• The Journal of the Acoustical Society of Korea
• /
• v.21 no.3
• /
• pp.310-314
• /
• 2002

The exact pitch (fundamental frequency) extraction is important in speech signal processing like speech recognition, speech analysis and synthesis. However the exact pitch extraction from speech signal is very difficult due to the effect of formant and transitional amplitude. So in this paper, the pitch is detected after the elimination of formant ingredients by flattening the spectrum in frequency region. The effect of the transition and change of phoneme is low in frequency region. In this paper we proposed the new flattening method of log spectrum and the performance was compared with LPC method and Cepstrum method. The results show the proposed method is better than conventional method.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.9C
• /
• pp.884-890
• /
• 2003

In this paper, we studied the speaker adaptation methods that improve the speaker independent recognition system. For the independent speakers, we compared the results between bigram and back-off bigram, MAP and MLLR. Cause back-off bigram applys unigram and back-off weighted value as bigram probability value, it has the effect adding little weighted value to bigram probability value. We did an experiment using total 39-feature vectors as featuring voice parameter with 12-MFCC, log energy and their delta and delta-delta parameter. For this recognition experiment, We constructed a system made by CHMM and tri-phones recognition unit and bigram and back-off bigrams language model.

• Phonetics and Speech Sciences
• /
• v.5 no.4
• /
• pp.157-169
• /
• 2013

Using a target detection task, this study compared the processing automaticity of phonemes and features in spoken syllable stimuli to determine the primitive representation in speech perception, phoneme or distinctive feature. For this, we modified the visual search task(Treisman et al., 1992) developed to investigate the processing of visual features(ex. color, shape or their conjunction) for auditory stimuli. In our task, the distinctive features(ex. aspiration or coronal) corresponded to visual primitive features(ex. color and shape), and the phonemes(ex. /$t^h$/) to visual conjunctive features(ex. colored shapes). The automaticity is measured by the set size effect that was the increasing amount of reaction time when the number of distracters increased. Three experiments were conducted. The laryngeal features(experiment 1), the manner features(experiment 2), and the place features(experiment 3) were compared with phonemes. The results showed that the distinctive features are consistently processed faster and automatically than the phonemes. Additionally there were differences in the processing automaticity among the classes of distinctive features. The laryngeal features are the most automatic, the manner features are moderately automatic and the place features are the least automatic. These results are consistent with the previous studies(Bae et al., 2002; Bae, 2010) that showed the perceptual hierarchy of distinctive features.

• Proceedings of the IEEK Conference
• /
• 2003.11a
• /
• pp.397-400
• /
• 2003

본 연구에서는 KM-Net(Hidden Markov Network)을 다양한 태스크에의 적용과 화자의 특성을 효과적으로 나타내기 위해 HM-Net 음성인식 시스템에 MLLR(Maximum Likelihood Linear Regression) 적응방법을 도입하였으며, HM-Net 학습 알고리즘을 개량하여 회귀클래스 생성방법을 제안한다. 제안방법은 PDT-SSS(Phonetic Decision Tree-based Successive State Splitting) 알고리즘의 문맥방향 상태분할에 의한 상태레벨 공유를 이용한 방법으로 새로운 화자로부터 문맥정보와 적응화 데이터의 발성 양에 의존하여 결정된 많은 적응 파라미터들을(평균, 분산) 자유롭게 제어할 수 있게 된다. 제안방법의 유효성을 확인하기 위해 국어공학센터(KLE) 452 음성 데이터와 항공편 예약관련 연속음성을 대상으로 인식실험을 수행한 결과, 전체적으로 음소인식의 경우 평균 34-37％, 단어인식의 경우 평균 9％, 연속음성인식의 경우 평균 7-8％의 인식성능 향상을 각각 보였다. 또한 적응화 데이터의 양에 따른 인식성능 비교에서, 제안방법을 적용한 인식 시스템이 적응 데이터의 양이 적은 경우에도 향상된 인식률을 보였으며. 잡음을 부가한 음성에 대한 적응화 실험에서도 향상된 인식성능을 보여 MLLR 적응방법의 특성을 만족하였다. 따라서 MLLR 적응방법을 도입한 HM-Net 음성인식 시스템에 제안한 회귀클래스 생성방법이 유효함을 확인한 수 있었다.

• MALSORI
• /
• no.59
• /
• pp.27-51
• /
• 2006

For speech recognition systems, rejection function as well as decoding function is necessary to improve the reliability. There have been many research efforts on out-of-vocabulary word rejection, however, little attention has been paid on non-target sentence rejection. Recently pronunciation approaches using speech recognition increase the need for non-target sentence rejection to provide more accurate and robust results. In this paper, we proposed filler model method and word/phoneme detection ratio method to implement non-target sentence rejection system. We made performance evaluation of filler model along to word-level, phoneme-level, and sentence-level filler models respectively. We also perform the similar experiment using word-level and phoneme-level word/phoneme detection ratio method. For the performance evaluation, the minimized average of FAR and FRR is used for comparing the effectiveness of each method along with the number of words of given sentences. From the experimental results, we got to know that word-level method outperforms the other methods, and word-level filler mode shows slightly better results than that of word detection ratio method.

• The Journal of the Acoustical Society of Korea
• /
• v.18 no.8
• /
• pp.3-8
• /
• 1999

Previous variable vocabulary speech recognition systems with context-independent acoustic modeling, could not represent the effect of neighboring phonemes. To solve this problem, we use allophone-based context-dependent acoustic model. This paper describes the method to improve acoustic model of the system effectively. Acoustic model is improved by using allophone clustering technique that uses entropy as a similarity measure and the optimal allophone model is generated by changing the number of allophones. We evaluate performance of the improved system by using Phonetically Optimized Words(POW) DB and PC commands(PC) DB. As a result, the allophone model composed of six hundreds allophones improved the recognition rate by 13% from the original context independent model m POW test DB.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.4
• /
• pp.323-328
• /
• 2003

This study describes an energy contour generation method for Korean n systems. We propose a vector-regression tree, which is a vector version of a scalar regression tree. A vector-regression tree predicts a response vector for an unknown feature vector. In our study, the tree yields a vector containing ten sampled energy values for each phone. After collecting 500 sentences and its corresponding speech corpus, we trained trees on 300 sentences and tested them on 200 sentences. We construct a bagged tree and a born again one to improve the performance of contour prediction. In the experiment, we got a 0.803 correlation coefficient for the observed and predicted energy values.

• The Journal of the Acoustical Society of Korea
• /
• v.13 no.5
• /
• pp.69-76
• /
• 1994

Acoustic cues of some consonantal phonology were tested in Korean words. All Korean consonants were recorded and acoustically analyzed in controlled phonological environments :ⅰ) word-initial, ⅱ) inter-vocalic, and ⅲ) word-final positions. The observed acoustic regulations are : ⅰ) The lengths of obstruents are longer word-initially than word-finally, ⅱ) The lengths of sonorants are longer word-finally than in word-initial or inter-vocalic positions, ⅲ) The formants of the lateral sound /l/ are higher word-finally than intervocalically. The phonological explanations of these acoustic regulations can be found in the rules of ⅰ) inter-vocalic voicing of plain stops, ⅱ) syllable-final unreleasing of obstruents, ⅲ) word-initial aspiration of stops, and ⅳ) liquid alternation between [r] and [l]. Numerical data of all these acoustic regulations are reported in order to facilitate their application toward improving naturalness for speech synthesis and accurateness for speech recognition.

• Annual Conference on Human and Language Technology
• /
• 1996.10a
• /
• pp.153-157
• /
• 1996

본 논문은 연속 분포 HMM을 사용한 핵심어 추출기법(Keyword Spotting)과 화자 인식에 기반한 음성 다이얼링 및 부서 안내에 관한 것이다. 개발된 시스템은 상대방의 이름, 직책, 존칭 등에 감탄사나 명령어 등이 혼합된 형태의 자연스런 음성 문장으로부터 다이얼링과 안내에 필요한 핵심어를 자동 추출하고 있다. 핵심 단어의 사용에는 자연성을 고려하여 문법적 제약을 최소한으로 두었으며, 각 단어 모델에 대해서는 음소의 갯수 더하기 $3{\sim}4$개의 상태 수와 3개 정도의 mixture component로써 좌우향 모델을, 묵음모델에 대해서는 2개 상태의 ergodic형 모델을 구성하였다. 인식에 있어서는 프레임 동기 One-Pass 비터비 알고리즘과 beam pruning을 채택하였으며, 인식에 사용된 어휘는 36개의 성명, 8개의 직위 및 존칭, 5개 정도의 호출어, 부탁을 나타내는 동사 및 그 활용이 10개 정도이다. 약 $3{\sim}6$개 정도의 단어로 구성된 문장을 실시간($1{\sim}3$초이내)에 인식하고, 약 98% 정도의 핵심어 인식 성능을 나타내고 있다.

• Annual Conference on Human and Language Technology
• /
• 1996.10a
• /
• pp.284-297
• /
• 1996

사용자가 컴퓨터와 자연스럽고 인간적으로 대화할 수 있고, 사람의 요구에 지능적인 해답을 능동적으로 제시할 수 있는 사용자 인터페이스 에이전트가 활발히 연구되고 있다. 음성, 펜, 제스쳐인식 등을 비롯한 다양한 방법을 통하여 사람의 의사전달방식을 컴퓨터의 입력수단으로 구현하여 사용자 편의성을 도모하고 있다. 본 논문에서는 컴퓨터를 블랙박스로 하고, 표면적으로 지능형 3차원 그래픽 얼굴 에이전트와 사용자가 의사소통을 하는 사용자 인터페이스를 대상으로 하였다. 컴퓨터가 단순문제 해결을 위한 도구에서 많은 정보를 다양한 매체를 통해 제공하는 보조자의 역할을 수행하게 되었기 때문에 위의 방법은 보다 적극적인 방법이라 할 수 있다. 이를 위한 기반 기술로써 국어를 발음하는 얼굴 애니메이션을 연구하였다. 발음을 표현하기 위한 데이터로써 디지털 카메라를 사용하여 입술 운동의 특징점의 위치를 조사하였고, 모델링 시스템을 개발하여 데이터를 입력하였다. 적은 데이터로도 복잡한 자유곡면을 표현할 수 있는 B-Spline곡면을 기본데이터로 사용하였기 때문에 애니메이션을 위한 데이터의 양 또한 줄일 수 있었다. 그리고 국어음소의 발음시간 수열에 대한 입술모양의 변화를 조사하여 발음소리와 입술 움직임을 동기화 시킨 발음 애니메이션을 구현하였다.