In domain training data augmentation on noise robust Punjabi Children speech recognition

Kadyan, Virender; Bawa, Puneet; Hasija, Taniya

doi:10.1007/s12652-021-03468-3

Cited by 14 publications

(6 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Environmental sound classification and acoustic scene classification ResNet [45,70,97,112] Autoencoder DNN [98][99][100]120] Snore sound classification, speech emotion recognition, and respiratory sound classification Gated Recurrent Unit (GRU) [24,128,175] Various applications Deep neural network (DNN) [77,121,125,128,146] CNN [32,40,76,81,86,88,96,128,140,157,161,165,167,173,174,177,178,180] Deep CNN (DCNN) [102,111,179] Sound event detection, speaker detection…”

Section: Classification Methods Referencesmentioning

confidence: 99%

A review on lung disease recognition by acoustic signal analysis with deep learning networks

2023

View full text Add to dashboard Cite

Recently, assistive explanations for difficulties in the health check area have been made viable thanks in considerable portion to technologies like deep learning and machine learning. Using auditory analysis and medical imaging, they also increase the predictive accuracy for prompt and early disease detection. Medical professionals are thankful for such technological support since it helps them manage further patients because of the shortage of skilled human resources. In addition to serious illnesses like lung cancer and respiratory diseases, the plurality of breathing difficulties is gradually rising and endangering society. Because early prediction and immediate treatment are crucial for respiratory disorders, chest X-rays and respiratory sound audio are proving to be quite helpful together. Compared to related review studies on lung disease classification/detection using deep learning algorithms, only two review studies based on signal analysis for lung disease diagnosis have been conducted in 2011 and 2018. This work provides a review of lung disease recognition with acoustic signal analysis with deep learning networks. We anticipate that physicians and researchers working with sound-signal-based machine learning will find this material beneficial.

show abstract

Section: Classification Methods Referencesmentioning

confidence: 99%

A review on lung disease recognition by acoustic signal analysis with deep learning networks

2023

View full text Add to dashboard Cite

show abstract

“…Class-dependent temporal-spectral structures and long-term descriptive statistics features were extracted for sound events. Other authors applied the Discrete Gabor Transform (DGT) audio image representation [119], multiresolution feature [53], hybrid method based on mel frequency cepstral coefficient and the gammatone frequency cepstral coefficient [62], inverted MFCC and extended MFCC [66], bag of audio words (BoAW) [120], narrow band auto-correlation features (NB-ACF) [121].…”

Section: Feature Extraction Methods In Sound Classificationmentioning

confidence: 99%

“…Despite the shortfalls identified in the selected articles, we also identified that the application of data augmentation methods in sound classification research has shown significant progress in the last five years, between 2017 and 2022. Advancement of classification or recognition of a sound dataset with integration of data augmentation techniques has helped to improve the generalization ability as recorded by the authors in [62,69,72,92,98,103]. Second, the introduction of class-specific data augmentation techniques in imbalanced datasets has helped to overcome the problem of overfitting [67,86,92,104] and thus increasing prediction performance [58,61] and classification stability [59,65,66,69,91,106].…”

Section: Classification Methods For Sound Classificationmentioning

confidence: 99%

Data Augmentation and Deep Learning Methods in Sound Classification: A Systematic Review

et al. 2022

View full text Add to dashboard Cite

The aim of this systematic literature review (SLR) is to identify and critically evaluate current research advancements with respect to small data and the use of data augmentation methods to increase the amount of data available for deep learning classifiers for sound (including voice, speech, and related audio signals) classification. Methodology: This SLR was carried out based on the standard SLR guidelines based on PRISMA, and three bibliographic databases were examined, namely, Web of Science, SCOPUS, and IEEE Xplore. Findings. The initial search findings using the variety of keyword combinations in the last five years (2017–2021) resulted in a total of 131 papers. To select relevant articles that are within the scope of this study, we adopted some screening exclusion criteria and snowballing (forward and backward snowballing) which resulted in 56 selected articles. Originality: Shortcomings of previous research studies include the lack of sufficient data, weakly labelled data, unbalanced datasets, noisy datasets, poor representations of sound features, and the lack of effective augmentation approach affecting the overall performance of classifiers, which we discuss in this article. Following the analysis of identified articles, we overview the sound datasets, feature extraction methods, data augmentation techniques, and its applications in different areas in the sound classification research problem. Finally, we conclude with the summary of SLR, answers to research questions, and recommendations for the sound classification task.

show abstract

“…Consequently, the class probability for particular utterance at a given time of such structure is obtained using a SoftMax nonlinearity using the following equation: where corresponds to an activation function corresponding to output layer at a particular HMM state . Therefore, an optimization of a given objective function is usually trained using a standard error-back propagation procedure [ 13 ]. It is performed by evaluating a natural cost function C as demonstrated in the following equation by utilizing SoftMax output function.…”

Section: Theoretical Backgroundmentioning

confidence: 99%

“…The extracted feature vectors are though well efficient in capturing relevant information while discarding the redundancies originated due to presence of noise in an input speech signal. Therefore, various feature extraction techniques: RASTA-PLP [ 12 ], MFCC [ 13 ], GFCC [ 14 ] and PNCC [ 15 ] have been investigated by various researchers with an effort of deploying an effective noise-robust ASR system. For the past many years, HMM has been a widely adapted modeling technique for efficient learning of parameters corresponding to an acoustic model [ 16 ].…”

Section: Introductionmentioning

confidence: 99%

Developing sequentially trained robust Punjabi speech recognition system under matched and mismatched conditions

Bawa

Kadyan

Tripathy³

et al. 2022

Complex Intell. Syst.

Self Cite

View full text Add to dashboard Cite

Development of a native language robust ASR framework is very challenging as well as an active area of research. Although an urge for investigation of effective front-end as well as back-end approaches are required for tackling environment differences, large training complexity and inter-speaker variability in achieving success of a recognition system. In this paper, four front-end approaches: mel-frequency cepstral coefficients (MFCC), Gammatone frequency cepstral coefficients (GFCC), relative spectral-perceptual linear prediction (RASTA-PLP) and power-normalized cepstral coefficients (PNCC) have been investigated to generate unique and robust feature vectors at different SNR values. Furthermore, to handle the large training data complexity, parameter optimization has been performed with sequence-discriminative training techniques: maximum mutual information (MMI), minimum phone error (MPE), boosted-MMI (bMMI), and state-level minimum Bayes risk (sMBR). It has been demonstrated by selection of an optimal value of parameters using lattice generation, and adjustments of learning rates. In proposed framework, four different systems have been tested by analyzing various feature extraction approaches (with or without speaker normalization through Vocal Tract Length Normalization (VTLN) approach in test set) and classification strategy on with or without artificial extension of train dataset. To compare each system performance, true matched (adult train and test—S1, child train and test—S2) and mismatched (adult train and child test—S3, adult + child train and child test—S4) systems on large adult and very small Punjabi clean speech corpus have been demonstrated. Consequently, gender-based in-domain data augmented is used to moderate acoustic and phonetic variations throughout adult and children’s speech under mismatched conditions. The experiment result shows that an effective framework developed on PNCC + VTLN front-end approach using TDNN-sMBR-based model through parameter optimization technique yields a relative improvement (RI) of 40.18%, 47.51%, and 49.87% in matched, mismatched and gender-based in-domain augmented system under typical clean and noisy conditions, respectively.

show abstract

In domain training data augmentation on noise robust Punjabi Children speech recognition

Cited by 14 publications

References 63 publications

A review on lung disease recognition by acoustic signal analysis with deep learning networks

A review on lung disease recognition by acoustic signal analysis with deep learning networks

Data Augmentation and Deep Learning Methods in Sound Classification: A Systematic Review

Developing sequentially trained robust Punjabi speech recognition system under matched and mismatched conditions

Contact Info

Product

Resources

About