Fusion Feature Extraction Based on Auditory and Energy for Noise-Robust Speech Recognition

Abstract

Environmental noise can pose a threat to the stable operation of current speech recognition systems. It is therefore essential to develop a front feature set that is able to identify speech under low signalto-noise ratio. In this paper, a robust fusion feature is proposed that can fully characterize speech information. To obtain the cochlear filter cepstral coefficients (CFCC), a novel feature is first extracted by the power-law nonlinear function, which can simulate the auditory characteristics of the human ear. Speech enhancement technology is then introduced into the front end of feature extraction, and the extracted feature and their first-order difference are combined in new mixed features. An energy feature Teager energy operator cepstral coefficient (TEOCC) is also extracted, and combined with the above-mentioned mixed features to form the fusion feature sets. Principal component analysis (PCA) is then applied to feature selection and optimization of the feature set, and the final feature set is used in a non-specific persons, isolated words, and smallvocabulary speech recognition system. Finally, a comparative experiment of speech recognition is designed to verify the advantages of the proposed feature set using a support vector machine (SVM). The experimental results show that the proposed feature set not only display a high recognition rate and excellent anti-noise performance in speech recognition, but can also fully characterize the auditory and energy information in the speech signals.INDEX TERMS Cochlear filter cepstral coefficients, Teager energy operators cepstral coefficients, principal component analysis, speech recognition.

Speech Recognition Algorithm in a Noisy Environment Based on Power Normalized Cepstral Coefficient and Modified Weighted-KNN

“…𝑚𝑚 𝑖𝑖,𝑗𝑗 = 𝑀𝑀𝑖𝑖𝑒𝑒(𝐷𝐷 (𝑖𝑖,1) , 𝐷𝐷 (𝑖𝑖,2) , … … 𝐷𝐷 (𝑖𝑖,𝑗𝑗) ) (19) where: D is the similarity based on DTW. Calculate the weight (w) for each set of K nearest neighbors using Equation 16.…”

“…She et al [19], created a new feature extraction technique using the supplied blended features. The combination uses the cepstral coefficients as a foundation of the cochlear filter to maximize accuracy in noisy surroundings (CFCC).…”

Fault feature extraction of rolling element bearings based on short-time processing

“…Energy-based methods are widely used in speech analysis [23][24]. The characteristic frequency of bearing can also be observed based on energy [25][26][27], such as Teager energy and short-time energy.…”

Feature compensation based on independent noise estimation for robust speech recognition

“…In the front-end processing, the Mel frequency cepstral coefficient (MFCC) is widely used to represent the speech signal [1]. Besides, the perceptual linear predictive (PLP) features [2], spectro-temporal features [3], and cochlear filter cepstral coefficients (CFCC) features [4] have also been successfully used for speech recognition. In the backend classification, the statistical acoustic models are commonly used, such as hidden Markov model (HMM) [5], *Correspondence: wupingping@nau.edu.cn 2 School of Engineering Auditing, Jiangsu Key Laboratory of Public Project Audit, Nanjing Audit University, Nanjing, China Full list of author information is available at the end of the article artificial neural network (ANN) [6], and dynamic Bayesian network (DBN) [7].…”

“…Fig 4. Performance comparison of the proposed algorithm (IGMM20) and original GMM-based feature compensation (GMM400 and GMM20) with different SNRs for the three types of testing noise…”