• 음성과학
• /
• 제10권4호
• /
• pp.117-124
• /
• 2003

Speaker recognition is the technology that confirms the identification of speaker by using the characteristic of speech. Such technique is classified into speaker identification and speaker verification: The first method discriminates the speaker from the preregistered group and recognize the word, the second verifies the speaker who claims the identification. This method that extracts the information of speaker from the speech and confirms the individual identification becomes one of the most efficient technology as the service via telephone network is popularized. Some problems, however, must be solved for the real application as follows; The first thing is concerning that the safe method is necessary to reject the imposter because the recognition is not performed for the only preregistered customer. The second thing is about the fact that the characteristic of speech is changed as time goes by, So this fact causes the severe degradation of recognition rate and the inconvenience of users as the number of times to utter the text increases. The last thing is relating to the fact that the common characteristic among speakers causes the wrong recognition result. The silence parts being included the center of speech cause that identification rate is decreased. In this paper, to make improvement, We proposed identification rate can be improved by removing silence part before processing identification algorithm. The methods detecting speech area are zero crossing rate, energy of signal detect end point and starting point of the speech and process DTW algorithm by using two methods in this paper. As a result, the proposed method is obtained about 3% of improved recognition rate compare with the conventional methods.

• 말소리와 음성과학
• /
• 제2권4호
• /
• pp.173-184
• /
• 2010

The purpose of this study is to investigate the speech rate characteristics (whole speech rate, articulation speech rate, and articulation percentage) and the pause characteristics (pause duration, pause frequency, and pause percentage) of Korean-speaking patients with idiopathic Parkinson's disease (referred to as IPD hereafter). The study aims first to examine the differences between the patient group with IPD and the other group without IPD concerning those measurements, and secondly to investigate the relevant measurements of the two groups following the sentence length changes. There were two groups of subjects in this study. The first group consisted of 7 subjects between the ages of 50 and 60 who were diagnosed as IPD with mild severity, and the second group consisted of 13 subjects without IPD who matched the age and gender of those in the first group. Those two groups were asked to read 8 different sentences in length at habitual speed. Speech rate and pause characteristics of the two groups were measured and compared each other. The followings results were observed. First, in a study of speech rate characteristics, the whole speech rate and the articulation speech rate of the patient group scored within the normal range, which is same as the group without IPD. On the other hand, with regard to the pause characteristics, differences between two groups were shown; the patient group had shorter pause duration, lower pause frequency, lower pause percentage, and higher articulation percentage. Secondly, in a study of relevant measurements following the sentence length, both groups showed a tendency for whole speech rate and articulation rate to increase as the length of the sentence increased, but the result of pause characteristics showed a difference between two groups. While the group without IPD showed a longer pause duration, higher pause frequency, and higher pause percentage as the length of sentences increases, no differences were shown among the patient group concerning the length of sentences. This study suggests a result that the patients with IPD of mild severity retained a normal speech rate and examined pause characteristics of the patient group which showed a different result from the group without IPD in terms of quality. Future studies on the speech rate and pause characteristics of Korean-speaking patients with IPD in various severities.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2006년도 하계종합학술대회
• /
• pp.349-350
• /
• 2006

This paper presents very low bit rate speech coder, ZFE-CELP(ZINC Function Excitation-Code Excited Linear Prediction). The ZFE-CELP speech codec is based on a ZINC function and CELP modeling of the excitation signal respectively according to the frame characteristic such as a voiced speech and an unvoiced speech. And this paper suggest strategies to improve the speech quality of the very low bit rate speech coder.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2001년도 하계종합학술대회 논문집(4)
• /
• pp.269-272
• /
• 2001

In speech recognition technology, the utterance of every talker have special resonant frequency according to shape of talker's lip and to the motion of tongue. And utterances are different according to each talker. Accordingly, we need the superior moth-od of speech feature parameter extraction which reflect talker's characteristic well. This paper suggests the modified-MfCC combined existing MFCC with gammatone filter. We experimented with speech data from telephone and then we obtained results of enhanced speech recognition rate which is higher than that of the other methods.

• 음성과학
• /
• 제1권
• /
• pp.285-293
• /
• 1997

This paper was constructed to investigate strange attractor in considering speech which is regarded as chaos in that the random signal appears in the deterministic raising system. This paper searches for the delay time from AR model power spectrum for constructing fit attractor for speech signal. As a result of applying Taken's embedding theory to the delay time, an exact correlation dimension solution is obtained. As a result of this consideration of speech, it is found that it has more speaker recognition characteristic parameter, and gains a large speaker discrimination recognition rate.

• 대한음성학회지:말소리
• /
• 제55권
• /
• pp.143-158
• /
• 2005

The adequate compression algorithm is essential to achieve high quality embedded TTS system. in this paper, we Propose waveform interpolation coder for TTS corpus compression after many speech coder investigation. Unlike speech coders in communication system, compression rate and anality are more important factors in TTS DB compression than other performance criteria. Thus we select waveform interpolation algorithm because it provides good speech quality under high compression rate at the cost of complexity. The implemented coder has bit rate 6kbps with quality degradation 0.47. The performance indicates that the waveform interpolation is adequate for TTS DB compression with some further study.

• 전자공학회논문지B
• /
• 제31B권1호
• /
• pp.11-22
• /
• 1994

For the conventional systme based on word, it is very difficult to enlarge the number of vocabulary. To cope with this problem, we must use more fundamental units of speech. For example, syllables and phonemes are such units, Korean speech consists of initial consonants, middle vowels and final consonants and has characteristic that we can obtain syllables from speech easily. In this paper, we show a speech recognition system with the advantage of the syllable characteristics peculiar to the Korean speech. The algorithm of recognition system is the Time Delay Neural Network. To recognize many recognition units, system consists of initial consonants, middle vowels, and final consonants recognition neural network. At first, our system recognizes initial consonants, middle vowels and final consonants. Then using this results, system recognizes isolated words. Through experiments, we got 85.12% recognition rate for 2735 data of initial consonants, 86.95% recognition rate for 3110 data of middle vowels, and 90.58% recognition rate for 1615 data of final consonants. And we got 71.2% recognition rate for 250 data of isolated words.

• 음성과학
• /
• 제14권1호
• /
• pp.151-162
• /
• 2007

This study focuses on the classification of pathological voice using GMM (Gaussian Mixture Model) and compares the results to the previous work which was done by ANN (Artificial Neural Network). Speech data from normal people and patients were collected, then diagnosed and classified into two different categories. Six characteristic parameters (Jitter, Shimmer, NHR, SPI, APQ and RAP) were chosen. Then the classification method based on the artificial neural network and Gaussian mixture method was employed to discriminate the data into normal and pathological speech. The GMM method attained 98.4% average correct classification rate with training data and 95.2% average correct classification rate with test data. The different mixture number (3 to 15) of GMM was used in order to obtain an optimal condition for classification. We also compared the average classification rate based on GMM, ANN and HMM. The proper number of mixtures on Gaussian model needs to be investigated in our future work.

• 대한전자공학회논문지TE
• /
• 제39권2호
• /
• pp.60-65
• /
• 2002

본 논문에서는, 음성 인식률 향상을 위하여 청각 특성을 기반으로 한 GFCC(gammatone filter frequency cepstrum coefficients) 파라미터를 음성 특징 파라미터로 제안한다. 그리고 전화망을 통해 얻은 고립단어를 대상으로 인식실험을 수행하였다. 성능비교를 위하여 MFCC(mel frequency cepstrum coefficients)와 LPCC(linear predictive cepstrum coefficient)를 사용하여 인식 실험을 하였다. 또한, 각 파라미터에 대하여 전화망의 채널 왜곡 보상기법으로 CMS(cepstral mean subtraction)를 도입한 방법과 적용시키지 않은 방법으로 인식실험을 하였다. 실험 결과로서, GFCC를 사용하여 인식을 수행한 방법이 다른 파라미터를 사용한 방법에 비해 향상된 결과를 얻었다.

• 한국음향학회지
• /
• 제14권5호
• /
• pp.51-57
• /
• 1995

본 논문에서는 청각 모델을 기초로 잡음에 강한 음성 특징 추출을 연구하였다. 청각모델은 basilar membrane 모델, 섬모세포(hair cell) 모델과 스펙트럼 출력단으로 구성하였다. Basilar membrane 모델은 음파의 진동에 따른 전달 특성을 묘사한 것으로 대역 통과 필터의 열로 나타난다. 섬모 세포 모델은 basilar membrane의 진동에 의한 신경 물질로의 변환을 나타낸다. 이것은 입력의 상대적인 값에 크게 반응하는 adaptation 기능을 이용하게 되며, 잡음 제거에 중요한 역할을 하게 된다. 스펙트럼 출력 단은 각 채널의 평균 firing rate를 이용하여 mean rate spectrum을 형성한다. 그리고 mean rate spectrum을 이용하여 특징 벡터를 추출하였다. 실험 결과는 청각 구조에 기초한 특징 추출이 다른 특징 추출 방법에 비해 잡음에서 더 향상된 성능을 가짐을 보였다.