Improved phase aware speech enhancement using bio-inspired and ANN techniques

Dash, Tusar Kanti; Solanki, Sandeep Singh; Panda, Ganapati

doi:10.1007/s10470-019-01566-z

Cited by 15 publications

(7 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Neural network-based classifier models are widely used in speech processing for improved performance (Lopez-Moreno et al, 2016 ; Dash et al, 2020 ). In this case, feed-forward fully connected neural network (FCNN) is used with the input layer connected to a fully connected layer of 10 neurons, a ReLU function, followed by a second fully connected layer, a softmax function.…”

Section: Methodsmentioning

confidence: 99%

Speech phoneme and spectral smearing based non-invasive COVID-19 detection

Mishra

Dash²,

Panda³

2023

Front. Artif. Intell.

Self Cite

View full text Add to dashboard Cite

COVID-19 is a deadly viral infection that mainly affects the nasopharyngeal and oropharyngeal cavities before the lung in the human body. Early detection followed by immediate treatment can potentially reduce lung invasion and decrease fatality. Recently, several COVID-19 detections methods have been proposed using cough and breath sounds. However, very little study has been done on the use of phoneme analysis and the smearing of the audio signal in COVID-19 detection. In this paper, this problem has been addressed and the classification of speech samples has been carried out in COVID-19-positive and healthy audio samples. Additionally, the grouping of the phonemes based on reference classification accuracies have been proposed for effectiveness and faster detection of the disease at a primary stage. The Mel and Gammatone Cepstral coefficients and their derivatives are used as the features for five standard machine learning-based classifiers. It is observed that the generalized additive model provides the highest accuracy of 97.22% for the phoneme grouping “/t//r//n//g//l/.” This smearing-based phoneme classification technique can also be used in the future to classify other speech-related disease detections.

show abstract

Section: Methodsmentioning

confidence: 99%

Speech phoneme and spectral smearing based non-invasive COVID-19 detection

Mishra

Dash²,

Panda³

2023

Front. Artif. Intell.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Also, it has been proved that the FF algorithm works better than the traditional Particle Swarm Optimization and Genetic Algorithm in terms of both efficiency and success rate [39] . Recently several speech processing based optimizations have been implemented successfully using FF algorithms [40] . Hence, the FF algorithm has been chosen for finding the best possible cepstral features to be used for the COVID-19 classification.…”

Section: Proposed Methodologymentioning

confidence: 99%

“…It is widely used in hearing aids, speech communications, and speech recognition tasks. Recently, the phase spectrum compensation based speech enhancement has been proposed [43] and its performance has been shown to be improved using the bio-inspired and ANN techniques [40] . This algorithm has been employed in this paper in the speech enhancement part.…”

Section: Proposed Methodologymentioning

confidence: 99%

Detection of COVID-19 from speech signal using bio-inspired based cepstral features

Dash¹,

Mishra²,

Panda³

et al. 2021

Pattern Recognition

Self Cite

View full text Add to dashboard Cite

“…When speech is recorded by different users in different environments, then the speech quality varies drastically in one category within the dataset as well as across different datasets [28]. The background noise level significantly affects the overall performance of the speech recognition system [29], [30]. For highly non-stationary situations, the noise level is computed using the noise estimation algorithm [31].…”

Section: B Preprocessingmentioning

confidence: 99%