• The Journal of the Acoustical Society of Korea
• /
• v.16 no.1E
• /
• pp.15-23
• /
• 1997

Zero-Crossings with Peak Amplitudes(ZCPA) model motivated by human auditory periphery was proposed to extract reliable features speech signals even in noisy environments for robust speech recognition. In this paper, some practical considerations for digital hardware implementations of the ZCPA model are addressed and evaluated for recognition of speech corrupted by several real world noises as well as white Gaussian noise. Infinite impulse response(IIR) filters which constitute the cochliar filterbank of the ZCPA are replaced by hamming bandpass filters of which frequency responses are less similar to biological neural tuning curves. Experimental results demonstrate that the detailed frequency response of the cochlear filters are not critical to performance. Also, the sensitivity of the model output to the variations in microphone gain is investigated, and results in good reliability of the ZCPA model.

• 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 IEEK Conference
• /
• 2007.07a
• /
• pp.289-290
• /
• 2007

In order to improve the performance of a speech recognition system in the presence of noise, we propose a noise robust front-end using two-channel speech signals by separating speech from noise based on the computational auditory scene analysis (CASA). The main cues for the separation are interaural time difference (ITD) and interaural level difference (ILD) between two-channel signal. As a result, we can extract 39 cepstral coefficients are extracted from separated speech components. It is shown from speech recognition experiments that proposed front-end has outperforms the ETSI front-end with single-channel speech.

• 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.

• The Journal of the Acoustical Society of Korea
• /
• v.38 no.6
• /
• pp.670-677
• /
• 2019

As the presence of background noise in acoustic signal degrades the performance of speech or acoustic event recognition, it is still challenging to extract noise-robust acoustic features from noisy signal. In this paper, we propose a combined structure of Wasserstein Generative Adversarial Network (WGAN) and MultiTask AutoEncoder (MTAE) as deep learning architecture that integrates the strength of MTAE and WGAN respectively such that it estimates not only noise but also speech features from noisy acoustic source. The proposed MTAE-WGAN structure is used to estimate speech signal and the residual noise by employing a gradient penalty and a weight initialization method for Leaky Rectified Linear Unit (LReLU) and Parametric ReLU (PReLU). The proposed MTAE-WGAN structure with the adopted gradient penalty loss function enhances the speech features and subsequently achieve substantial Phoneme Error Rate (PER) improvements over the stand-alone Deep Denoising Autoencoder (DDAE), MTAE, Redundant Convolutional Encoder-Decoder (R-CED) and Recurrent MTAE (RMTAE) models for robust speech recognition.

• Journal of Broadcast Engineering
• /
• v.8 no.2
• /
• pp.198-203
• /
• 2003

We develop the method of estimating the endpoints of speech by jointly using the lip motion (visual speech) and speech being included in multimedia data and then propose a new speech recognition system (SRS) based on that method. The endpoints of noisy speech are estimated as follows : For each test word, two kinds of endpoints are detected from visual speech and clean speech, respectively Their difference is made and then added to the endpoints of visual speech to estimate those for noisy speech. This estimation method for endpoints (i.e. speech interval) is applied to form a new SRS. The SRS differs from the convention alone in that each word model in the recognizer is provided an interval of speech not Identical but estimated respectively for the corresponding word. Simulation results show that the proposed method enables the endpoints to be accurately estimated regardless of the amount of noise and consequently achieves 8 o/o improvement in recognition rate.

• MALSORI
• /
• no.60
• /
• pp.145-164
• /
• 2006

This paper proposes class histogram equalization (CHEQ) to compensate noisy acoustic features for robust speech recognition. CHEQ aims to compensate for the acoustic mismatch between training and test speech recognition environments as well as to reduce the limitations of the conventional histogram equalization (HEQ). In contrast to HEQ, CHEQ adopts multiple class-specific distribution functions for training and test environments and equalizes the features by using their class-specific training and test distributions. According to the class-information extraction methods, CHEQ is further classified into two forms such as hard-CHEQ based on vector quantization and soft-CHEQ using the Gaussian mixture model. Experiments on the Aurora 2 database confirmed the effectiveness of CHEQ by producing a relative word error reduction of 61.17% over the baseline met-cepstral features and that of 19.62% over the conventional HEQ.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.4
• /
• pp.775-780
• /
• 2013

This paper proposes a speaker-dependent speech recognition algorithm which can classify the gender for male and female speakers in white noise and car noise, using a neural network. The proposed speech recognition algorithm is trained by the neural network to recognize the gender for male and female speakers, using LPC (Linear Predictive Coding) cepstrum coefficients. In the experiment results, the maximal improvement of total speech recognition rate is 96% for white noise and 88% for car noise, respectively, after trained a total of six neural networks. Finally, the proposed speech recognition algorithm is compared with the results of a conventional speech recognition algorithm in the background noisy environment.

• IEIE Transactions on Smart Processing and Computing
• /
• v.3 no.5
• /
• pp.259-266
• /
• 2014

In this paper, we propose a novel technique for noise robust automatic speech recognition (ASR). The development of ASR techniques has made it possible to recognize isolated words with a near perfect word recognition rate. However, in a highly noisy environment, a distinct mismatch between the trained speech and the test data results in a significantly degraded word recognition rate (WRA). Unlike conventional ASR systems employing Mel-frequency cepstral coefficients (MFCCs) and a hidden Markov model (HMM), this study employ histogram of oriented gradient (HOG) features and a Support Vector Machine (SVM) to ASR tasks to overcome this problem. Our proposed ASR system is less vulnerable to external interference noise, and achieves a higher WRA compared to a conventional ASR system equipped with MFCCs and an HMM. The performance of our proposed ASR system was evaluated using a phonetically balanced word (PBW) set mixed with artificially added noise.

• ETRI Journal
• /
• v.46 no.1
• /
• pp.22-34
• /
• 2024

Exposure to varied noisy environments impairs the recognition performance of artificial intelligence-based speech recognition technologies. Degraded-performance services can be utilized as limited systems that assure good performance in certain environments, but impair the general quality of speech recognition services. This study introduces an audiovisual speech recognition (AVSR) model robust to various noise settings, mimicking human dialogue recognition elements. The model converts word embeddings and log-Mel spectrograms into feature vectors for audio recognition. A dense spatial-temporal convolutional neural network model extracts features from log-Mel spectrograms, transformed for visual-based recognition. This approach exhibits improved aural and visual recognition capabilities. We assess the signal-to-noise ratio in nine synthesized noise environments, with the proposed model exhibiting lower average error rates. The error rate for the AVSR model using a three-feature multi-fusion method is 1.711%, compared to the general 3.939% rate. This model is applicable in noise-affected environments owing to its enhanced stability and recognition rate.