• The Journal of Korean Institute of Communications and Information Sciences
• /
• 제40권5호
• /
• pp.924-930
• /
• 2015

In this paper, we propose a novel approach of low computational complexity to improve the speech quality of the small acoustic equipment in noisy environment. The conventional gain control algorithm suppresses the noise of input signal, and then the part of wide dynamic range compression (WDRC) amplifies the undesired signal. The proposed algorithm controls the gain of hearing aids according to speech present probability by using the output of a voice activity detection (VAD). The performance of the proposed scheme is evaluated under various noise conditions by using objective measurement and yields superior results compared with the conventional algorithm.

• 전자공학회논문지 IE
• /
• 제44권4호
• /
• pp.1-10
• /
• 2007

In this thesis, we study the implementation of hands-free phone in a car, taking acoustic echo canceller, in order to remove acoustic echo effectively. Conventional coustic echo canceller used for only adaptive filtering has much difficulty to solve both echo and double-talk problem. To tackle this problem, we propose acoustic echo canceller consisting of adaptive filter using a modified NLMS, VAD to catch exact voice activity duration using two independent forgetting factors, double-talk detector to detect fast and precise double talk duration using cross-correlation between microphone signal and residual echo, and output controller using VAD and double-talk detector. The proposed hands-free phone taking acoustic echo canceller shows the performance that has not acoustic echo and guarantees full duplex.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 한국음향학회 2000년도 하계학술발표대회 논문집 제19권 1호
• /
• pp.103-106
• /
• 2000

무제한 인식 시스템을 구현하기 위해서는 적절한 인식단위, 훈련 데이터 베이스의 확보, 인식단위의 분할, 인식 알고리즘과 같은 문제점을 모두 해결하여야 한다. 따라서 본 논문에서는 무제한 음성인식 시스템의 인식의 기본 단위로 모음의 안정구간을 검출하여 분할하는 CV(Consonant-Vowel), VC(Vowel-Consonant), VC CV(Vowel-Consonant-Consonant-Vowel)단위와 분할 파라미터를 제안하고, 분할 실험을 통해 그 유효성을 확인하고자 한다.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 한국음향학회 2002년도 하계학술발표대회 논문집 제21권 1호
• /
• pp.25-28
• /
• 2002

Voice activity detection is important Problem in the speech recognition and communication. This paper introduces feature parameter which is reconstructed by the spectral entropy of information theory for the robust voice activity detection in the noise environment, analyzes and compares it with the energy method of voice activity detection and performance. In experiment, we confirmed that the spectral entropy is more feature parameter than the energy method for the robust voice activity detection in the various noise environment.

• Journal of Veterinary Clinics
• /
• 제18권4호
• /
• pp.329-333
• /
• 2001

Evaluation on the diagnostic performances of urease test and polymerase chain reaction (PCR) for detection of Helicobacter species infection in dogs has rarely been performed in research with site-specific situations, although assessing diagnostic tests is an essential part prior to its practical use in a variety of clinical settings. The clinical value of a diagnostic test may be misjudged and comparisons between different tests may yield misleading conclusions when high within-patient correlations are present. We applied a conceptually simple statistical approach to estimate the sensitivity and specificity of urease test and PCR for detection of Helicobacter species infection in dogs. This approach assumes that responses from three different sampling sites within an animal are correlated where unit for statistical analysis is the site rather than the animal. The sensitivity and specificity of urease test was 0.74% (95% confidence interval, 0.64-0.84) and 0.87 (95% CI, 0.67-1.00), respectively. For PCR, the sensitivity was 0.95(95% CI, 0.89-1.00) and specificity 0.90 (95% CI, 0.70-1.00). Two tests were almost equally specific. Urease test, however, has a lower diagnostic accuracy and thus should only be used after careful validation in terms of sensitivity.

• The Journal of the Acoustical Society of Korea
• /
• 제19권6호
• /
• pp.53-61
• /
• 2000

In the speech recognition under the noisy environments, reducing the mismatch introduced between training and testing environments is an important issue. Spectral subtraction is widely used technique because of its simplicity and relatively good performance in noisy environments. In this paper, we introduce histogram method as a reliable noise estimation approach for spectral subtraction. This method has advantages over the conventional noise estimation methods in that it does not need to detect non-speech intervals and it can estimate the noise spectra even in time-varying noise environments. Even though spectral subtraction is performed using a reliable average noise spectrum by the histogram method, considerable amount of residual noise remains due to the variations of instantaneous noise spectrum about mean. To overcome this limitation, we propose a new over-estimation technique based on distribution characteristics of histogram used for noise estimation. Since the proposed technique decides the degree of over-estimation adaptively according to the measured noise distribution, it has advantages to be few the influence of the SNR variation on the noise levels. According to speaker-independent isolated word recognition experiments in car noise environment under various SNR conditions, the proposed histogram-based over-estimation technique outperforms the conventional over-estimation technique.

• Speech Sciences
• /
• 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.

• The Transactions of the Korea Information Processing Society
• /
• 제5권12호
• /
• pp.3047-3062
• /
• 1998

This paper deseribes the desihn and the implementation of the Realtime Transport Protocol(RTP)/ Rdaltime Control Protocol(RTCP) (RFC 1889,1890) that is used to transmit the audio/video data to any destination and to feedback the Quality of Service (QoS) information of the received media data to the sender, in the teleconferencing systems proposed by ITU-T. These protocols are implemented with multi thead technique and run on top of UDP/IP-Multicast through the socket interface as the underlying protocol. The upper layer is impelmented such that in can be accessed by the H245 comference control protocol. The RTP packetizes the digitized audio/video data from the encoder info a fixed format, and multieast to the participants. The RTCP monitors RTP packets and extracts the QoS values from it such as round-trip delay, jiter and packet loss to form RTCP packets and non periokically sends them to the sender site. In this Paper, we also descritx the study of measurement and analysis for QoS factors that observed on performing teleconferencing system over Internet. The results from this experiment is indicate that RTT and Jitter value are acceptable even entwork load is high. However, it appears that packet loss rate is high in daytime and most losses periods have length one or two.