• Journal of the Korean Society for Precision Engineering
• /
• v.23 no.5 s.182
• /
• pp.68-76
• /
• 2006

The ability to recognize human emotion is one of the hallmarks of human-robot interaction. Hence this paper describes the realization of emotion recognition. For emotion recognition from voice, we propose a new feature called frequency range of meaningful signal. With this feature, we reached average recognition rate of 76% in speaker-dependent. From the experimental results, we confirm the usefulness of the proposed feature. We also define the noise environment and conduct the noise-environment test. In contrast to other features, the proposed feature is robust in a noise-environment.

• Speech Sciences
• /
• v.11 no.1
• /
• pp.7-20
• /
• 2004

In this paper, we propose a two-step noise compensation algorithm in feature extraction for achieving robust speech recognition. The proposed method frees us from requiring a priori information on noisy environments and is simple to implement. First, in frequency domain, the Harmonics-based Spectral Subtraction (HSS) is applied so that it reduces the additive background noise and makes the shape of harmonics in speech spectrum more pronounced. We then apply a judiciously weighted variance Feature Vector Normalization (FVN) to compensate for both the channel distortion and additive noise. The weighted variance FVN compensates for the variance mismatch in both the speech and the non-speech regions respectively. Representative performance evaluation using Aurora 2 database shows that the proposed method yields 27.18% relative improvement in accuracy under a multi-noise training task and 57.94% relative improvement under a clean training task.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2015.07a
• /
• pp.9-12
• /
• 2015

In this paper, we propose a new feature matching algorithm by modifying and combining the FAST(Features from Accelerated Segment Test) feature detector and SURF feature descriptor which is robust to the distortion of the given image. Scale space is generated to consider the variation of the scale and determine the candidate of features in the image robust to the noise. The original FAST algorithm results in many feature points along edges. To solve this problem, we apply the principal curvatures for refining it. We also use SURF descriptor to make it robust against the variations in the image by rotation. Through the experiments, it is shown that the proposed algorithm has better performance than the conventional feature matching algorithms even though it has much less computational load. Especially, it shows a strength for noisy images.

• Phonetics and Speech Sciences
• /
• v.5 no.1
• /
• pp.11-16
• /
• 2013

This paper proposes robust feature extraction for accurate voice activity detection (VAD). VAD is one of the principal modules for speech signal processing such as speech codec, speech enhancement, and speech recognition. Noisy environments contain nonstationary noises causing the accuracy of the VAD to drastically decline because the fluctuation of features in the noise intervals results in increased false alarm rates. In this paper, in order to improve the VAD performance, harmonic-weighted energy is proposed. This feature extraction method focuses on voiced speech intervals and weighted harmonic-to-noise ratios to determine the amount of the harmonicity to frame energy. For performance evaluation, the receiver operating characteristic curves and equal error rate are measured.

• IEIE Transactions on Smart Processing and Computing
• /
• v.1 no.3
• /
• pp.143-151
• /
• 2012

A new data-driven method for the design of a blind modulation frequency filter that suppresses the slow-varying noise components is proposed. The proposed method is based on the temporal local decorrelation of the feature vector sequence, and is done on an utterance-by-utterance basis. Although the conventional modulation frequency filtering approaches the same form regardless of the task and environment conditions, the proposed method can provide an adaptive modulation frequency filter that outperforms conventional methods for each utterance. In addition, the method ultimately performs channel normalization in a feature domain with applications to log-spectral parameters. The performance was evaluated by speaker-independent isolated-word recognition experiments under additive noise environments. The proposed method achieved outstanding improvement for speech recognition in environments with significant noise and was also effective in a range of feature representations.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.51 no.3
• /
• pp.122-128
• /
• 2002

In this paper, a robust pattern classification of breath sounds for the diagnosis of pulmonary dysfunction in noise environment is proposed. The feature parameter extraction method by highpass lifter algorithm and PM(projection measure) algorithm are used. 17 different groups of breath sounds are experimentally classified and investigated. The classification has been performed by 6 different types of combinations with proposed methods to evaluate the performances, such as ARC with EDM and LCC with EDM, WLCC with EDM, ARC with PM, LCC with PM, WLCC with PM. Furthermore, all feature parameters are extracted to 80th orders by 5th orders step, and all experiments are evaluated in increasing noise environments by degrees SNR 24dB to 0dB. As a results, WLCC which is derived from highpass lifter algorithm, is selected for the feature parameter extraction method. Pm is more robust than EDM in noisy environments to test and compare experimental results. WLCC with PM method(WLCC/PM) has a better performance in an increasing noise environment for diagnosis of pulmonary dysfunction.

• ETRI Journal
• /
• v.35 no.3
• /
• pp.512-522
• /
• 2013

In this paper, the radius weight mean (RWM) and the feature-embedding technique are used to present a novel watermarking scheme for color images. Simulations validate that the stego-images generated by the proposed scheme are robust against most common image-processing operations, such as compression, color quantization, bit truncation, noise addition, cropping, blurring, mosaicking, zigzagging, inversion, (edge) sharpening, and so on. The proposed method possesses outstanding performance in resisting high compression ratio attacks: JPEG2000 and JPEG. Further, to provide extra hiding storage, a steganographic method using the RWM with the least significant bit substitution technique is suggested. Experiment results indicate that the resulting perceived quality is desirable, whereas the peak signal-to-noise ratio is high. The payload generated using the proposed method is also superior to that generated by existing approaches.

• MALSORI
• /
• no.63
• /
• pp.125-137
• /
• 2007

Recently, many techniques have been proposed to improve the noise robustness for speaker verification. In this paper, we consider the feature recombination technique in multi-band approach. In the conventional feature recombination for speaker verification, to compute the likelihoods of speaker models or universal background model, whole feature components are used. This computation method is not effective in a view point of multi-band approach. To deal with non-effectiveness of the conventional feature recombination technique, we introduce a subband likelihood computation, and propose a modified feature recombination using subband likelihoods. In decision step of speaker verification system in noise environments, a few very low likelihood scores of a speaker model or universal background model cause speaker verification system to make wrong decision. To overcome this problem, a reliable feature selection method is proposed. The low likelihood scores of unreliable feature are substituted by likelihood scores of the adaptive noise model. In here, this adaptive noise model is estimated by maximum a posteriori adaptation technique using noise features directly obtained from noisy test speech. The proposed method using subband-based reliable feature selection obtains better performance than conventional feature recombination system. The error reduction rate is more than 31 % compared with the feature recombination-based speaker verification system.

• ETRI Journal
• /
• v.30 no.1
• /
• pp.89-100
• /
• 2008

We consider the feature recombination technique in a multiband approach to speaker identification and verification. To overcome the ineffectiveness of conventional feature recombination in broadband noisy environments, we propose a new subband feature recombination which uses subband likelihoods and a subband reliable-feature selection technique with an adaptive noise model. In the decision step of speaker recognition, a few very low unreliable feature likelihood scores can cause a speaker recognition system to make an incorrect decision. To overcome this problem, reliable-feature selection adjusts the likelihood scores of an unreliable feature by comparison with those of an adaptive noise model, which is estimated by the maximum a posteriori adaptation technique using noise features directly obtained from noisy test speech. To evaluate the effectiveness of the proposed methods in noisy environments, we use the TIMIT database and the NTIMIT database, which is the corresponding telephone version of TIMIT database. The proposed subband feature recombination with subband reliable-feature selection achieves better performance than the conventional feature recombination system with reliable-feature selection.

• The Journal of the Acoustical Society of Korea
• /
• v.23 no.2
• /
• pp.180-186
• /
• 2004

The presence of noise in speech signals degrades the performance of recognition systems in which there are mismatches between the training and test environments. To make a speech recognizer robust, it is necessary to compensate these mismatches. In this paper, we studied about an improvement of stochastic feature extraction based on band-SNR for robust speech recognition. At first, we proposed a modified version of the multi-band spectral subtraction (MSS) method which adjusts the subtraction level of noise spectrum according to band-SNR. In the proposed method referred as M-MSS, a noise normalization factor was newly introduced to finely control the over-estimation factor depending on the band-SNR. Also, we modified the architecture of the stochastic feature extraction (SFE) method. We could get a better performance when the spectral subtraction was applied in the power spectrum domain than in the mel-scale domain. This method is denoted as M-SFE. Last, we applied the M-MSS method to the modified stochastic feature extraction structure, which is denoted as the MMSS-MSFE method. The proposed methods were evaluated on isolated word recognition under various noise environments. The average error rates of the M-MSS, M-SFE, and MMSS-MSFE methods over the ordinary spectral subtraction (SS) method were reduced by 18.6%, 15.1%, and 33.9%, respectively. From these results, we can conclude that the proposed methods provide good candidates for robust feature extraction in the noisy speech recognition.