• 한국음향학회지
• /
• 제13권1호
• /
• pp.24-31
• /
• 1994

본 논문에서는 연속분포 hidden Markov모델을 이용한 화자독립 연속 음성 인식 시스템에 관해 기술한다. 연속분포 모델은 평균과 분산 벡터로 구성되며 음성신호를 직접 모델링하여 양자화 왜곡이 없어진다. 특징벡터는 filter bank 계수 및 그 1, 2차 미분계수를 사용하여 음성신호의 동적 특성을 반영하였다. Segmental K-means 알고리즘을 이용하여 학습하였으며, 연속어 인식에서 가장 문제가 되는 조음화 현상으로 인한 인식률 저하를 막기 위해 앞뒤의 음소를 고려해주는 triphone을 인식단위로 사용하였다. Search 알고리즘으로는 시간 면에서 효율이 좋은 one-pass search 알고리즘을 사용하였다 성능 평가를 위한 회자 독립인식 실험에서 문법이 없을 경우 $83\%$, finite state network을 적용한 경우에는 $94\%$의 인식률을 나타내었다.

• 대한음성학회지:말소리
• /
• 제53호
• /
• pp.119-127
• /
• 2005

Speech recognition is one of the user interface technologies in commanding and controlling any terminal such as a TV, PC, cellular phone etc. in a ubiquitous environment. In controlling a terminal, the mismatch between training and testing causes rapid performance degradation. That is, the mismatch decreases not only the performance of the recognition system but also the reliability of that. Therefore, the performance degradation due to the mismatch caused by the change of the environment should be necessarily compensated. Whenever the environment changes, environment adaptation is performed using the user's speech and the background noise of the changed environment and the performance is increased by employing the models appropriately transformed to the changed environment. So far, the research on the environment compensation has been done actively. However, the compensation method for the effect of distant-talking speech has not been developed yet. Thus, in this paper we apply MLLR-based environment adaptation to compensate for the effect of distant-talking speech and the performance is improved.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 1996년도 10월 학술대회지
• /
• pp.435-447
• /
• 1996

In this paper, we propose the method that extracts the speech feature using the hearing model through signal processing techniques. The proposed method includes the following procedure ; normalization of the short-time speech block by its maximum value, multi-resolution analysis using the discrete wavelet transformation and re-synthesize using the discrete inverse wavelet transformation, differentiation after analysis and synthesis, full wave rectification and integration. In order to verify the performance of the proposed speech feature in the speech recognition task, korean digit recognition experiments were carried out using both the DTW and the VQ-HMM. The results showed that, in the case of using DTW, the recognition rates were 99.79% and 90.33% for speaker-dependent and speaker-independent task respectively and, in the case of using VQ-HMM, the rate were 96.5% and 81.5% respectively. And it indicates that the proposed speech feature has the potential for use as a simple and efficient feature for recognition task

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2005년도 춘계 학술대회 발표논문집
• /
• pp.45-48
• /
• 2005

This study is about constructing L2 pronunciation correction system for L1 speakers using speech technology. Chinese pronunciation system consists of initials, finals and tones. Initials/finals are in segmental level and tones are in suprasegmental level. So different method could be used assessing Korean users' Chinese. The recognition rate of initials is 81.9% and that of finals is 68.7% in the standard acoustic model. Differ from native speech recognition, nonnative speech recognition could be promoted by additional modeling using L2 speakers' speech. As a first step for the those task we analysed nonnative speech and then set a strategy for modeling Korean speakers'.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2006년도 춘계 학술대회 발표논문집
• /
• pp.45-48
• /
• 2006

As the speech recognition systems are used in many emerging applications, robust performance of speech recognition systems under extremely noisy conditions become more important. The voice activity detection (VAD) has been taken into account as one of the important factors for robust speech recognition. In this paper, we investigate conventional VAD algorithms and analyze the weak and the strong points of each algorithm.

• 대한음성학회지:말소리
• /
• 제46호
• /
• pp.65-76
• /
• 2003

In this paper, we employ the adaptive comb filtering for effective noise reduction in mobile communication environment. Adaptive comb filtering is a well-known method for noise reduction, but requires correct pitch period and must be applied just in voiced speech frames. To satisfy these requirements we use two kinds of information extracted from speech packets, one of which is the pitch period information measured precisely by a speech coder and the other is the frame rate information related to a decision on speech or silence frame. Experiments on speech recognition system confirm the efficiency of this method. Feature parameters employing this method give superior performance in noise environment to those extracted directly from output speech.

• 융합보안논문지
• /
• 제24권2호
• /
• pp.161-165
• /
• 2024

최근 음성 인식 모델들이 점점 발달하고 있고 이와 더불어 좋은 데이터를 얻기 위한 다양한 음성 처리 기술들도 발전하고 있다. 한편 국방 분야에서도 노이즈가 낀 음성 데이터로부터 노이즈를 제거하고 이를 효과적으로 음성 인식하는 기술을 접목하려고 시도하고 있다. 본 논문에서는 다양한 소음이 존재하는 전장 상황 속에서 음성 인식 기술을 활용하여 효과적으로 지휘관이 명령을 전달할 수 있는 음성 인식방법을 제안하였다. 제안방법은 노이즈가 있는 음성에 대해서 노이즈를 제거 후 OpenAI의 Whisper 모델을 사용하여 텍스트로 변환하는 방법이다. 실험결과로써, 제안 방법은 노이즈를 제거하지 않은 기존 방법에 비해서 글자 오류률(Charactor Error Rate, CER)이 6.17% 감소된 것을 볼 수가 있었다. 추가적으로 제안방법을 이용하여 국방분야에 적용할 수 있는 부분에 대해서도 기술하였다.

• 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.

• 한국음향학회지
• /
• 제15권4호
• /
• pp.24-31
• /
• 1996

이 논문에서는 호텔예약을 위한 음성번역시스템(KT-STS:Korea Telecom Speech Translation System)에 대해 기술한다. KT-STS는 한국손님이 일본의 호텔을 예약하고자 할 때 사용할 수 있는 시스템으로 한국어 음성을 인식하여 일본어로 번역을 해주는 시스템이다. 이 시스템은 한국어 음성인식부, 한일 기계번역부, 그리고 한국어 음성합성부로 구성되어 있다. 한국어 음성인식부는 HMM(Hidden Markov Model)에 근거한 화자독립, 300 단어급 연속음성인식시스템이다. 언어모델은 바이그램(bigram)을 전향 언어모델로, 의존문법을 후향 언어모델로 사용한다. 기계번역부에서는 의존문법과 직적 번역 방식을 사용하였다. 음성합성부에서 합성단위로 반음소를 사용하며 합성방식은 주기파형분해 및 재배치 방식을 이용한다. KT-STS는 TMS320C30 DSP 보드를 장착한 SPARC20 위크스테이션 상에서 거의 실시간으로 동작한다. 음성인식 실험결과 94.68%의 단어인식률과 82.42%의 문장인식률을 얻었으며, 한일 번역기만의 번역 성공률은 100%였다. 우리는 이 시스템과 일본 KDD에서 개발한 시스템을 전용선으로 연결하여 한일간 자동통역 국제시연을 가진 바 있다.

• 대한음성학회지:말소리
• /
• 제42호
• /
• pp.37-46
• /
• 2001

Recently speech technologies have shown notable advancements and they now play major roles in computer-aided language learning systems. In the current paper, use of speech recognition technologies is viewed with our system for teaching English pronunciation to Japanese speakers.