Feature Extraction Techniques in Speech Processing: A Survey

Hibare, Rekha; Vibhute, Anup

doi:10.5120/18744-9997

Cited by 26 publications

(7 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The wavelet packet 2D decomposes the images into four subbands namely approximate, horizontal, vertical, and details [43]. In WPD, each subband can be further decomposed up to a different level as shown in Fig.…”

Section: Feature Engineeringmentioning

confidence: 99%

Malaria cell image classification by explainable artificial intelligence

Raihan

Nahid

2021

Health Technol.

View full text Add to dashboard Cite

Malaria is one of the most common diseases in the world. It is caused by Plasmodium parasites and spreads among humans by the bite of female Anopheles mosquitoes. Only in 2019, children under the age of five accounted for 67% of all malaria deaths. The diagnosing process of malaria can be error-prone due to an inexperienced pathologist and may take a longer time. In this paper, we have presented a malaria detection framework based on wavelet packet 2d, Convolutional Neural Network. (CNN), and Whale Optimization Algorithm (WOA). We have extracted a global feature set using the wavelet packet 2D and CNN. Further, we removed noisy features and selected an effective feature using WOA and XGBoost. The selected feature set is almost half of the initial feature set. Additionally, we have used SHapley Additive exPlanations (SHAP) to interpret the trained model and assess the significance of each feature. Based on the selected feature set, the XGBoost algorithm provides accuracy, precision, recall, and F1 score of 94. 78%, 94. 39%, 95. 21%, and 94. 80% respectively.

show abstract

Section: Feature Engineeringmentioning

confidence: 99%

Malaria cell image classification by explainable artificial intelligence

Raihan

Nahid

2021

Health Technol.

View full text Add to dashboard Cite

show abstract

“…The coefficients of the difference equation characterize the formants and the numbers which describe the formants and the residue are stored. LPC is a powerful speech analysis method and it has gained fame as a formant estimation method [43].…”

Section: ) Mfcc Based Featuresmentioning

confidence: 99%

A Hybrid Meta-Heuristic Feature Selection Method for Identification of Indian Spoken Languages From Audio Signals

et al. 2020

View full text Add to dashboard Cite

With the recent advancements in the fields of machine learning and artificial intelligence, spoken language identification-based applications have been increasing in terms of the impact they have on the day-to-day lives of common people. Western countries have been enjoying the privilege of spoken language recognition-based applications for a while now, however, they have not gained much popularity in multi-lingual countries like India owing to various complexities. In this paper, we have addressed this issue by attempting to identify different Indian languages based on various well-known features like Mel-Frequency Cepstral Coefficient (MFCC), Linear Prediction Coefficient (LPC), Discrete Wavelet Transform (DWT), Gammatone Frequency Cepstral Coefficient (GFCC) as well as a few deep learning architecture based features like i-vector and x-vector extracted from the audio signals. After comparing the initial results, it is observed that the combination of MFCC and LPC produces the best results. Then we have developed a new nature-inspired feature selection (FS) algorithm by hybridizing Binary Bat Algorithm (BBA) with Late Acceptance Hill-Climbing (LAHC) to select the optimal subset from the said feature vectors in order to reduce the model complexity and help it train faster. Using Random Forest (RF) classifier, we have achieved an accuracy of 92.35% on Indic TTS database developed by IIT-Madras, and an accuracy of 100%

show abstract

“…Generally, for practical purposes, the pre-emphasized signal is blocked into 200 frames each 25ms long with 10ms frame shift. Moreover, to minimize the spectral distortions and signal mismatch when blocking the speech signal, each frame is further multiplied with a Hamming window [36], shown in Figure (3). The Hamming window is mathematically illustrated in Eqn.…”

Section: ) Framing and Windowingmentioning

confidence: 99%

Hybrid Feature Selection Method Based on Harmony Search and Naked Mole-Rat Algorithms for Spoken Language Identification From Audio Signals

et al. 2020

View full text Add to dashboard Cite

This era is dominated by artificial intelligence and its various applications-one of which is Spoken Language Identification (S-LID) which has always been a challenging issue and an important research area in the domain of speech signal processing. This paper deals with SLID to be used for Human-Computer Interaction (HCI) based applications by attempting to classify various languages from three multilingual databases namely CSS10: A Collection of Single Speaker Speech Datasets for 10 Languages, VoxForge and Indian Institute of Technology, Madras (IIT-Madras) speech corpus database by extracting their Mel-Spectrogram features and Relative Spectral Transform-Perceptual Linear Prediction (RASTA-PLP) features. A new hybrid Feature Selection (FS) algorithm have been developed using the versatile Harmony Search (HS) algorithm and a new nature-inspired algorithm called Naked Mole-Rat (NMR) algorithm to select the best subset of features and reduce the model complexity to help it train faster. This selected feature set is fed to five classifiers namely Support Vector Machine (SVM), k-Nearest Neighbor (k-NN), Multi-layer Perceptron (MLP), Naïve Bayes (NB) and Random Forest (RF). The evaluation measures used in this paper are precision, recall, f1-score, classification accuracy and number of selected features. An accuracy of 99.89% on CSS10, 98.22% on VoxForge and 99.75% on IIT-Madras speech corpus databases is achieved using RF. Furthermore, the proposed algorithm is found to outperform 15 standard meta-heuristic FS algorithms.

show abstract

Feature Extraction Techniques in Speech Processing: A Survey

Cited by 26 publications

References 21 publications

Malaria cell image classification by explainable artificial intelligence

Malaria cell image classification by explainable artificial intelligence

A Hybrid Meta-Heuristic Feature Selection Method for Identification of Indian Spoken Languages From Audio Signals

Hybrid Feature Selection Method Based on Harmony Search and Naked Mole-Rat Algorithms for Spoken Language Identification From Audio Signals

Contact Info

Product

Resources

About