (EPS) related to voice change, a common side effect of antipsychotic drugs, a Korean-based extrapyramidal symptom speech corpus was constructed through the sentence development. Through this, speech patterns of EPS and non-EPS groups were investigated, and in particular, a strong speech feature correlation was shown in the EPS group. In addition, it was confirmed that the type of speech sentence affects the speech feature pattern, and these results suggest the possibility of early detection of antipsychotics-induced EPS based on the speech features.

• Proceedings of the KSPS conference
• /
• 2007.05a
• /
• pp.123-126
• /
• 2007

This paper suggests a method to improve the performance of the pathological/normal voice classification. The effectiveness of the mel frequency-based filter bank energies using the fisher discriminant ratio (FDR) is analyzed. And mel frequency cepstrum coefficients (MFCCs) and the feature vectors through the linear discriminant analysis (LDA) transformation of the filter bank energies (FBE) are implemented. This paper shows that the FBE LDA-based GMM is more distinct method for the pathological/normal voice classification than the MFCC-based GMM.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.243-244
• /
• 2006

In this study, we propose a speech/music discrimination method using spectral peak track analysis. The proposed method uses the spectral peak track's duration at the same frequency channel for feature parameter. And use the duration threshold to discriminate the speech/music. Experiment result, correct discrimination ratio varies according to threshold, but achieved a performance comparable to another method and has a computational efficient for discrimination.