• Journal of KIISE:Software and Applications
• /
• v.31 no.6
• /
• pp.799-807
• /
• 2004

In this paper, we deal with an emotion recognition method using facial images and speech signal. Six basic human emotions including happiness, sadness, anger, surprise, fear and dislike are investigated. Emotion recognition using the facial expression is performed by using a multi-resolution analysis based on the discrete wavelet transform. And then, the feature vectors are extracted from the linear discriminant analysis method. On the other hand, the emotion recognition from speech signal method has a structure of performing the recognition algorithm independently for each wavelet subband and then the final recognition is obtained from a multi-decision making scheme.

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.3
• /
• pp.18-25
• /
• 1997

This study describes a modified preemphasis formula, what we call energy-dependent preemphasis(EDP). This uses the normalized short-term energy of speech signal, with the assumption that the source characteristics of the glottal pulses and the radiation characteristics of the lips are approximately proportional to the energy of speech signal. Using this method, speech analyses, such as AR spectrum estimation, formant detection, are performed for nonstationary starting parts of 5 Korean single vowels. The results are compared with the conventional two preemphasis methods. We found that the proposed preemphasis gave enhanced spectral shapes and more accurate formant frequencies and avoided overlapping phenomenon of adjacent two formants.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.2
• /
• pp.185-192
• /
• 2013

In this paper, proposed to improve the performance of speech and mixed content signal classification using MFCC based on GMM probability model used for the MPEG USAC(Unified Speech and Audio Coding) standard. For effective pattern recognition, the Gaussian mixture model (GMM) probability model is used. For the optimal GMM parameter extraction, we use the expectation maximization (EM) algorithm. The proposed classification algorithm is divided into two significant parts. The first one extracts the optimal parameters for the GMM. The second distinguishes between speech and mixed content signals using MFCC feature parameters. The performance of the proposed classification algorithm shows better results compared to the conventionally implemented USAC scheme.

• Phonetics and Speech Sciences
• /
• v.1 no.3
• /
• pp.95-102
• /
• 2009

In this paper, an efficient target speech detection algorithm is proposed for the performance improvement of multi-input speech enhancement. Using the normalized cross correlation value between two selected channels, the proposed algorithm estimates the probabilistic distribution function of the value from the pure noise interval. Then, log-likelihoods are calculated with the function and the normalized cross correlation value to detect the target speech interval precisely. The detection results are applied to the generalized sidelobe canceller-based algorithm. Experimental results show that the proposed algorithm significantly improves the speech recognition performance and the signal-to-noise ratios.

• Speech Sciences
• /
• v.10 no.1
• /
• pp.85-94
• /
• 2003

In this paper an algorithm to reduce the size of Text-to-Speech database is proposed. The algorithm is based on the characteristics of Korean phonemic units. From the initial database, a reduced phoneme unit set is induced by articulatory similarity of concatenating phonemes. Speech data is read by one female announcer for 1000 phonetically balanced sentences. All the recorded speech is then segmented by phoneticians. Total size of the original speech data is about 640 MB including laryngograph signal. To synthesize wave, RE-PSOLA (Residual-Excited Pitch Synchronous Overlap and Add Method) was used. The voice quality of synthesized speech was compared with original speech in terms of spectrographic informations and objective tests. The quality of the synthesized speech is not much degraded when the size of synthesis DB was reduced from 320 MB to 82 MB.

• The Journal of the Acoustical Society of Korea
• /
• v.19 no.7
• /
• pp.42-47
• /
• 2000

This paper describes a real-time implementation of a GSM-EFR (Global System for Mobil communications Enhanced Full Rate) speech coder using OakDSP core; a 16bit fixed-point Digital Signal Processor (DSP) by DSP Group, Inc. The real-time implemented speech coder required about 24MIPS for computation and 7.06K words and 12.19K words for code and data memory, respectively. The implemented GSM-EFR speech coder passes all of test vectors provided by ETSI (European Telecommunication Standard Institute), and perceptual speech quality measurement using MNB algorithm shows that the quality of the GSM-EFR speech coder is similar to the one of 32kbps ADPCM. The real-time implemented GSM-EFR speech coder which is the highest bit-rate mode of the GSM-AMR speech coder will be used as the basic structure of the GSM-AMR speech coder which is embedded in MODEM ASIC of IMT2000 asynchronous mode mobile station.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.35S no.12
• /
• pp.93-102
• /
• 1998

In noisy environments, human speech productions are influenced by noises(Lombard effect), and speech signals are contaminated. These distortions dramatically reduce the performance of speech recognition systems. This paper proposes a method of the Lombard effect compensation and noise suppression in order to improve speech recognition performance in noise environments. To estimate the intensity of the Lombard effect which is a nonlinear distortion depending on the ambient noise levels, speakers, and phonetic units, we formulate the measure of the Lombard effect level based on the acoustic speech signal, and the measure is used to compensate the Lombard effect. The distortions of speech under noisy environments are cancelled out as follows. First, spectral subtraction and band-pass filtering are used to cancel out noise. Second, energy nomalization is proposed to cancel out the variation of vocal intensity by the Lombard effect. Finally, the Lombard effect level controls the transform which converts Lombard speech cepstrum to clean speech cepstrum. The proposed method was validated on 50 korean word recognition. Average recognition rates were 82.6%, 95.7%, 97.6% with the proposed method, while 46.3%, 75.5%, 87.4% without any compensation at SNR 0, 10, 20 dB, respectively.

• The Journal of the Acoustical Society of Korea
• /
• v.30 no.7
• /
• pp.383-389
• /
• 2011

In this paper, we propose a improved speech absence probability estimation algorithm by applying environmental noise classification for speech enhancement. The previous speech absence probability required to seek a priori probability of speech absence was derived by applying microphone input signal and the noise signal based on the estimated value of a posteriori SNR threshold. In this paper, the proposed algorithm estimates the speech absence probability using noise classification algorithm which is based on Gaussian mixture model in order to apply the optimal parameter each noise types, unlike the conventional fixed threshold and smoothing parameter. Performance of the proposed enhancement algorithm is evaluated by ITU-T P.862 PESQ (perceptual evaluation of speech quality) and composite measure under various noise environments. It is verified that the proposed algorithm yields better results compared to the conventional speech absence probability estimation algorithm.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.27 no.3A
• /
• pp.196-204
• /
• 2002

The Sinusoidal Transform Coding(STC) is a vocoding scheme based on a sinusoidal model of a speech signal. The low bit-rate speech coding based on sinusoidal model is a method that models and synthesizes speech with fundamental frequency and its harmonic elements, spectral envelope and phase in the frequency region. In this paper, we propose the 2.4kbps low-rate speech coding algorithm using the sinusoidal model of a speech signal. In the proposed coder, the pitch frequency is estimated by choosing the frequency that makes least mean squared error between synthetic speech with all spectrum peaks and speech synthesized with chosen frequency and its harmonics. The spectral envelope is estimated using SEEVOC(Spectral Envelope Estimation VOCoder) algorithm and the discrete all-pole model. The phase information is obtained using the time of pitch pulse occurrence, i.e., the onset time, as well as the phase of the vocal tract system. Experimental results show that the synthetic speech preserves both the formant and phase information of the original speech very well. The performance of the coder has been evaluated in terms of the MOS test based on informal listening tests, and it achieved over the MOS score of 3.1.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.2
• /
• pp.161-168
• /
• 2021

In this paper, a Silent Speech Interface (SSI) technology was proposed in which Doppler frequency shifts of the reflected signal were used to synthesize the speech signals when 40kHz ultrasonic signal was incident to speaker's mouth region. In SSI, the mapping rules from the features derived from non-speech signals to those from audible speech signals was constructed, the speech signals are synthesized from non-speech signals using the constructed mapping rules. The mapping rules were built by minimizing the overall errors between the estimated and true speech parameters in the conventional SSI methods. In the present study, the mapping rules were constructed so that the distribution of the estimated parameters is similar to that of the true parameters by using Generative Adversarial Networks (GAN). The experimental result using 60 Korean words showed that, both objectively and subjectively, the performance of the proposed method was superior to that of the conventional neural networks-based methods.