• The Journal of the Acoustical Society of Korea
• /
• v.21 no.2
• /
• pp.173-181
• /
• 2002

Generally the one of serious problems in Voice Activity Detection (VAD) is speech region detection in noise environment. Therefore, this paper propose the new method using energy, lsp varation. As a result of processing time and speech quality of the proposed algorithm, the processing time is reduced due to the accurate detection of inactive period, and there is almot no difference in the subjective quality test. As a result of bit rate, proposed algorithm measures the number of VAD=1 and the result shows predominant reduction of bit rate as SNR of noisy speech is low (about 5∼10 dB).

• Journal of the Institute of Convergence Signal Processing
• /
• v.4 no.2
• /
• pp.18-24
• /
• 2003

One of the most important subjects in the implementation of real time speech recognizer is to design both reliable VAD(Voice Activity Detection) and suitable speech feature vector. But, because it is difficult to calculate reliable VAD in the environment having surrounding noise, designed suitable speech feature vector may not be obtained. Solving this problem, in this paper, we implement not only short time power spectrum which is generally used but also two additive parameters, the comparison measure of spectrum density having robust property in noise and linear discriminant function using linear regression, then perform VAD by using the combination of each parameter having apt weight in other magnitudes of surrounding noise and confirm that proposed parameters show a robust characteristic in circumstances having surrounding noise by using DTW(Dynamic Time Waning) in recognition experiment.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.6 no.2
• /
• pp.237-242
• /
• 2011

This paper proposes a detection algorithm for each section which detects the voiced section, unvoiced section, and the silence section at each frame using a multi-layer perceptron neural network. First, a power spectrum and FFT (fast Fourier transform) coefficients obtained by FFT are used as the input to the neural network for each frame, then the neural network is trained using these power spectrum and FFT coefficients. In this experiment, the performance of the proposed algorithm for detection of the voiced section, unvoiced section, and silence section was evaluated based on the detection rates using various speeches, which are degraded by white noise and used as the input data of the neural network. In this experiment, the detection rates were 92% or more for such speech and white noise when training data and evaluation data were the different.

• Proceedings of the Acoustical Society of Korea Conference
• /
• autumn
• /
• pp.19-22
• /
• 2000

ITU-T 국제 표준화 기구에서 인터넷 폰과 화상회의를 목적으로 개발된 G.723.1 음성 부호화기는 잡음 구간에서의 전송률을 낮추기 위한 방법으로 VAD(Voice Activity Detector)와 CNG(Comfortable Noise Generator)를 사용하고 있다. 이중 VAD는 최종적으로 현재 프레임의 에너지 레벨을 비교하여 음성의 활동 유무를 판정하고 있다. 하지만 G.723.1 VAD에서는 보다 안정적인 판정을 위해 음성 활동 구간 사이에 삽입되어 있는 묵음 구간에 대해서는 거의 대부분 음성이 활동하는 영역으로 판정을 하고 있다. 따라서 본 논문에서는 묵음 구간에 대해 보다 정확한 판정을 통하여 기존의 방법에 비해 전송률을 더욱 감소시킬 수 있는 방법을 제안한다. 제안한 방법은 음성신호와 잡음신호의 LSP 파라미터 간격 정보를 이용하여 음성구간을 검출한다. 묵음구간을 길게 조절한 문장을 사용하여 실험한 결과 VAD=1로 판정한 프레임수가 약 $48.98\%$ 감소하였으며 주관적인 음질평가의 경우 음질의 열하는 거의 발생하지 않았다.

• The Journal of the Acoustical Society of Korea
• /
• v.31 no.3
• /
• pp.161-169
• /
• 2012

This paper presents a robust speech end-point detector using double talk detection in echoic conditioned speech recognition robot. The proposed method consists of combining conventional end-point detector result and double talk detector result. We have tested the proposed method in isolated word recognition system under echoic conditioned environment. As a result, the proposed algorithm shows superior performance of 30 % to the available techniques in the points of speech recognition rates.

• Journal of Digital Convergence
• /
• v.13 no.10
• /
• pp.313-318
• /
• 2015

A traditional speech enhancement methods distort the sound spectrum generated according to estimation of the remaining noise, or invalid noise is a problem of lowering the speech recognition performance. In this paper, we propose a speech detection method that convergence the sound energy distribution process and sound energy parameters. The proposed method was used to receive properties reduce the influence of noise to maximize voice energy. In addition, the smaller value from the feature parameters of the speech signal The log energy features of the interval having a more of the log energy value relative to the region having a large energy similar to the log energy feature of the size of the voice signal containing the noise which reducing the mismatch of the training and the recognition environment recognition experiments Results confirmed that the improved recognition performance are checked compared to the conventional method. Car noise environment of Pause Hit Rate is in the 0dB and 5dB lower SNR region showed an accuracy of 97.1% and 97.3% in the high SNR region 10dB and 15dB 98.3%, showed an accuracy of 98.6%.

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.5
• /
• pp.441-446
• /
• 2009

This paper proposes an automatic indexing algorithm of golf video using audio information. In the proposed algorithm, the input audio stream is demultiplexed into the stream of video and audio. By means of Adaboost-cascade classifier, the continuous audio stream is classified into announcer's speech segment recorded in studio, music segment accompanied with players' names on TV screen, reaction segment of audience according to the play, reporter's speech segment with field background, filed noise segment like wind or waves. And golf swing sound including drive shot, iron shot, and putting shot is detected by the method of impulse onset detection and modulation spectrum verification. The detected swing and applause are used effectively to index action or highlight unit. Compared with video based semantic analysis, main advantage of the proposed system is its small computation requirement so that it facilitates to apply the technology to embedded consumer electronic devices for fast browsing.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.10a
• /
• pp.824-826
• /
• 2015

최근 음성인식 시스템의 성능 향상은 많이 개선되었지만 아직도 잡음과 같은 문제로 인하여 문제점이 나타나고 있다. 음성인식 시스템에 있어서의 잡음 문제를 해결함으로써 인식 성능을 향상할 목적으로 본 논문에서는 단시간 스펙트럼에 기초한 주파수특성을 고려한 위너필터를 사용한 잡음 차감 알고리즘을 제안한다. 제안한 알고리즘은 먼저 각 프레임에서 문턱값을 검출한 후에 비묵음 구간과 묵음 구간을 식별한다. 각 프레임에 대해서 비묵음 구간에서는 위너필터법에 의한 잡음 차감법을 실시하며, 묵음 구간에 대해서는 일반적인 잡음 차감법을 적용한다.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1998.06e
• /
• pp.305-308
• /
• 1998

본 논문에서는 핵심어 검출의 성능을 향상시키기 위한 새로운 후처리 방법을 제안한다. 일반적으로 핵심어 검출 시스템에 의해 검출된 상위 n개의 후보 단어들의 우도(likelihood)는 비슷한 경우가 많다. 따라서, 한 음성구간에 대해 음향학적으로 유사한 핵심어들간의 오인식 가능성이 높아진다. 그러나 기존의 핵심어 검출에 사용된 후처리 방법은 음성의 모든 구간에 같은 비중을 두고 우도를 평가하므로 비슷한 음향학적 특징을 가지는 유사한 핵심어들의 비교에 적합하지 못하다. 이를 해결하기 위하여, 본 논문에서는 후보단어들의 부분적인 음향학적 특징 차이에 기반한 가중치를 우도 계산 시에 반영함으로써 보다 변별력을 높이는 알고리즘을 제안한다. 실험 결과, 제안된 방법을 이용하여 유사한 후보단어들간의 변별력을 높일 수 있었고, 인식율이 93%일 때, 우도비검사 방법에 비해 19.6%의 false alarm rate을 감소시킬 수 있었다.

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.7
• /
• pp.674-679
• /
• 2009

This paper proposes a method of player event retrieval using combination of two functions: detection of player name in speech information and detection of sound event from audio information in golf videos. The system consists of indexing module and retrieval module. At the indexing time audio segmentation and noise reduction are applied to audio stream demultiplexed from the golf videos. The noise-reduced speech is then fed into speech recognizer, which outputs spoken descriptors. The player name and sound event are indexed by the spoken descriptors. At search time, text query is converted into phoneme sequences. The lists of each query term are retrieved through a description matcher to identify full and partial phrase hits. For the retrieval of the player name, this paper compares the results of word-based, phoneme-based, and hybrid approach.