• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2003.06a
• /
• pp.18-21
• /
• 2003

In general it has been considered to be the difficult problem that we divide continuous speech into short interval with having identical phoneme quality. In this paper we used Gaussian Mixture Model (GMM) related to probability density to divide speech into phonemes, an initial, medial, and final sound. From them we peformed continuous speech recognition. Decision boundary of phonemes is determined by algorithm with maximum frequency in a short interval. Recognition process is performed by Continuous Hidden Markov Model(CHMM), and we compared it with another phoneme divided by eye-measurement. For the experiments result we confirmed that the method we presented is relatively superior in auto-segmentation in korean speech.

• Language and Information
• /
• v.7 no.2
• /
• pp.81-101
• /
• 2003

This paper introduces a computerized version of the Korean Standard Pronunciation Rules that can be used in speech engineering systems such as Korean speech synthesis and recognition systems. For this purpose, we build Petri net models for each item of the Standard Pronunciation Rules, and then integrate them into the sound conversion table. The reversion of the Korean Standard Pronunciation Rules regulates the way of matching sounds into grammatically correct written characters. This paper presents not only the sound conversion table but also the character conversion table obtained by reversely converting the sound conversion table. Malting use of these tables, we have implemented a Korean character into a sound system and a Korean sound into the character conversion system, and tested them with various data sets reflecting all the items of the Standard Pronunciation Rules to verify the soundness and completeness of our tables. The test results show that the tables improve the process speed in addition to the soundness and completeness.

• Journal of Digital Convergence
• /
• v.11 no.6
• /
• pp.137-142
• /
• 2013

Speech recognition system is input of inaccurate vocabulary by feature extraction case of recognition by appear result of unrecognized or similar phoneme recognized. Therefore, in this paper, we propose a speech recognition error correction method using phoneme similarity rate and reliability measures based on the characteristics of the phonemes. Phonemes similarity rate was phoneme of learning model obtained used MFCC and LPC feature extraction method, measured with reliability rate. Minimize the error to be unrecognized by measuring the rate of similar phonemes and reliability. Turned out to error speech in the process of speech recognition was error compensation performed. In this paper, the result of applying the proposed system showed a recognition rate of 98.3%, error compensation rate 95.5% in the speech recognition.

• Journal of IKEEE
• /
• v.17 no.3
• /
• pp.241-247
• /
• 2013

This paper presents the design of a System on Programmable Chip (SoPC) based on Field Programmable Gate Array (FPGA) for speech recognition in which Mel-Frequency Cepstral Coefficients (MFCC) for speech feature extraction and Vector Quantization for recognition are used. The implementing process of the speech recognition system undergoes the following steps: feature extraction, training codebook, recognition. In the first step of feature extraction, the input voice data will be transformed into spectral components and extracted to get the main features by using MFCC algorithm. In the recognition step, the obtained spectral features from the first step will be processed and compared with the trained components. The Vector Quantization (VQ) is applied in this step. In our experiment, Altera's DE2 board with Cyclone II FPGA is used to implement the recognition system which can recognize 64 words. The execution speed of the blocks in the speech recognition system is surveyed by calculating the number of clock cycles while executing each block. The recognition accuracies are also measured in different parameters of the system. These results in execution speed and recognition accuracy could help the designer to choose the best configurations in speech recognition on SoPC.

• Speech Sciences
• /
• v.15 no.4
• /
• pp.43-60
• /
• 2008

Instrumental studies (e.g., aerodynamic, EPG, and EMMA) have shown that the first of two stops in sequence can be articulatorily reduced in time and space sometimes; either gradient or categorical. The current EMMA study aims to examine possible factors_linguistic (e.g., speech rate, word boundary, and prosodic boundary) and paralinguistic (e.g., natural context and repetition)_to induce gradient reduction of $C_1$ in /pk/ cluster sequences. EMMA data are collected from five Seoul-Korean speakers. The results show that gradient reduction of lip aperture seldom occurs, being quite restricted both in speaker frequency and in token frequency. The results also suggest that the place assimilation is not a lexical process, implying that speakers have not fully developed this process to be phonologized in the abstract level.

• The Journal of the Korea Contents Association
• /
• v.10 no.7
• /
• pp.470-480
• /
• 2010

Although e-Learning contents contain audio materials as well as visual materials, research on the design of audio materials has been focused on visual design. If it is considered that non-speech sounds which are a type of audio materials can promptly provide feedbacks of learners' responses and guide learners' learning process, the systemic design of non-speech sounds is needed. Therefore, the purpose of this study is to investigate the learners' perceptions toward non-speech sounds contained the e-Learning contents with multidimensional scaling method. For this purpose, the eleven non-speech sounds were selected among non-speech sounds designed Korea Open Courseware. The 66 juniors in A university responded the degree of similarity among 11 non-speech sounds and the learners' perceptions towards non-speech sounds were represented in the multidimensional space. The result shows that learners perceive separately non-speech sounds by the length of non-speech sounds and the atmosphere which is positive or negative.

• The Journal of the Korea Contents Association
• /
• v.12 no.4
• /
• pp.52-59
• /
• 2012

Children develop their language skill rapidly between age 3 and 5. To meet the child's language development through a variety of experiences, it is necessary to develop age-appropriate contents. So it needs to develop various contents using speech interface for children, but there is no speech database of korean children. In this paper, we develop speech database of 3 to 5 years old children in korean. For collecting accurate children's speech, child education experts examine in the speech database development process. The words for database are selected from MCDI-K in two stage and children speak a word three times. Such collected speech are tokenized by child and word and stored in database. This speech database will be transferred through web and, hopefully, be the foundation of development of children-oriented contents.

• Journal of KIISE
• /
• v.42 no.11
• /
• pp.1372-1379
• /
• 2015

This paper presents an analysis of feature extraction methods used for distinguishing the speech of patients with cleft palates and people with normal palates. This research is a basic study on the development of a software system for automatic recognition and restoration of speech disorders, in pursuit of improving the welfare of speech disabled persons. Monosyllable voice data for experiments were collected for three groups: normal speech, cleft palate speech, and simulated clef palate speech. The data consists of 14 basic Korean consonants, 5 complex consonants, and 7 vowels. Feature extractions are performed using three well-known methods: LPC, MFCC, and PLP. The pattern recognition process is executed using the acoustic model GMM. From our experiments, we concluded that the MFCC method is generally the most effective way to identify speech distortions. These results may contribute to the automatic detection and correction of the distorted speech of cleft palate patients, along with the development of an identification tool for levels of speech distortion.

• Speech Sciences
• /
• v.8 no.4
• /
• pp.185-191
• /
• 2001

This study was designed to determine what components of spoken language have been relatively neglected in the teaching of listening comprehension in Korea and to suggest a model of listening process. Two types of tests were undertaken using spoken and written forms of English with secondary school teachers of English and college students. Findings: Hearing power has been generally neglected in the teaching of listening comprehension. Hearing power which can be thought as an active process is defined as an ability to transfer the sequence of discrete phonetic segments without word boundary into the sequence of words in phonemic representations by using both nonlinguistic factors and linguistic factors including perception rules based on phonetics and phonology. Vocabularies, hearing-speaking power, syntactic structures and idiomatic expressions are to be taught for spoken English. A model of listening process was suggested and discussed.

• Proceedings of the Korean Society for Language and Information Conference
• /
• 2007.11a
• /
• pp.405-414
• /
• 2007

This paper describes a preliminary work on prosody modeling aspect of a text-to-speech system for Thai. Specifically, the model is designed to predict symbolic markers from text (i.e., prosodic phrase boundaries, accent, and intonation boundaries), and then using these markers to generate pitch, intensity, and durational patterns for the synthesis module of the system. In this paper, a novel method for annotating the prosodic structure of Thai sentences based on dependency representation of syntax is presented. The goal of the annotation process is to predict from text the rhythm of the input sentence when spoken according to its intended meaning. The encoding of the prosodic structure is established by minimizing speech disrhythmy while maintaining the congruency with syntax. That is, each word in the sentence is assigned a prosodic feature called strength dynamic which is based on the dependency representation of syntax. The strength dynamics assigned are then used to obtain rhythmic groupings in terms of a phonological unit called foot. Finally, the foot structure is used to predict the durational pattern of the input sentence. The aforementioned process has been tested on a set of ambiguous sentences, which represents various structural ambiguities involving five types of compounds in Thai.