• 음성과학
• /
• 제10권2호
• /
• pp.77-84
• /
• 2003

In this research, we seek the beginning of the speech and detect the stationary speech region using lip information. Performing running average of the estimated speech signal in the stationary region, we reduce the effect of musical noise which is inherent to the conventional MlMSE (Minimum Mean Square Error) speech enhancement algorithm. In addition to it, SFM (Spectral Flatness Measure) is incorporated to reduce the speech signal estimation error due to speaking habit and some lacking lip information. The proposed algorithm with Wiener filtering shows the superior performance to the conventional methods according to MOS (Mean Opinion Score) test.

• 한국통신학회논문지
• /
• 제23권7호
• /
• pp.1650-1658
• /
• 1998

본 논문에서는 이동통신 시스템의 반향을 제거하기 위해 음성부호화기에서 얻은 음성 분석 정보를 이용하여 반향을 제거하는 방법을 제시하였다. 반향 제거기 적응 알고리즘의 입력 신호로서 기존의 방법인 음성부호화기의 출력 음성신호를 사용하지 않고 음성 부호화기 디코더 과정에서 제공되어지는 여기 신호, 선형 예측 오차 신호를 사용하였다. 모의 실험을 위해 Normalized Least Mean Square(NLMS) 알고리즘을 이용한 적응 반향 제거기를 구성하였고, 기존의 음성신호를 사용하는 반향제거기에 비해 음성 부호화기에서 제공되어지는 음성의 여기 신호 성분을 적응 알고리즘 입력신호로 사용함으로써 40 dB Echo Return Loss Enhancement(ERLE)를 얻는데 걸리는 시간에 있어서 약 4배 정도의 빠른 속도를 얻을 수 있다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 ITC-CSCC -1
• /
• pp.466-469
• /
• 2002

Using intelligent information contained within the speech to identify the specific hidden data in the watermarked multimedia data is considered to be an efficient method to achieve the speech digital watermarking. This paper presents the performance comparison between various types of speech codec in order to determine an appropriate one to be used in digital watermarking applications. In the experiments, the speech signal encoded by four different types of speech codec, namely CELP, GSM, SBC and G.723.1codecs is embedded into a grayscale image, and theirs performance in term of speech recognition are compared. The method for embedding the speech signal into the host data is borrowed from a watermarking method based on the zerotrees of wavelet packet coefficients. To evaluate efficiency of the speech codec used in watermarking applications, the speech signal after being extracted from the attacked watermarked image will be played back to the listeners, and then be justified whether its content is intelligible or not.

• 음성과학
• /
• 제3권
• /
• pp.156-166
• /
• 1998

In this paper, I would like to propose a dividing method by estimating the inflection points and the average magnitude energy in speech signals. The method proposed in this paper gave not only a satisfactory solution for the problems on dividing method by zero-crossing rate, but could estimate the feature of the transient period after dividing the starting point and transient period in speech signals before steady state. In the results of the experiment carried out with monosyllabic speech, it was found that even through speech samples indicated in D.C. level, the staring and ending point of the speech signals were exactly divided by the method. In addition to the results, I could compare with the features, such as the length of transient period, the short term energy, the frequency characteristics, in each speech signal.

• 말소리와 음성과학
• /
• 제3권4호
• /
• pp.117-124
• /
• 2011

This study investigated the effects of the types of noise and signal to noise ratios (SNRs) on speech intelligibility of an adult with dysartrhia. Speech intelligibility was judged by 48 naive listeners using a word transcription task. Repeated measures design was used with the types of noise (multi-talker babble/environmental noise) and SNRs (0, +10 dB, +20 dB) as within-subject factors. The dependent measure was the percentage of correctly transcribed words. Results revealed that two main effects were statistically significant. Listeners performed significantly worse in the multi-talker babble condition than the environmental noise condition, and they performed significantly better at higher levels of SNRs. The current results suggested that the multi-talker babble and lower level of SNRs decreased the speech intelligibility of adults with dysarthria, and speech-language pathologists should consider environmental factors such as the types of noise and SNRs in evaluating speech intelligibility of adults with dysarthria.

• 한국정보통신학회논문지
• /
• 제15권10호
• /
• pp.2093-2099
• /
• 2011

음성 신호와 자동차 엔진 배기음 등의 소음이 섞인 신호에서 통계적 방법을 이용하여 음성 신호와 자동차 소음 신호를 분리하였다. 분리된 신호에서 음성신호를 구분해 내기 위해 128개의 원소를 갖는 신호 조각의 연속으로 신호를 재구성하고 각 신호 조각에 대해 FFT를 구하였다. 각 신호 조각의 FFT 계수 중에서 저주파 영역의 일부 계수 중 계수 각각에 대해 각 신호 조각 사이의 자기 공분산을 구하고 이들을 평균하였다. 그리고 linear regression을 이용 하여 평균 자기 공분산 값들을 연결하는 직선의 방정식을 구한 후 이 직선의 기울기를 비교하여 음성 신호와 자동차 소음 신호를 구분하는 방법을 제안하고 유용성을 확인하였다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1998년도 추계종합학술대회 논문집
• /
• pp.1183-1186
• /
• 1998

Adaptive nois canceller can extract the noiseremoved spech in noisy speech signal by adapting the filter-coefficients to the background noise environment. A kind of LMS algorithm is one of the most popular adaptive algorithm for noise cancellation due to low complexity, good numerical property and the merit of easy implementation. However there is the matter of increasing misadjustment at voiced speech signal. Therefore the demanded speech signal may be extracted. In this paper, we propose a fast and noise robust wavelet packet adaptive noise canceller with NLMS-SUM method LMS combined algorithm. That is, we decompose the frequency of noisy speech signal at the base of the proposed analysis tree structure. NLMS algorithm in low frequency band can efficiently dliminate the effect of the low frequency noise and SUM method LMS algorithm at each high frequency band can remove the high frequency nosie. The proposed wavelet packet adaptive noise canceller is enhanced the more in SNR and according to Itakura-Satio(IS) distance, it is closer to the clean speech signal than any other previous adaptive noise canceller.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제50권12호
• /
• pp.590-596
• /
• 2001

The pre-emphasis is an essential process for speech signal processing. Widely used two methods are the typical method using a fixed value near unity and te optimal method using the autocorrelation ratio of the signal. This study proposes a new pre-emphasis method using the short-term energy difference of speech signal, which can effectively compensate the glottal source characteristics and lip radiation characteristics. Using the proposed pre-emphasis, speech analysis, such as spectrum estimation, formant detection, is performed and the results are compared with those of the conventional two pre-emphasis methods. The speech analysis with 5 single vowels showed that the proposed method enhanced the spectral shapes and gave nearly constant formant frequencies and could escape the overlapping of adjacent two formants. comparison with FFT spectra had verified the above results and showed the accuracy of the proposed method. The computational complexity of the proposed method reduced to about 50% of the optimal method.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1997년도 추계학술대회 논문집 학회본부
• /
• pp.597-599
• /
• 1997

Cochannel speaker separation is employed when speech from two talkers has been summed into one signal and it is desirable to recover one or both of the speech signals from the composite signal. Cochannel speech occurs in many common situations such as when two AM signals containing speech are transmitted on the same frequency or when two people are speaking simultaneously (e. g., when talking on the telephone). In this paper, the method that separated the speech in such a situation is proposed. Especially, only the voiced sound of few sound states is separated. And the similarity of the signals by the cross correlation between the signals for exactness of original signal and separated signal is proved.

• 음성과학
• /
• 제5권1호
• /
• pp.151-165
• /
• 1999

This paper describes a series of researches to diagnose vocal diseases using the statistical method and the acoustic signal analysis method. Speech materials are collected at the hospital. Using the pathological database, the basic parameters for the diagnosis are obtained. Based on the statistical characteristics of the parameters, valid parameters are chosen and those are used to diagnose the pathological speech signal. Cepstrum is used to extract parameters which represents characteristics of pathological speech. 3 layered neural network is used to train and classify pathological speech into normal, benign and malignant case.