AutoSSR: an efficient approach for automatic spontaneous speech recognition model for the Punjabi Language

Kumar, Yogesh; Singh, Navdeep; Kumar, M. G. Sharavana; Singh, Amitoj

doi:10.1007/s00500-020-05248-1

Cited by 19 publications

(3 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, because viewers are increasingly likely to use online media platforms, the only method to distinguish between fake and true news is to apply artificial intelligence algorithms to detect them automatically. Infact, textbased approaches to detecting fake news have been tried in the past, but they have not achieved the expected results [8].…”

Section: Fig1: Samples Of Fake News Articlesmentioning

confidence: 99%

WITHDRAWN: Fake News Detection Using Ensemble Techniques

Malhotra

Malik

2023

Preprint

View full text Add to dashboard Cite

Fake news is misinformation or distorted news that is spread over social media with the intent of harming an individual, organization, or government body. Collecting news from an internet platform is simple because it is quick, user-friendly, and constantly updated. However, this information is also subject to personal preferences or interests, which can negatively affect individuals or organizations. As a result, it is critical to detect the spread of fake news by computational methods. Semantic web approaches also plays an important role in detecting false news since they are used to understand the data that is available online in the same manner that humans do. As a result, this research examined various learning models for classifying whether the information is true or false using a fake and real news dataset. Around 40,000 items were analyzed, including approximately 20,000 from each fake and actual news dataset. Ensemble learning models such as support vector machine, logistic regression, CatBoost, XgBoost, multinomial, Naive Bayes, and random forest were used and evaluated using recall, accuracy, false rejection rate (FRR), F1 score, precision, negative predictive value (NPV), false discovery rate (FDR), and Matthews' correlation coefficient. Based on these evaluations, the best learning models were hybridized and computed alongside the passive-aggressive classifier and deep Auto_ViML model. Following computation, it was determined that the deep Auto_ViML model had the highest accuracy, precision, recall, and F1 score of 99%. In contrast, the hybrid learning model had the best value of false rejection rate of 71%. In comparison, the support vector machine was computed in 0.000245 seconds.

show abstract

Section: Fig1: Samples Of Fake News Articlesmentioning

confidence: 99%

WITHDRAWN: Fake News Detection Using Ensemble Techniques

Malhotra

Malik

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…GMM–HMM and DNN–HMM with the experimental configuration detailing significant RI of 4–5% and 1–3%, respectively Shivakumar et al [ 5 ] English language children dataset employing transfer learning MFCC-based GMM–HMM and DNN–HMM-based modeling The paper presents a systematic and an extensive analysis of the proposed transfer learning technique considering the key factors affecting children’s speech recognition from prior literature. Evaluations are presented by making the comparisons of earlier GMM–HMM and the newer DNN Models such that the author had experimented for the detailed effectiveness of standard adaptation techniques versus transfer learning Kumar et al [ 42 ] Adult data comprising of 13,218 Punjabi words with over 200 min of recorded speech MFCC feature extraction technique In this paper, the author has experimented for auto-denoising method employing the novel Corpus Optimization Algorithm on the Punjabi language corpus. At the same time, for 13,218 Punjabi words, the WER was lowered to 5.8%.…”

Section: Resultsmentioning

confidence: 99%

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

Bawa

Kadyan

Tripathy³

et al. 2022

Complex Intell. Syst.

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

“…The most swift and inherent mode of conveyance between humans is through the speech. Ever since the pre-history of humans to today s world, speech communication is the foremost mode of social bonding and information exchange among humans [2]. The speech signal has some embedded information in the form of emotions [3], [4].…”

Section: Introductionmentioning

confidence: 99%

Impact of Feature Extraction and Feature Selection Algorithms on Punjabi Speech Emotion Recognition Using Convolutional Neural Network

Kaur

Singh

2022

ACM Trans. Asian Low-Resour. Lang. Inf. Process.

View full text Add to dashboard Cite

The challenge to refine the spontaneity and productivity of a machine and human coherence, speech emotion recognition has been an overriding area of research. The trustability and fulfillment of such emotion recognition are largely involved with the feature extraction and selection processes. An important role is played in exploring and distinguishing audio content during the feature extraction phase. Also, the features that have been extracted should be tough to a number of disturbances and reliable enough for an adequate classification system. This paper focuses on three main components of a Speech Emotion Recognition (SER) Process. The first one is the optimal feature extraction method for Punjabi SER system. The second one is the use of an appropriate feature selection method that desires to select effectual features from the ones extracted in the first step, and removes the redundant features, to improve the conduct of emotion recognition. The third one is the classification model that has been used further for emotion recognition. So, the scope of this paper is to explain the three main steps of Punjabi SER system, feature extraction, feature selection, and emotion recognition with classifier. The results have been calculated and compared for number of feature set combinations, with and without feature selection process. A total of 10 experiments are carried out and various performance metrics such as precision, recall, F1-score, accuracy, etc. are used to demonstrate the results.

show abstract

AutoSSR: an efficient approach for automatic spontaneous speech recognition model for the Punjabi Language

Cited by 19 publications

References 26 publications

WITHDRAWN: Fake News Detection Using Ensemble Techniques

WITHDRAWN: Fake News Detection Using Ensemble Techniques

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

Impact of Feature Extraction and Feature Selection Algorithms on Punjabi Speech Emotion Recognition Using Convolutional Neural Network

Contact Info

Product

Resources

About