• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.01a
• /
• pp.441-445
• /
• 2009

We have developed a real-time software tool to extract a speech feature vector whose time sequences consist of three groups of vector components; the phonetic/acoustic features such as formant frequencies, the phonemic features as outputs on neural networks, and some distances of Japanese phonemes. In those features, since the phoneme distances for Japanese five vowels are applicable to express vowel articulation, we have designed a switch, a volume control and a color representation which are operated by pronouncing vowel sounds. As examples of those vowel interface, we have developed some speech training tools to display a image character or a rolling color ball and to control a cursor's movement for aurally- or vocally-handicapped children. In this paper, we introduce the functions and the principle of those systems.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.4
• /
• pp.156-156
• /
• 2002

We apply independent component analysis (ICA) for extracting an optimal basis to the problem of finding efficient features for representing speech signals of a given speaker The speech segments are assumed to be generated by a linear combination of the basis functions, thus the distribution of speech segments of a speaker is modeled by adapting the basis functions so that each source component is statistically independent. The learned basis functions are oriented and localized in both space and frequency, bearing a resemblance to Gabor wavelets. These features are speaker dependent characteristics and to assess their efficiency we performed speaker identification experiments and compared our results with the conventional Fourier-basis. Our results show that the proposed method is more efficient than the conventional Fourier-based features in that they can obtain a higher speaker identification rate.

• 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.

• Journal of Broadcast Engineering
• /
• v.24 no.5
• /
• pp.735-742
• /
• 2019

In this paper, we propose a method of extracting speech features for phoneme recognition based on spikegram. The Fourier-transform-based features are widely used in phoneme recognition, but they are not extracted in a biologically plausible way and cannot have high temporal resolution due to the frame-based operation. For better phoneme recognition, therefore, it is desirable to have a new method of extracting speech features, which analyzes speech signal in high temporal resolution following the model of human auditory system. In this paper, we analyze speech signal based on a spikegram that models feature extraction and transmission in auditory system, and then propose a method of feature extraction from the spikegram for phoneme recognition. We evaluate the performance of proposed features by using a DNN-based phoneme recognizer and confirm that the proposed features provide better performance than the Fourier-transform-based features for short-length phonemes. From this result, we can verify the feasibility of new speech features extracted based on auditory model for phoneme recognition.

• The Journal of the Acoustical Society of Korea
• /
• v.29 no.1E
• /
• pp.45-53
• /
• 2010

In this paper, we present the use of the Features Weighted Mahalanobis Distance (FWMD) in improving the performance of Likelihood Maximizing Beamforming (Limabeam) algorithm in speech recognition for microphone array. The proposed approach is based on the replacement of the traditional distance measure in a Gaussian classifier with adding weight for different features in the Mahalanobis distance according to their distances after the variance normalization. By using Features Weighted Mahalanobis Distance for Limabeam algorithm (FWMD-Limabeam), we obtained correct word recognition rate of 90.26% for calibrate Limabeam and 87.23% for unsupervised Limabeam, resulting in a higher rate of 3% and 6% respectively than those produced by the original Limabearn. By implementing a HM-Net speech recognition strategy alternatively, we could save memory and reduce computation complexity.

• Speech Sciences
• /
• v.15 no.1
• /
• pp.63-72
• /
• 2008

Various acoustic features were extracted and analyzed to estimate the inter- and intra-speaker variability of emotional speech. Tokens of vowel /a/ from sentences spoken with different modes of emotion (sadness, neutral, happiness, fear and anger) were analyzed. All of the acoustic features (fundamental frequency, spectral slope, HNR, H1-A1 and formant frequency) indicated greater contribution to inter- than intra-speaker variability across all emotions. Each acoustic feature of speech signal showed a different degree of contribution to speaker discrimination in different emotional modes. Sadness and neutral indicated greater speaker discrimination than other emotional modes (happiness, fear, anger in descending order of F-ratio). In other words, the speaker specificity was better represented in sadness and neutral than in happiness, fear and anger with any of the acoustic features.

• Speech Sciences
• /
• v.5 no.1
• /
• pp.63-80
• /
• 1999

In this paper, an adaptive method of dividing a speech signal into an initial, a medial and a final sound of the form of utterance utilized by evaluating extreme limits of short term energy and autocorrelation functions. By applying this method into speech signal composed of a consonant, a vowel and a consonant, it was divided into an initial, a medial and a final sound and its feature analysis of sample by LPC were carried out. As a result of spectrum analysis in each period, it was observed that there existed spectrum features of a consonant and a vowel in the initial and medial periods respectively and features of both in a final sound. Also, when all kinds of words were adaptively divided into 3 periods by using the proposed method, it was found that the initial sounds of the same consonant and the medial sounds of the same vowels have the same spectrum characteristics respectively, but the final sound showed different spectrum characteristics even if it had the same consonant as the initial sound.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2004.10a
• /
• pp.1123-1126
• /
• 2004

Recognizing emotion in speech is required lots of spoken language corpus not only at the different emotional statues, but also in individual languages. In this paper, we focused on the changes speech signals in different emotions. We compared the features of speech information like formant and pitch according to the 4 emotions (normal, happiness, sadness, anger). In Korean, pitch data on monophthongs changed in each emotion. Therefore we suggested the suitable analysis techniques using these features to recognize emotions in Korean.

• The Journal of the Acoustical Society of Korea
• /
• v.20 no.2
• /
• pp.10-15
• /
• 2001

In this paper, we describe the comparison between the combination of features using a speech and music discrimination, which is classifying between speech and music on audio signals. Audio signals are classified into 3classes (speech, music, speech and music) and 2classes (speech, music). Experiments carried out on three types of feature, Mel-cepstrum, energy, zero-crossings, and try to find a best combination between features to speech and music discrimination. We using a Gaussian Mixture Model (GMM) for discrimination algorithm and combine different features into a single vector prior to modeling the data with a GMM. In 3classes, 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％). In 2classes, the best result is achieved using Mel-cepstrum, energy and Mel-cepstrum, energy, zero-crossings in a single feature vector (speech: 98.9％, music: 100％).

• Speech Sciences
• /
• v.3
• /
• pp.156-166
• /
• 1998

In this paper, I would like to propose a dividing method by estimating the inflection points and the average magnitude energy in speech signals. The method proposed in this paper gave not only a satisfactory solution for the problems on dividing method by zero-crossing rate, but could estimate the feature of the transient period after dividing the starting point and transient period in speech signals before steady state. In the results of the experiment carried out with monosyllabic speech, it was found that even through speech samples indicated in D.C. level, the staring and ending point of the speech signals were exactly divided by the method. In addition to the results, I could compare with the features, such as the length of transient period, the short term energy, the frequency characteristics, in each speech signal.