• Proceedings of the Acoustical Society of Korea Conference
• /
• 1998.06e
• /
• pp.407-410
• /
• 1998

본 논문에서는 변형된 Teager 에너지를 이용하여 음성의 끝점을 검출하는 알고리듬을 제안하였다. 기존의 방법에서는 대부분 음성신호의 에너지와 영교차율을 이용하거나 이 파라미터들과 함께 다른 여러 파라미터들을 사용하여 끝점을 검출하였다. 여러 파라미터들을 사용하는 알고리듬의 경우 계산량이 많아지게 되는데, 이에 비해 본 논문에서는 하나의 파라미터를 이용하기 때문에 계산량이 기존의 알고리듬보다 적다. 그리고 이 알고리듬에서 사용한 변형된 Teager 에너지는 음성신호의 진폭뿐만 아니라 주파수까지 고려한 파라미터이다. 일반적으로 마찰음은 진폭이 작아 검출하기가 어려운데, 본 논문에서는 이러한 마찰음에 대해 실험을 했고, 그 결과를 통해 제안한 알고리듬이 기존의 다른 여러 알고리듬보다 성능이 우수하다는 것을 확인할 수 있었다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.4
• /
• pp.991-998
• /
• 2010

In realization of wireless home network system using speech recognition in indoor voice recognition environment, background noise and reverberation are two main causes of digression in voice recognition system. In this study, the home network system resistant to reverberation and background noise using voice section detection method based on spectral entropy in indoor recognition environment is to be realized. Spectral subtraction can reduce the effect of reverberation and remove noise independent from voice signal by eliminating signal distorted by reverberation in spectrum. For effective spectral subtraction, the correct separation of voice section and silent section should be accompanied and for this, improvement of performance needs to be done, applying to voice section detection method based on entropy. In this study, experimental and indoor environment testing is carried out to figure out command recognition rate in indoor recognition environment. The test result shows that command recognition rate improved in static environment and reverberant room condition, using voice section detection method based on spectral entropy.

• Proceedings of the Acoustical Society of Korea Conference
• /
• spring
• /
• pp.149-152
• /
• 2000

음성신호처리분야에서 피치시점 검출은 음성 합성시에 여기원의 특성을 나타내어 음질의 자연성을 결정한다. 이에 본 논문에서는 음색 변경시에 운율조절에 필요한 피치시점 검출법을 제안한다. 제안한 방법은 시간영역에서 직접 처리하기 때문에 피치동기분석이 용이하고 다른 영역으로의 변환과정이 불필요하다. 또한 기존의 피치시점검출 방법에서는 결정논리를 실험적인 문턱 값이나 무게치를 적용하여 처리하는 반면에 제안한 방법은 분석구간별로 얻어지는 주기적인 성문특성을 적용하여서 정확한 피치시점을 검출할 수 있었다

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.10a
• /
• pp.274-277
• /
• 2010

본 논문에서는 다층 퍼셉트론 신경회로망을 사용하여 각 프레임에서 유성음, 무성음, 그리고 묵음 구간을 검출하는 구간검출 알고리즘을 제안한다. 신경회로망의 입력으로는 고속 푸리에변환에 의한 전력스펙트럼 및 고속 푸리에변환 계수가 사용되어 네트워크가 학습된다. 본 실험에서는 원 음성에 백색잡음이 중첩된 음성을 신경회로망에 입력함으로서 각 프레임에서의 유성음, 무성음, 묵음 구간의 검출성능 결과를 나타낸다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.1
• /
• pp.28-32
• /
• 2014

For a signal such as speech showing piece-wise linear shape in a very short time period, a nonuniform sampling method based on the inflection point detection (IPD) is proposed to reduce data rate. The method exploits the geometrical characteristics of signal further than the existing local maxima/minima detection (MMD) based sampling method. As results, the reconstructed signal by the interpolation of the IPD based sampled data resembles the original speech more. Computer simulation shows that the proposed IPD based method produces about 9~23 dB improvement over the existing MMD method. To show the usefulness of the IPD technique, it is applied to speech coding, and compared to the continuously variable slope delta modulation (CVSD). The nonuniformly sampled data is binary coded with one bit flag set "1". Noninflection samples are not sent, but only flag bits set 0 are sent. The method shows 0.3 ~ 9 dB SNR and 0.5 ~ 1.3 mean opinion score (MOS) improvements over the CVSD.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.4
• /
• pp.817-822
• /
• 2011

This paper first proposes the speech recognition algorithm by detection of the speech and noise sections at each frame using a neural network training by back-propagation algorithm, then proposes the spectral subtraction method which removes the noises at each frame according to detection of the speech and noise sections. In this experiment, the performance of the proposed recognition system was evaluated based on the recognition rate using various speeches that are degraded by white noise and car noise. Moreover, experimental results of the noise reduction by the spectral subtraction method demonstrate using the speech and noise sections detecting by the speech recognition algorithm at each frame. Based on measuring signal-to-noise ratio, experiments confirm that the proposed algorithm is effective for the speech by corrupted the noise using signal-to-noise ratio.

• The Journal of the Acoustical Society of Korea
• /
• v.31 no.6
• /
• pp.353-358
• /
• 2012

This paper describes acoustic phonetic parameters for detecting nasal place in a knowledge-based speech recognition system. Initial acoustic phonetic parameters are selected by studying nasal production mechanisms which are radiation of the sound through the nasal cavity. Nasals are produced with differing articulatory configuration which can be classified by measuring acoustic phonetic parameters such as band energy ratio, band energy differences, formants and formant differences. These acoustic phonetic parameters were tested in a classification experiment among labial nasal, alveolar nasal and velar nasal. An overall classification rate of 57.5% is obtained using the proposed acoustic phonetic parameters on the TIMIT database.

• Proceedings of the IEEK Conference
• /
• 2000.09a
• /
• pp.149-152
• /
• 2000

본 연구에서는 기존의 통계 이론에 근거한 음성 검출 기법을 제안하는 음성 스펙트럼 모형화기법을 통해 개선시키고자 한다 기존의 방법과는 달리 음성을 하나의 단일 모형이 아닌 여러 클래스(class) 모형의 결합체로 간주한다. 각 클래스 모형의 추정을 위해 신호원 부호화(source coding)의 클러스터링(clustering)과 유사한 기법을 제안하고, 이를 이용한 두 가지의 검출 기법을 제안한다. 하나는 각각의 클래스에 대해 LRT(likelihood ratio test)를 수행하고, 이를 최종적으로 통합하는 기법이고 다른 하나는 각 클래스의 모형으로부터 혼합모형(mixture model)을 구하여 이를 이용하여 LRT를 수행하는 방법이다. 제안한 두 가지 방법 모두 비교적 적은 연산량 증가에도 불구하고 실험 결과 기존 방법에 비해 매우 우수한 성능을 보였다.

• Journal of IKEEE
• /
• v.13 no.2
• /
• pp.132-139
• /
• 2009

In this paper, a speech feature based double-talk detector method is proposed for an acoustic echo cancellation in hands-free communication system. The double-talk detector is an important element, since it controls the update of the adaptive filter for an acoustic echo cancellation. In previous research, the double talk detector is considered in the signal processing stage without taking the speech characteristics into account. However, in the proposed method, speech features which are used for the speech recognition is used for the discriminative features between the far-end and near-end speech. We obtained a substantial improvement over the previous double-talk detector methods using the only signal in time domain.

• Journal of Broadcast Engineering
• /
• v.23 no.1
• /
• pp.86-92
• /
• 2018

In this paper, we propose a method for coding history detection of digital speech signal. In digital speech communication and storage, the signal is encoded to reduce the number of bits. Therefore, when a speech signal waveform is given, we need to detect its coding history so that we can determine whether the signal is an original or an coded one, and if coded, determine the number of times of coding. In this paper, we propose a coding history detection method for 12.2kbps AMR codec in terms of original, single coding, and double coding. The proposed method extracts a speech-specific feature vector from the given speech, and models the feature vector using a deep neural network. We confirm that the proposed feature vector provides better performance in coding history detection than the feature vector computed from the general spectrogram.