• The Journal of the Korea Contents Association
• /
• v.19 no.12
• /
• pp.270-278
• /
• 2019

This study was performed to compare the aerodynamic characteristics of young and elderly adult male patients with voice disorders during continuous speech. Aerodynamic measurements were obtained after 12 young male patients and 9 elderly male patients read a paragraph. The elderly group showed longer duration, lower airflow rate and air volume than the younger group, but the differences were not significant except phonation time. So, when interpreting the meaning of aerodynamic measures of elderly voice disorder patients in the aspects of airflow and air volume, it should take into account various conditions(e. g. reading materials, pulmonary functions) as well as age.

• The Journal of the Acoustical Society of Korea
• /
• v.14 no.4
• /
• pp.74-81
• /
• 1995

This paper describes the development of speech databases for the Korean language which were constructed at Communications Research Laboratory in KAIST. The procedure and environment to construct the speech database are presented in detail, and the phonetic and linguistic properties of the databases are presented. the databases were intended for use in designing and evaluating speech recognition algorithms. The databases consist of five different sets of speech contents : trade-related continuous speech with 3,000 words, variable-length connected digits, phoneme-balanced 75 isolated words, 500 isolated Korean provincial names, and Korean A-set words.

• Annual Conference on Human and Language Technology
• /
• 1997.10a
• /
• pp.495-499
• /
• 1997

컴퓨터의 사용이 보편화됨에 따라 컴퓨터와 사용자 사이의 쉽고 자연스러운 의사 소통을 위한 자연어 인터페이스에 대한 연구가 활발히 진행되고 있다. 이 중에서 특히, 음성인식 분야는 음성명령, 받아쓰기 시스템 등 일반적인 컴퓨터 사용자의 요구를 충족시켜 줄 수 있는 분야로 주목을 받고 있다. 그러나 음성인식은 인식 자체만으로는 인식률에 한계가 있으며, 인식 결과를 향상시키기 위해서는 후처리 단계가 필요하다. 본 논문에서는 음성 인식의 성능을 향상시키기 위해 음성 인식의 결과로 들어온 연속된 한국어 음성을 올바른 음절로 복원시켜 주는 시스템을 구현하였다. 이 시스템에서는 어절단위의 연속된 한국어 음성을 입력으로 받아 한국어 발음 규칙을 역으로 적용하여 원래의 음절로 복원시키고, 형태소 분석기를 이용하여 복원된 음절이 올바른지를 확인하고 수정한다. 초등학교 교과서에 나오는 문장을 대상으로 본 시스템의 성능을 실험한 결과, 90.42%의 복원율을 나타내었다. 현재 정확하게 복원이 되지 않는 것 중에는 동음이의어가 차지하는 비중이 크며, 이 문제는 구문분석이나 의미분석을 이용하여 어느 정도 개선할 수 있을 것으로 보인다.

• Journal of Internet Computing and Services
• /
• v.7 no.4
• /
• pp.57-66
• /
• 2006

In this paper, I propose a new method of Multi-Pulse Speech Coding(FBD-MPC: Frequency Band Division MPC) by using TSIUVC(Transition Segment Including UnVoiced Consonant) searching, extraction and approximation-synthesis method in a frequency domain. As, a result. the extraction rates of TSIUVC are 84.8%(plosive), 94.9%(fricative) and 92.3%(affricative) in female voice, 88%(plosive), 94.9%(fricative) and 92.3%(affricative) in male voice respectively. Also, I obtain a high quality approximation-synthesis waveforms within TSIUVC by using frequency information of 0.547kHz below and 2.813kHz above. I evaluate MPC by using switching information of voiced/unvoiced and FBD-MPC by using switching information of voiced/Silence/TSIUVC. As, a result, I knew that synthesis speech of FBD-MPC was better in speech quality than synthesis speech of the MPC.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1998.08a
• /
• pp.454-459
• /
• 1998

연속된 음성의 인식을 위해서는 음성신호를 음성학적인 단위인 단어, 음절, 음소 등으로 분할하여야 한다. 이러한 분할을 위해서는 전이구간의 검출이 선행되어야 한다. 본 논문에서는 음성신호에서 전이구간을 검출하기 위해 피치동기로 된 상관관계 계수의 변화를 나타내는 파라미터를 새로이 제안하였다. 이 파라미터는 음성신호의 안정구간에서는 매우 작은 값을 나타내지만 음성의 시작이나 유성음과 무성음의 경계에서는 큰 값을 나타내어 전이구간검출용 파라미터로 매우 용이하다.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.4
• /
• pp.298-303
• /
• 2023

This study aimed to investigate the clinical utility of voiced sentence tasks for voice evaluation. To this end, we analyzed the correlation between perturbation-based acoustic measurements [jitter percent (jitter), shimmer percent (shimmer), Noise to Harmonic Ratio (NHR)] using sustained vowel phonation, and cepstrum-based acoustic measurements [Cepstral Peak Prominence (CPP), Low/High spectral ratio (L/H ratio)] using voiced sentences. As a result of analyzing data collected from 65 patients with voice disorders, there was a significant correlation between the CPP and jitter (r = -.624, p = .000), shimmer (r = -.530, p = .000), NHR (r = -.469, p = .000).This suggests that the cepstrum measurement of voiced sentences can be used as an alternative to the analysis limitations of the pathological voice such as not possible perturbation-based acoustic measurement, and result difference according to the analysis section.

• Journal of IKEEE
• /
• v.11 no.2
• /
• pp.89-94
• /
• 2007

This paper is a study on continuous speech recognition in the Korean language using HMM-based models with continuous density functions. Here, we propose the most efficient method of continuous speech recognition for the Korean language under the condition of a continuous HMM model with 2 to 44 density functions. Two voice models were used CI-Model that uses 36 uni-phones and CD-Model that uses 3,000 tri-phones. Language model was based on N-gram. Using these models, 500 sentences and 6,486 words under speaker-independent condition were processed. In the case of the CI-Model, the maximum word recognition rate was 94.4% and sentence recognition rate was 64.6%. For the CD-Model, word recognition rate was 98.2% and sentence recognition rate was 73.6%. The recognition rate of CD-Model we obtained was stable.

• The Journal of the Acoustical Society of Korea
• /
• v.14 no.5
• /
• pp.44-50
• /
• 1995

This paper describes a large-vocabulary continuous speech recognition system using continuous hidden Markov models for the Korean language. To improve the performance of the system, we study on the selection of speech modeling units, inter-word modeling, search algorithm, and grammars. We used triphones as basic speech modeling units, generalized triphones and function word-dependent phones are used to improve the trainability of speech units and to reduce errors in function words. Silence between words is optionally inserted by using a silence model and a null transition. Word pair grammar and bigram model based oil word classes are used. Also we implement a search algorithm to find N-best candidate sentences. A postprocessor reorders the N-best sentences using word triple grammar, selects the most likely sentence as the final recognition result, and finally corrects trivial errors related with postpositions. In recognition tests using a 3,000-word continuous speech database, the system attained $93.1\%$ word recognition accuracy and $73.8\%$ sentence recognition accuracy using word triple grammar in postprocessing.

• The Journal of the Acoustical Society of Korea
• /
• v.23 no.8
• /
• pp.583-589
• /
• 2004

Proposed is a speaker normalization method based on vector quantizer for continuous speech recognition (CSR) system in which no acoustic information is made use of. The proposed method, which is an improvement of the previously reported speaker normalization scheme for a simple digit recognizer, builds up a canonical codebook by iteratively training the codebook while the size of codebook is increased after each iteration from a relatively small initial size. Once the codebook established, the warp factors of speakers are estimated by comparing exhaustively the warped versions of each speaker's utterance with the codebook. Two sets of phones are used to estimate the warp factors: one, a set of vowels only. and the other, a set composed of all the Phonemes. A Piecewise linear warping function which corresponds to the estimated warp factor is adopted to warp the power spectrum of the utterance. Then the warped feature vectors are extracted to be used to train and to test the speech recognizer. The effectiveness of the proposed method is investigated by a set of recognition experiments using the TIMIT corpus and HTK speech recognition tool kit. The experimental results showed comparable recognition rate improvement with the formant based warping method.

• Annual Conference on Human and Language Technology
• /
• 1998.10c
• /
• pp.391-395
• /
• 1998

대용량의 연속된 음성을 인식하는 데에는 형태소 사이의 음운변동과 언절과 어절 사이의 불일치 등으로 인한 어려움이 따른다. 그러므로 언어학적인 지식을 이용한 자연어 처리 기술과의 결합이 필수적이라 할 수 있다. 본 논문에서는 문장 단위의 연속 음성 문자열을 올바른 어절로 띄어주는 시스템을 제안한다. 먼저 띄어쓰기 발음열 사전을 이용하여 어절의 경계를 추정한다. 이 때 보다 정확한 띄어쓰기 위치를 추정하기 위하여 2음절 이상의 최장 조사 어미와 음절 분리가능빈도가 이용된다. 이렇게 해서 분리된 어절들은 음절 복원기를 거친 뒤, 형태소 분석을 행하여 올바른 어절인지를 검사한다. 분석에 실패한 어절은 띄어쓰기 오류 유형에 따라 교정을 한 후 형태소 분석을 재시도한다. 제안한 시스템을 테스트해 본 결과 96.8%의 정확도를 보였다. 본 시스템은 음운 변동 처리기와 함께 말소리를 음성 그대로 인식하는 인식기의 후처리로 이용할 수 있을 것이다.