• Proceedings of the Korea Contents Association Conference
• /
• 2004.11a
• /
• pp.308-313
• /
• 2004

In this paper, we compared and analyzed the discrimination performance of speech/music about combinations of each features parameter. Audio signals are classified into 3 classes (speech, music, speech and music). On three types of features, Mel-cepstrum, energy, zero-crossings used to the experiments. Then compared and analyzed the best of the combinations between features to speech/ music discrimination performance. The best result is achieved using Mel-cepstrum, energy and zero-crossings in a single feature vector (speech: 95.1%, music: 61.9%, speech & music: 55.5%).

• Phonetics and Speech Sciences
• /
• v.6 no.3
• /
• pp.131-138
• /
• 2014

A close-copy stylization of intonation curve was used for an acoustical analysis of emotional speech. For the analysis, 408 utterances of five emotions (happiness, anger, fear, neutral and sadness) were processed to extract acoustical feature values. The results show that certain pitch point features (pitch point movement time and pitch point distance within a sentence) and sentence level features (pitch range of a final pitch point, pitch range of a sentence and pitch slope of a sentence) are affected by emotions. Pitch point movement time, pitch point distance within a sentence and pitch slope of a sentence show no significant difference between male and female participants. The emotions with high arousal (happiness and anger) are consistently distinguished from the emotion with low arousal (sadness) in terms of these acoustical features. Emotions with higher arousal show steeper pitch slope of a sentence. They have steeper pitch slope at the end of a sentence. They also show wider pitch range of a sentence. The acoustical analysis in this study implies the possibility that the measurement of these acoustical features can be used to cluster and identify emotions of speech.

• The KIPS Transactions:PartB
• /
• v.16B no.6
• /
• pp.471-478
• /
• 2009

The lung diseases classifying as one of the six incurable diseases in modern days are caused mostly by smoking and air pollution. Such causes the lung function damages, and results in malfunction of the exchange of carbon dioxide and oxygen in an alveolus, which the interest is augment with risk diseases of life prolongation. With this in the paper, we proposed a diagnosis method of lung diseases by applying parameters of voice analysis aiming at the getting the voice feature extraction. Firstly, we sampled the voice data from patients and normal persons in the same age and sex, and made two sample groups from them. Also, we conducted an analysis by applying the various parameters of voice analysis through the collected voice data. The relational significance between the patient and normal groups can be evaluated in terms of speech rates and intensity as a part of analized parameters. In conclusion, the patient group has shown slower speech rates and bigger intensity than the normal group. With this, we propose the method of voice feature extraction for lung diseases.

• Journal of Internet Computing and Services
• /
• v.2 no.1
• /
• pp.31-38
• /
• 2001

Speech database built of phonemes is significant in the studies of speech recognition, speech synthesis and analysis, Phoneme, consist of voiced sounds and unvoiced ones, Though there are many feature differences in voiced and unvoiced sounds, the traditional algorithms for detecting the boundary between phonemes do not reflect on them and determine the boundary between phonemes by comparing parameters of current frame with those of previous frame in time domain, In this paper, we propose the assort algorithm, which is based on a block and reflecting upon the feature differences between voiced and unvoiced sounds for phoneme segmentation, The assort algorithm uses the distance measure based upon MFCC(Mel-Frequency Cepstrum Coefficient) as a comparing spectrum measure, and uses the energy, zero crossing rate, spectral energy ratio, the formant frequency to separate voiced sounds from unvoiced sounds, N, the result of out experiment, the proposed system showed about 79 percents precision subject to the 3 or 4 syllables isolated words, and improved about 8 percents in the precision over the existing phonemes segmentation system.

• MALSORI
• /
• no.52
• /
• pp.111-120
• /
• 2004

This paper focuses on the DSP implementation of an HMM-based speech recognizer that can handle several hundred words of vocabulary size as well as speaker independency. First, we develop an HMM-based speech recognition system on the PC that operates on the frame basis with parallel processing of feature extraction and Viterbi decoding to make the processing delay as small as possible. Many techniques such as linear discriminant analysis, state-based Gaussian selection, and phonetic tied mixture model are employed for reduction of computational burden and memory size. The system is then properly optimized and compiled on the TMS320C6711 DSP for real-time operation. The implemented system uses 486kbytes of memory for data and acoustic models, and 24.5 kbytes for program code. Maximum required time of 29.2 ms for processing a frame of 32 ms of speech validates real-time operation of the implemented system.

• MALSORI
• /
• no.46
• /
• pp.77-86
• /
• 2003

Channel distortion and coarticulation effect in the Korean connected digit telephone speech make it difficult to achieve high performance of connected digit recognition in the telephone environment. In this paper, as a basic research to improve the recognition performance of Korean connected digit telephone speech, recognition error patterns are investigated and analyzed. Korean connected digit telephone speech database released by SiTEC and HTK system are used for recognition experiments. Both DWFBA and MRTCN methods are used for feature extraction and channel compensation, respectively. Experimental results are discussed with our findings.

• Speech Sciences
• /
• v.12 no.2
• /
• pp.171-182
• /
• 2005

An efficient GMM (Gaussian mixture modeling) method based on LPCA (local principal component analysis) with VQ (vector quantization) for speaker identification is proposed. To reduce the dimension and correlation of the feature vector, this paper proposes a speaker identification method based on principal component analysis. The proposed method firstly partitions the data space into several disjoint regions by VQ, and then performs PCA in each region. Finally, the GMM for the speaker is obtained from the transformed feature vectors in each region. Compared to the conventional GMM method with diagonal covariance matrix, the proposed method requires less storage and complexity while maintaining the same performance requires less storage and shows faster results.

• Phonetics and Speech Sciences
• /
• v.15 no.2
• /
• pp.43-51
• /
• 2023

In this paper, we propose an approach for dialect classification based on the speed and pause of speech utterances as well as the age and gender of the speakers. Dialect classification is one of the important techniques for speech analysis. For example, an accurate dialect classification model can potentially improve the performance of speaker or speech recognition. According to previous studies, research based on deep learning using Mel-Frequency Cepstral Coefficients (MFCC) features has been the dominant approach. We focus on the acoustic differences between regions and conduct dialect classification based on the extracted features derived from the differences. In this paper, we propose an approach of extracting underexplored additional features, namely the speed and the pauses of speech utterances along with the metadata including the age and the gender of the speakers. Experimental results show that our proposed approach results in higher accuracy, especially with the speech rate feature, compared to the method only using the MFCC features. The accuracy improved from 91.02% to 97.02% compared to the previous method that only used MFCC features, by incorporating all the proposed features in this paper.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.9 no.3
• /
• pp.67-72
• /
• 2010

This paper presents biometrical driver verification system in car experiment through analysis of speech, and face information. We have used Mel-scale Frequency Cesptral Coefficients (MFCCs) for speaker verification using speech information. For face verification, face region is detected by AdaBoost algorithm and dimension-reduced feature vector is extracted by using principal component analysis only from face region. In this paper, we apply the extracted speech- and face feature vectors to an SVM kernel with Gaussian Mixture Models(GMM) supervector. The experimental results of the proposed approach show a clear improvement compared to a simple GMM or SVM approach.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.8 no.9
• /
• pp.1299-1305
• /
• 2013

In this paper, we investigate a method of reducing the computational cost in speech recognition by dimensionality reduction of MFCC feature vectors. Eigendecomposition of the feature vectors renders linear transformation of the vectors in such a way that puts the vector components in order of variances. The first component has the largest variance and hence serves as the most important one in relevant pattern classification. Therefore, we might consider a method of reducing the computational cost and achieving no degradation of the recognition performance at the same time by dimensionality reduction through exclusion of the least-variance components. Experimental results show that the MFCC components might be reduced by about half without significant adverse effect on the recognition error rate.