• Journal of the Institute of Convergence Signal Processing
• /
• v.11 no.4
• /
• pp.289-297
• /
• 2010

In this paper, A method to prevent the external acoustic noise from being misrecognized as the speech recognition object is presented in the speech activity detection process for the speech recognition. Also this paper confirmed besides the acoustic energy to the lip movement image signals. First of all, the successive images are obtained through the image camera for personal computer and the lip movement whether or not is discriminated. The next, the lip movement image signal data is stored in the shared memory and shares with the speech recognition process. In the mean time, the acoustic energy whether or not by the utterance of a speaker is verified by confirming data stored in the shared memory in the speech activity detection process which is the preprocess phase of the speech recognition. Finally, as a experimental result of linking the speech recognition processor and the image processor, it is confirmed to be normal progression to the output of the speech recognition result if face to the image camera and speak. On the other hand, it is confirmed not to the output the result of the speech recognition if does not face to the image camera and speak. Also, the initial feature values under off-line are replaced by them. Similarly, the initial template image captured while off-line is replaced with a template image captured under on-line, so the discrimination of the lip movement image tracking is raised. An image processing test bed was implemented to confirm the lip movement image tracking process visually and to analyze the related parameters on a real-time basis. As a result of linking the speech and image processing system, the interworking rate shows 99.3% in the various illumination environments.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1993.06a
• /
• pp.259-262
• /
• 1993

In this paper, a new pitch beginning point detection method by extracting the G-peak, is proposed. By the speech production model, the area of the first peak on a pitch interval of speech signals is emphasized. By using the above characteristics, this method have more advantages than the others for pitch beginning point detection. The defective decision caused by an impulsive noise is minimized and the pre-filtering is not necessary for this method, because the integration of signals takes place in the process.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2001.10a
• /
• pp.265-270
• /
• 2001

Voice is one of the most efficient communication media and it includes several kinds of factors about speaker, context emotion and so on. Human emotion is expressed in the speech, the gesture, the physiological phenomena(the breath, the beating of the pulse, etc). In this paper, the method to have cognizance of emotion from anyone's voice signals is presented and simulated by using neuro-fuzzy model.

• The Journal of the Acoustical Society of Korea
• /
• v.38 no.4
• /
• pp.433-441
• /
• 2019

In this paper, a method of estimating speech parameters for ultrasonic Doppler signals reflected from the articulatory muscles using LSTM (Long Short Term Memory) RNN (Recurrent Neural Networks) was introduced and compared with the method using MLP (Multi-Layer Perceptrons). LSTM RNN were used to estimate the Fourier transform coefficients of speech signals from the ultrasonic Doppler signals. The log energy value of the Mel frequency band and the Fourier transform coefficients, which were extracted respectively from the ultrasonic Doppler signal and the speech signal, were used as the input and reference for training LSTM RNN. The performance of LSTM RNN and MLP was evaluated and compared by experiments using test data, and the RMSE (Root Mean Squared Error) was used as a measure. The RMSE of each experiment was 0.5810 and 0.7380, respectively. The difference was about 0.1570, so that it confirmed that the performance of the method using the LSTM RNN was better.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.9
• /
• pp.1673-1678
• /
• 2016

In the area of the speech recognition processing, background noises are caused the incorrect response to the speech input, therefore the speech recognition rates are decreased by the background noises. Accordingly, a more high level noise processing techniques are required since these kinds of noise countermeasures are not simple. Therefore, this paper proposes an algorithm to distinguish between the stationary background noises or non-stationary background noises and the speech signal having short time duration in the noisy environments. The proposed algorithm uses the characteristic parameter of the improved speech signal as an important measure in order to distinguish different types of the background noises and the speech signals. Next, this algorithm estimates various kinds of the background noises using a multi-layer perceptron neural network. In this experiment, it was experimentally clear the estimation of the background noises and the speech signals.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.5
• /
• pp.807-812
• /
• 2020

This paper proposes a blind speech source separation algorithm using a microphone to separate only the target speech source signal in an environment in which various speech source signals are mixed. The proposed algorithm is a model of frequency domain representation based on independent component analysis method. Accordingly, for the purpose of verifying the validity of independent component analysis in the frequency domain for two speech sources, the proposed algorithm is executed by changing the type of speech sources to perform speech sources separation to verify the improvement effect. It was clarified from the experimental results by the waveform of this experiment that the two-channel speech source signals can be clearly separated compared to the original waveform. In addition, in this experiments, the proposed algorithm improves the speech source separation performance compared to the existing algorithms, from the experimental results using the target signal to interference energy ratio.

• The Journal of the Acoustical Society of Korea
• /
• v.20 no.2
• /
• pp.10-15
• /
• 2001

In this paper, we describe the comparison between the combination of features using a speech and music discrimination, which is classifying between speech and music on audio signals. Audio signals are classified into 3classes (speech, music, speech and music) and 2classes (speech, music). Experiments carried out on three types of feature, Mel-cepstrum, energy, zero-crossings, and try to find a best combination between features to speech and music discrimination. We using a Gaussian Mixture Model (GMM) for discrimination algorithm and combine different features into a single vector prior to modeling the data with a GMM. In 3classes, the best result is achieved using Mel-cepstrum, energy and zero-crossings in a single feature vector (speech: 95.1％, music: 61.9％, speech & music: 55.5％). In 2classes, the best result is achieved using Mel-cepstrum, energy and Mel-cepstrum, energy, zero-crossings in a single feature vector (speech: 98.9％, music: 100％).

• MALSORI
• /
• no.62
• /
• pp.85-96
• /
• 2007

In this paper, we carried out recognition experiments for noisy speech having various levels of car noise and output of an audio system using the speech interface. The speech interface consists of three parts: pre-processing, acoustic echo canceller, post-processing. First, a high pass filter is employed as a pre-processing part to remove some engine noises. Then, an echo canceller implemented by using an FIR-type filter with an NLMS adaptive algorithm is used to remove the music or speech coming from the audio system in a car. As a last part, the MMSE-STSA based speech enhancement method is applied to the out of the echo canceller to remove the residual noise further. For recognition experiments, we generated test signals by adding music to the car noisy speech from Aurora 2 database. The HTK-based continuous HMM system is constructed for a recognition system. Experimental results show that the proposed speech interface is very promising for robust speech recognition in a noisy car environment.

• Speech Sciences
• /
• v.7 no.1
• /
• pp.17-29
• /
• 2000

The STC(Sinusoidal Transform Coding) is a vocoding technique that uses a sinusoidal speech model to obtain high- quality speech at low data rate. It models and synthesizes the speech signal with fundamental frequency and its harmonic elements in frequency domain. To reduce the data rate, it is necessary to represent the sinusoidal amplitudes and phases with as small number of peaks as possible while maintaining the speech quality. As a basic research to develop a low-rate speech coding algorithm using the sinusoidal model, in this paper, we investigate the speech quality depending on the number of sinusoids. By varying the number of spectral peaks from 5 to 40 speech signals are reconstructed, and then their qualities are evaluated using spectral envelope distortion measure and MOS(Mean Opinion Score). Two approaches are used to obtain the spectral peaks: one is a conventional STFT (Short-Time Fourier Transform), and the other is a multiresolutional analysis method.

• Speech Sciences
• /
• v.8 no.4
• /
• pp.45-58
• /
• 2001

Modulated components of a speech signal are frequently used for speech coding, speech recognition, and speech synthesis. Time-frequency representation (TFR) reveals some information about instantaneous frequency, instantaneous bandwidth and boundary of each component of the considering speech signal. In many cases, the extraction of AM-FM components corresponding to instantaneous frequencies is difficult since the Fourier spectra of the components with time-varying instantaneous frequency are overlapped each other in Fourier frequency domain. In this paper, an efficient method decomposing speech signal into AM-FM components is proposed. A variable bandwidth filter is developed for the decomposition of speech signals with time-varying instantaneous frequencies. The variable bandwidth filter can extract AM-FM components of a speech signal whose TFRs are not overlapped in timefrequency domain. Also, amplitude and instantaneous frequency of the decomposed components are estimated by using Hilbert transform.