• The Journal of the Korea Contents Association
• /
• v.13 no.3
• /
• pp.1-8
• /
• 2013

This paper proposes a new feature extraction algorithm to improve children's speech recognition in Korean. The proposed feature extraction algorithm combines three methods. The first method is on the vocal tract length normalization to compensate acoustic features because the vocal tract length in children is shorter than in adults. The second method is to use the uniform bandwidth because children's voice is centered on high spectral regions. Finally, the proposed algorithm uses a smoothing filter for a robust speech recognizer in real environments. This paper shows the new feature extraction algorithm improves the children's speech recognition performance.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.7 no.3
• /
• pp.475-483
• /
• 2012

The characteristic features of speech signal do not vary significantly from frame to frame. Therefore, it is advisable to reduce the redundancy involved in the similar feature vectors. The objective of this paper is to search for the optimal condition of minimum redundancy and maximum relevancy of the speech feature vectors in speech recognition. For this purpose, we realize redundancy reduction by way of a vigilance parameter and investigate the resultant effect on the speaker-independent speech recognition of isolated words by using FVQ/HMM. Experimental results showed that the number of feature vectors might be reduced by 30% without deteriorating the speech recognition accuracy.

• Proceedings of the KSPS conference
• /
• 2007.05a
• /
• pp.217-220
• /
• 2007

This study outlines a small-sized dialog style ETRI Korean TTS system which applies a HMM based speech synthesis techniques. In order to build the VoiceFont, dialog-style 500 sentences were used in training HMM. And the context information about phonemes, syllables, words, phrases and sentence were extracted fully automatically to build context-dependent HMM. In training the acoustic model, acoustic features such as Mel-cepstrums, logF0 and its delta, delta-delta were used. The size of the VoiceFont which was built through the training is 0.93Mb. The developed HMM-based TTS system were installed on the ARM720T processor which operates 60MHz clocks/second. To reduce computation time, the MLSA inverse filtering module is implemented with Assembly language. The speed of the fully implemented system is the 1.73 times faster than real time.

• The Journal of the Acoustical Society of Korea
• /
• v.14 no.5
• /
• pp.94-101
• /
• 1995

In this paper, a new vocal cords model, called a four-mass model, is proposed for a hoarse speech mechanism. Pathological changes of vocal cords cause hoarse speech and glottal waveform reflects motion states of vocal cords. From these facts, we assumed that the morbid vocal cords be dissymmetric and take the four-mass type. The glottal waveforms and the model parameters of normal and hoarse speech signals are analyzed, and some relations bet ween the model parameters and the hoarse pathology are discussed. Experimental results show that the new research method of hoarse speech can reveal relations between the acoustic features of hoarse speech and the hoarse pathology, and be used to diagnose laryngeal diseases and to improve tone quality of hoarse speech.

• The Journal of the Acoustical Society of Korea
• /
• v.35 no.2
• /
• pp.134-142
• /
• 2016

In this paper, a method synthesizing speech signal using the 40 kHz ultrasonic signals reflected from the articulatory muscles was introduced and performance was evaluated. When the ultrasound signals are radiated to articulating face, the Doppler effects caused by movements of lips, jaw, and chin observed. The signals that have different frequencies from that of the transmitted signals are found in the received signals. These ADS (Acoustic-Doppler Signals) were used for estimating of the speech parameters in this study. Prior to synthesizing speech signal, a quantitative correlation analysis between ADS and speech signals was carried out on each frequency bin. According to the results, the feasibility of the ADS-based speech synthesis was validated. ADS-to-speech transformation was achieved by the joint Gaussian mixture model-based conversion rules. The experimental results from the 5 subjects showed that filter bank energy and LPC (Linear Predictive Coefficient) cepstrum coefficients are the optimal features for ADS, and speech, respectively. In the subjective evaluation where synthesized speech signals were obtained using the excitation sources extracted from original speech signals, it was confirmed that the ADS-to-speech conversion method yielded 72.2 % average recognition rates.

• Phonetics and Speech Sciences
• /
• v.13 no.1
• /
• pp.65-72
• /
• 2021

The aim of this study is to prepare basic data that can be used for evaluation and intervention by investigating the characteristics of diphthongs produced by children with speech sound disorders. To confirm this, two groups of 10 children each, with and without speech sound disorders were asked to imitate the meaningless two-syllable 'diphthongs + da'. The slope of F1 and F2, amount of change of formant, and duration of glide were analyzed by Praat (version 6.1.16). As a result, the difference between the two groups was found in the slope of F1 of /ju/. Children with speech sound disorders had smaller changes in formants and shorter duration time values compared to normal children, and there were statistically significant differences. The amount of change in formant in the glide was found in F1 of /ju, jɛ/, F2 of /jɑ, jɛ/, and there were significant differences in the duration of glide in /ju, jɛ/. The results of this study showed that the range of articulation of diphthongs in children with speech sound disorders is relatively smaller than that of normal children, thus the time it takes to articulate was reduced. These results suggest that the range of articulation and acoustic analysis should be further investigated for evaluation and intervention regarding diphthongs of children with speech sound disorders.

• Journal of Digital Convergence
• /
• v.11 no.6
• /
• pp.169-174
• /
• 2013

Speech recognition, the problem of performance degradation is the difference between the model training and recognition environments. Silence features normalized using the method as a way to reduce the inconsistency of such an environment. Silence features normalized way of existing in the low signal-to-noise ratio. Increase the energy level of the silence interval for voice and non-voice classification accuracy due to the falling. There is a problem in the recognition performance is degraded. This paper proposed a robust speech detection method in noisy environments using a silence feature normalization and voice energy maximize. In the high signal-to-noise ratio for the proposed method was used to maximize the characteristics receive less characterized the effects of noise by the voice energy. Cepstral feature distribution of voice / non-voice characteristics in the low signal-to-noise ratio and improves the recognition performance. Result of the recognition experiment, recognition performance improved compared to the conventional method.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.6 no.3
• /
• pp.77-86
• /
• 2007

Recently, systems based on speech recognition interface such as telematics terminals are being developed. However, many errors still exist in speech recognition and then studies about error correction are actively conducting. This paper proposes an error correction in post-processing of the speech recognition based on features of Korean phoneme. To support this algorithm, we used the phoneme similarity considering features of Korean phoneme. The phoneme similarity, which is utilized in this paper, rams data by mono-phoneme, and uses MFCC and LPC to extract feature in each Korean phoneme. In addition, the phoneme similarity uses a Bhattacharrya distance measure to get the similarity between one phoneme and the other. By using the phoneme similarity, the error of eo-jeol that may not be morphologically analyzed could be corrected. Also, the syllable recovery and morphological analysis are performed again. The results of the experiment show the improvement of 7.5% and 5.3% for each of MFCC and LPC.

• English Language & Literature Teaching
• /
• v.15 no.2
• /
• pp.225-243
• /
• 2009

This study investigates the use of different speech act of apology strategies between male and female EFL college students by comparing the components of intensity, stylistic competence, and semantic formulas. The data was collected from 37 participants who were studying freshmen English reading course at the Department of English Education of C University in Seoul. Most students were English majors taking pre-teacher course of teaching English for secondary school students. The participants were divided into two gender groups of male and female. The discourse completion test (DCT) which was revised from the speech act of apology by Olshtain and Cohen (1990) was provided with the participants after the researcher explained the speech act of apology in ten situations. The speech act of apology depends on situation variables: social solidarity, severity of offense, and social status. The results show that in the preference of intensity, male and female have almost the similar ratio in high (female: 24.7%, male 24%) and low intensity (female: 75.3%, male: 76%). In the use of stylistic competence, male group (21%) expresses more diversely formal features than female group (12%), while female (87%) use more informal features than male (66%). Most of participants show a limitation in the use of speaking four types of semantic formulas: expression of apology (APOL), acknowledgment of responsibility (RESP), offer of repair (REPR), and promise of forbearance (FORB). As nonnative speakers, the participants cannot conduct the semantic formula in some situations regardless of the tasks provided. The results suggest that English teachers should recognize pragmatic variations in which students feel difficulty in appropriate speaking strategies on apology. This study also contributes to teaching learners the strategies and speaking patterns in the course of various apology situations.

• Phonetics and Speech Sciences
• /
• v.13 no.4
• /
• pp.55-66
• /
• 2021

Proper prosody in reading allows the reader to naturally convey the meaning, which manifests as changes in pitch, loudness, and speech rate. Children with reading disability face difficulty in delivering information due to poor prosody. This study identified the difference in prosodic features between children with reading disabilities and nondisabled children through means of reading tasks. Reading tasks, according to sentence types (short sentences, assumptions/conditions, intentions, relative-clause), were recorded by 15 children studying in the 3rd to 6th grade in elementary school. Children with reading disability had a statistically significant wider range of pitch, slower speech rate, more frequent usage of pauses, longer total pause duration, and steeper pitch slope than nondisabled one in sentence-final and -medial words. Children with reading disability, therefore, exhibited a less natural and expressive reading than nondisabled children. Through this study, the characteristics of prosody observed in children with reading disability were identified and the need for an approach for effective intervention was also suggested.