• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37A no.12
• /
• pp.1122-1132
• /
• 2012

Compressed sensing has been applied to many fields such as images, speech signals, radars, etc. It has been mainly applied to stationary signals, and reconstruction error could grow as compression ratios are increased by decreasing measurements. To resolve the problem, speech signals are divided into frames and processed in parallel. The frames are made sparse by dictionary learning, and adaptive compressed sensing is applied which designs the compressed sensing reconstruction matrix adaptively by using the difference between the sparse coefficient vector and its reconstruction. Through the proposed method, we could see that fast and accurate reconstruction of non-stationary signals is possible with compressed sensing.

• The Journal of the Acoustical Society of Korea
• /
• v.26 no.1
• /
• pp.16-24
• /
• 2007

Voice activity detectors (VADs) are important in wireless communication and speech signal processing. In the conventional VAD methods. an expression for the likelihood ratio test (LRT) based on statistical models is derived. Then, speech or noise is decided by comparing the value of the expression with a threshold. We propose a new method with the modified decision rule based on the Gaussian distribution and the uniformly most power (UMP) test. This method requires the distribution of the absolute value of the incoming speech signal. Then we can obtain the final decision through the relation between the Rayleigh distributions. This VAD method can detect speech without a priori signal-to-noise ratio (SNR) which is required in the conventional VAD algorithms. Additionally, in the various VAD performance tests, the proposed VAD method is shown to be more effective than the traditional scheme.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.7
• /
• pp.91-98
• /
• 2010

Large corpus-based concatenating Text-to-Speech (TTS) systems can generate natural synthetic speech without additional signal processing. Because the improvements in the natualness, personality, speaking style, emotions of synthetic speech need the increase of the size of speech DB, it is necessary to prune the redundant speech segments in a large speech segment DB. In this paper, we propose a new method to construct a segmental speech DB for the Korean TTS system based on a clustering algorithm to downsize the segmental speech DB. For the performance test, the synthetic speech was generated using the Korean TTS system which consists of the language processing module, prosody processing module, segment selection module, speech concatenation module, and segmental speech DB. And MOS test was executed with the a set of synthetic speech generated with 4 different segmental speech DBs. We constructed 4 different segmental speech DB by combining CM1(or CM2) tree clustering method and full DB (or reduced DB). Experimental results show that the proposed method can reduce the size of speech DB by 23% and get high MOS in the perception test. Therefore the proposed method can be applied to make a small sized TTS.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.7 no.5
• /
• pp.907-912
• /
• 2006

Pre-emphasizing the speech compensates for falloff at high frequencies. The most common form of pre-emphasis is y(n)=s(n)-A${\cdot}$s(n-1), where A typically lies between 0.9 and 1.0 in voiced signal. And, this value reflects the degree of pre-emphasis and equals R(1)/R(0) in conventional method. This paper proposes a new flattening method to compensate the weaked high frequency components that occur by vocal cord characteristic. We used QMF(Quardrature Mirror Filter) to minimize the output signal distortion. After using the QMF to compensate high frequency components, flattening process is followed by R(1)/R(0) at each frame. Experimental results show that the proposed method flattened the weaked high frequency components effectively than auto correlation method. Therefore, the flattening algorithm will apply in speech signal processing like speech recognition, speech analysis and synthesis.

• Journal of Electrical Engineering and Technology
• /
• v.11 no.2
• /
• pp.529-536
• /
• 2016

In this paper we proposed an unsupervised algorithm to estimate the reverberation time (RT) directly from the reverberant speech signal. For estimation process we use maximum likelihood estimation (MLE) which is a very well-known and state of the art method for estimation in the field of signal processing. All existing RT estimation methods are based on the decay rate distribution. The decay rate can be obtained either from the energy envelop decay curve analysis of noise source when it is switch off or from decay curve of impulse response of an enclosure. The analysis of a pre-existing method of reverberation time estimation is the foundation of the proposed method. In one of the state of the art method, the reverberation decay is modeled as a Laplacian distribution. In this paper, the proposed method models the reverberation decay as a Gamma distribution along with the unification of an effective technique for spotting free decay in reverberant speech. Maximum likelihood estimation technique is then used to estimate the RT from the free decays. The method was motivated by our observation that the RT of a reverberant signal when falls in specific range, then the decay rate of the signal follows Gamma distribution. Experiments are carried out on different reverberant speech signal to measure the accuracy of the suggested method. The experimental results reveal that the proposed method performs better and the accuracy is high in comparison to the state of the art method.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.8 no.5
• /
• pp.665-670
• /
• 2013

In this paper, we propose a new method of speech detection and phoneme segmentation. We investigate the effect of applying preemphasis FIR filtering on the speech signal before the usual speech detection that utilizes the energy profile for discriminating signals from background noise. By this procedure, only the speech section of low energy and frequency becomes distinct in energy profile. It is verified experimentally that the silence/speech boundary becomes sharper by applying the filtering compared to the conventional method. By applications of this procedure, phoneme segmentation is also found to be much facilitated.

• Journal of Korea Multimedia Society
• /
• v.19 no.7
• /
• pp.1127-1136
• /
• 2016

Speech enhancement algorithm plays an important role in numerous speech signal processing applications. Over the last few decades, many algorithms have been studied for speech enhancement. The algorithms are based on spectral subtraction, Wiener filter, and subspace method etc. They have good performance of speech enhancement, but the performance can be deteriorated in specific noises or low SNR environment. In this paper, a new speech enhancement algorithms are proposed based on adaptive noise canceller. And the proposed algorithm improved performance of adaptive noise cancelling using 2-D binary mask. From objective experimental index, it is confirmed that the proposed algorithm is useful and has better performance than recently proposed speech enhancement algorithms.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.6
• /
• pp.637-646
• /
• 2022

In this paper the comparative study on the pronunciation of Vietnamese learners and Koreans for the Korean syllable final double consonants was performed. For many errors and the suggested teaching methods related to the pronunciation of the Korean syllable final double consonants that were investigated and analyzed through linguistic research the results of this study by using the analysis tools of speech signal processing were confirmed. Thus, we suggest the new educational method in this paper. Using SVM, which is widely used in machine learning of artificial intelligence the pronunciation of Vietnamese learners and that of Koreans were compared. Being able to obtain the decision hyperplane of the SVM means that Vietnamese learners' pronunciation of the Korean syllable final double consonants is quite different from that of Koreans. Otherwise their pronunciation are pretty similar each other. The new teaching method presented in this paper is not only composed of writing and listening but is included things such as the speech signal waveform in the time domain and its corresponding energy that can be visualized to the learners.

• Proceedings of the KSPS conference
• /
• 2002.11a
• /
• pp.179-182
• /
• 2002

The development of noise robust speech processing systems is becoming increasingly important as speech technology is currently widely applied in real world applications. Recently, to resolve such a noise problem, adaptive noise canceller(ANC) is frequently used, which is based upon adaptive filters. The adaptive recursive filters perform better than adaptive non-recursive filters due to the added poles, but the stability may be severely threatened. But these problems of adaptive recursive filters was solved by ACHARF algorithm. This paper presents a method which combines speaker verification system with ANC(Adaptive Noise Canceller) using the ACHARF algorithm. In the front-end stage, ANC is adopted to suppress the additive noise imposed on the speech signal. The results show that the performance of speaker verification system becomes better than before.

• Journal of the Korea Computer Industry Society
• /
• v.5 no.2
• /
• pp.269-274
• /
• 2004

Noisy speech recognition is one of most important problems in speech recognition. In this paper, a method which efficiently removes the mixed noise with speech, is proposed. The proposed method is based on the ICA to separate the mixed noise. ICA(Independent component analysis) is a signal processing technique, whose goal is to express a set of random variables as linear combinations of components that are statistically as independent from each other as possible.