FEATURE EXTRACTION ALGORITHM USING NEW CEPSTRAL TECHNIQUES FOR ROBUST SPEECH RECOGNITION

A statistically designed Automatic Speech Recognition (ASR) system extracts features from speech signals using feature extraction methods, links the extracted features with the expected phonetics of the hypothesis using acoustic models, uses language model to add prior information about the structure of the target language. For many years, Mel-frequency Cepstral coefficients (MFCC), n-gram, and Hidden Markov Model (HMM) approaches have been used predominantly for feature extraction, language modeling and acoustic modeling, respectively. However, performance degradation of MFCC in noisy conditions and inaccuracy of HMMs while handling large vocabularies have made researchers to propose more efficient methods. The proposed work uses noise robust method Gammatone Frequency Cepstral Coefficients(GFCC) for feature extraction, trigram language modeling, and HMM-Gaussian mixture model (GMM) based acoustic modeling to implement a continuous Hindi language ASR system. Also, it applies Differential Evolution (DE) technique to refine the GFCC features and discriminative techniques to enhance performance of the acoustic model. The performance of the implemented system has been evaluated by using different feature extraction methods, variants of n-gram language modeling techniques and different discriminative techniques in clean as well as noisy conditions. Initially, the results reveal that DE optimized GFCC with HMM-Gaussian Mixture Model (GMM) acoustic modeling performs better than MFCC, PLP and MF-PLP feature extraction methods. Secondly, the experimental results show that the Minimum Phone Error (MPE) outperforms Maximum Mutual Information (MMI) and Maximum Likelihood Estimation (MLE) and trigram based language modeling gives more accurate results than unigram and bigram language modeling. Finally, it has been concluded that the continuous Hindi language ASR system implemented using DE refined GFFC feature extraction method with MPE discriminative training technique and trigram based language modeling gives better accuracy in clean as-well-as noisy environments.

Performance evaluation of Hindi speech recognition system using optimized filterbanks

This paper describes a study of a set of features based on cepstral mean and variance normalization (CMVN) plus auto regressive moving average (ARMA) filtering technique which is called MVA and on histogram equalization (HEQ) for robust speech recognition. First, we use MVA then HEQ in combination with CMVN and ARMA filtering as a post-processing module to mel frequency cepstral coefficients (MFCC), Relative Spectral-Perceptual linear prediction (RASTA-PLP) and power normalized cepstral coefficients (PNCC) features to improve the performance of the automatic speech recognition (ASR) system. The results on the Arabic database task have shown that both methods MVA and HEQ+ARMA improves the success rate for all features compared to the baseline system however HEQ was not found to perform better than MVA. The results also provide that RASTA-PLP outperforms PNCC and MFCC features.

An auditory-based feature extraction algorithm is proposed for enhancing the robustness of automatic speech recognition. In the proposed approach, the speech signal is characterized using a new feature referred to as the Basilar-membrane Frequency-band Cepstral Coefficient (BFCC). In contrast to the conventional Mel-Frequency Cepstral Coefficient (MFCC) method based on a Fourier spectrogram, the proposed BFCC method uses an auditory spectrogram based on a gammachirp wavelet transform in order to more accurately mimic the auditory response of the human ear and improve the noise immunity. In addition, a Hidden Markov Model (HMM) is used for both training and testing purposes. The evaluation results obtained using the AURORA 2 noisy speech database show that compared to the MFCC method, the proposed scheme improves the speech recognition rate by 15% on average given speech samples with Siganl-to-Noise Ratios (SNRs) ranging from 0 to 20 dB. Thus, the proposed method has significant potential for the development of robust speech recognition systems for ambient assisted living.

This research presents a development of the affine projection algorithm (APA) in voice communication applications. A method of controlling the parameters of the APA is devised to improve the performance in cancelling various types of ambient noise that could possibly corrupt speech signals in voice communication systems. Indicators are used to identify the type of noise accompanying the target signal. Then the corrupted signal is processed in a noise a cancellation setup in such a way that three parameters of algorithm are changed according to the nature of the noise. The spreading of elements in the covariance matrix of the noise is used as an indicator for the type of noise so that the projection order, step-size and filter length are changed at the same time. This way the performance of the canceller is improved rendering lower estimation error with a moderate computational power. The method was tested under various types of noise and showed better convergence performance than the original APA as well as other commonly used algorithms in noise cancellation systems. The MSE of the proposed VPAPA method drops to -65 dB in steady state compared to -20 dB using NLMS and just below -30 dB using standard APA with projection order of 8, while the powerful RLS reaches around -60dB under the same environment. The method can be useful for clearer voice communication in variable environmental noise.

A technique for suppressing the effect of any type of impulsive noise in the context of automatic speech recognition (ASR) is presented. The authors suggest the interposition in the mel frequency cepstral coefficients (MFCC) feature extraction front-end of (i) an identification stage responsible for the detection of corrupted cepstral vectors and (ii) a restoration stage that acts locally on the degraded cepstrum.

An automatic speech recognition (ASR) is commonly used in these days. Current ASR systems perform well in ideal environment; however, it does not perform well in realistic noisy environment. As a robust ASR, ETSI has standardized Advanced Front-End (AFE) that adopts two-stage of iterative Wiener filter (IWF) to realize a speech enhancement as the front-end of ASR. In the ETSI AFE, 16 kHz speech is divided uniformly by QMF (Quadrature Mirror Filter) into lower-band and higher-band signal and only lower-band signal is emphasized by the IWF and MFCC (Mel Frequency Cepstral Coefficient) is extracted from both the second-stage of emphasized lower-band signal and non-emphasized higher-band signal. FFT is used to estimate speech spectrum that designs the Wiener filter. On the other hand, we have already proposed robust complex speech analysis for an analytic signal. It can estimate more robust and more accurate speech spectrum due to the introduced robust criterion and nature of analytic signal. This paper proposes an improved AFE using wide-band robust ELS (Extended Least Square) complex analysis and real-valued analysis instead of FFT. Moreover, the QMF synthesis is also introduced for second-stage of wide-band analysis. The experimental results using the CENSREC-2 speech database demonstrate that the performance is improved.

The strength and shape of the dose-response relationship between different types of noise and myocardial infarction (MI) remain unclear. Therefore, we aimed to summarize the evidence of the association between various types of noise and MI incidence and mortality through a dose-response meta-analysis. We performed a systematic search of the PubMed, Embase, and Web of Science databases up to December 19, 2021. The generalized least-squares method and restricted cubic splines were used to assess the potential linear and nonlinear dose-response relationships between noise exposure and the risk of MI events. Twenty observational studies with 34 reports met the eligibility criteria. In the linear models, the pooled relative risk and corresponding 95% confidence interval (CI) for MI incidence was 1.04 (95% CI: 1.02 - 1.05), and the MI mortality was 1.02 (95% CI: 1.02 - 1.03) for each 10dB(A) increase in noise exposure. In addition, we observed an approximately J-shaped dose-response relationship between noise and MI mortality (Pnonlinearity = 0.0037), whereas the threshold for the statistical impact of noise on MI mortality may be 42dB(A). Our findings support the notion that various types of noise exposure have a positive dose-response relationship with the risk of MI incidence and mortality.

Robustness of the automatic speech recognition (ASR) system relies upon the accuracy of feature extraction and classification in training phase. The mismatch between training and testing conditions during classification of large feature vectors causes a low performance. In this paper, the issue of robustness of acoustic information is addressed for practical Punjabi dataset. Traditional feature extraction approaches: mel frequency cepstral coefficients (MFCC) and gammatone frequency cepstral coefficients (GFCC) face the issue of high variance with leakage of spectral information. Also, handling of the huge number of feature information creates chaos for large speech vocabulary. To overcome this dilemma, a Principal component analysis (PCA) based multi-windowing technique is proposed with the incorporation of baseline GFCC and MFCC based feature approaches after the tuning of taper parameter. The proposed integrated approaches result in better feature vectors, which are further processed using differential evolution + hidden Markov model (DE + HMM) based modelling classifier. The integrated approaches show substantial performance for word recognition as compared to the conventional or fused feature extraction systems.

Linear discriminant analysis (LDA) has long been used to derive data-driven temporal filters in order to improve the robustness of speech features used in speech recognition. In this paper, we proposed the use of new optimization criteria of principal component analysis (PCA) and the minimum classification error (MCE) for constructing the temporal filters. Detailed comparative performance analysis for the features obtained using the three optimization criteria, LDA, PCA, and MCE, with various types of noise and a wide range of SNR values is presented. It was found that the new criteria lead to superior performance over the original MFCC features, just as LDA-derived filters can. In addition, the newly proposed MCE-derived filters can often do better than the LDA-derived filters. Also, it is shown that further performance improvements are achievable if any of these LDA/PCA/MCE-derived filters are integrated with the conventional approach of cepstral mean and variance normalization (CMVN). The performance improvements obtained in recognition experiments are further supported by analyses conducted using two different distance measures.

The contribution of type and levels of community noises to the perception of loudness, noisiness, and annoyance is being explored in ongoing research projects. Particular attention has been given to the relationship between scaling method and the conclusions it is possible to draw from the data, especially with regard to observers' abilities to differentiate noises according to the above attributes. Procedures for calibrating and possibly standardizing the perceptual scales have been attempted with preliminary success. Various types of noises have been investigated: aircraft noise under different flying conditions, traffic noise, and a number of other community noises. Besides specific scaling problems, the investigations have addressed the specific problems of observers' abilities to differentiate among noises that are combined in a complex setting as well as their ability to integrate various noises into a unitary perception of loudness and annoyance. Since the experimental setups reflect real‐life situations, the answers to these latter questions are relevant to understanding the responses of the individual who is exposed to combinations of noises in his or her community.The contribution of type and levels of community noises to the perception of loudness, noisiness, and annoyance is being explored in ongoing research projects. Particular attention has been given to the relationship between scaling method and the conclusions it is possible to draw from the data, especially with regard to observers' abilities to differentiate noises according to the above attributes. Procedures for calibrating and possibly standardizing the perceptual scales have been attempted with preliminary success. Various types of noises have been investigated: aircraft noise under different flying conditions, traffic noise, and a number of other community noises. Besides specific scaling problems, the investigations have addressed the specific problems of observers' abilities to differentiate among noises that are combined in a complex setting as well as their ability to integrate various noises into a unitary perception of loudness and annoyance. Since the experimental setups reflect real‐life situ...

We investigate the use of Fourier plane nonlinear filtering for phase-encoded images. We investigate the performance of the nonlinear joint transform correlator and the nonlinearly transformed matched filter for phase-encoded images with different types of input noise. We use the peak-to-output-energy ratio, peak-to-sidelobe ratio, and discrimination ratio as the metrics for measuring the performances. We mathematically analyze the peak-to-output-energy ratio of the nonlinearly transformed matched filter for phase-encoded images with spatially nonoverlapping white noise. Computer simulations are provided to show the performance improvements of the nonlinear filtering techniques for the phase-encoded images. In comparison with linear filtering techniques, we find that the nonlinear filtering techniques substantially improve the performance metrics. From the computer-simulation results it can be seen that the nonlinear joint transform correlator performs better than the nonlinearly transformed matched filter in detecting phase-encoded targets in the presence of different types of noise, such as additive overlapping white noise, spatially nonoverlapping white background noise, spatially nonoverlapping colored background noise, and nontarget objects.

The objective of this work is to study the speaker-specific nature of analytic phase of speech signals. Since computation of analytic phase suffers from phase wrapping problem, we have used its derivative- The instantaneous frequency for feature extraction. The cepstral coefficients extracted from smoothed subband instantaneous frequencies (IFCC) are used as features for speaker verification. The performance of IFCC features is evaluated on NIST-2003 speaker recognition evaluation database and is compared with baseline mel-frequency cepstral coefficients (MFCC). The performance of IFCC features is observed to be comparable with MFCC features in terms of equal error rates and minimum detection cost function values. Different strategies for evaluating the speaker verification performance of IFCC and MFCC are explored and it is found that the evaluation based on cosine similarity delivers better performance than other strategies under consideration.

Realistic thermal conditions with various humidity levels have been considered to examine the combined effects of noise and thermal conditions on indoor environmental perceptions. Subjective assessments of temperature, humidity and psychoacoustics were conducted with 26 subjects under combined environments of seven thermal conditions (18℃: RH 30, 60%, 24℃: RH 27, 43, 65%, 30℃: RH 30, 60%), two noise types (fan and babble noises) and five noise levels (45, 50, 55, 60 and 65 dBA). Three-minute moderate noise exposure did not affect temperature or humidity sensations. However, the temperature and humidity levels affected loudness, annoyance and acoustic preferences when noise was presented as babble. Fan noise perceptions were found to be independent of thermal conditions. Gender differences were clearly found in terms of thermal and psychoacoustic perceptions. Men were more sensitive to hot sensations than women, and women were more sensitive to arid sensations than men. Women were more sensitive to noise levels than men. Gender differences were also found in terms of different types of noise. Men were found to be significantly less sensitive to fan noise than women. Even though psychoacoustic parameters were affected by indoor thermal conditions, thermal parameters were not affected by short-term moderate noise. The combined effect of various types of noise and temperature is still unclear, and this will be considered in a future larger cohort study.

Electrocardiogram (ECG) signals are crucial for monitoring cardiac activity and diagnosing various cardiovascular conditions. However, these signals are often contaminated by different types of noise, such as baseline wander, muscle artifacts, and power line interference, which can obscure critical information and hinder accurate diagnosis. This study used a 1-Dimensional Convolutional Neural Network (1D CNN) architecture with seven convolutional layers for denoising ECG signals. The model utilizes a fully convolutional autoencoder approach, comprising an encoder that transforms noisy input signals into compact feature representations and a decoder that reconstructs the cleaned signals. The proposed architecture was tested using the MIT-BIH Noise Stress Test Database, which includes ECG recordings with simulated noise conditions. Performance evaluation metrics such as Mean Squared Error (MSE), Signal-to-Noise Ratio (SNR), and Mean Absolute Deviation (MAD) were used to assess the model's effectiveness. Results showed a low MSE of 0.034, a high SNR of 15.8 dB, and a MAD of 0.754, indicating significant noise reduction and high-quality signal reconstruction. These findings demonstrate that the 1D CNN architecture effectively reduces various types of noise in ECG signals, thereby enhancing signal quality and facilitating more accurate analysis and diagnosis. The model's ability to maintain the integrity of crucial ECG features while removing noise suggests its potential utility in clinical applications for improving cardiovascular disease diagnosis