A Novel Temporal Attentive-Pooling based Convolutional Recurrent Architecture for Acoustic Signal Enhancement

Hussain, Tassadaq; Wang, Wei-Chien; Gogate, Mandar; Dashtipour, Kia; Yu, Tao; Lu, Xugang; Ahsan, Adeel; Hussain, Amir

doi:10.48550/arxiv.2201.09913

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is important to note that despite reducing the parameters, there was no major improvement observed in the performance of the model. Hussain et al [7] integrated temporal attentive-pooling (TAP) into the CNN approach for the SE task. The convolutional layer was used to extract the local information of audio signals and RNN was used to characterize temporal contextual information.…”

Section: Introductionmentioning

confidence: 99%

A Novel Speech Intelligibility Enhancement Model based on CanonicalCorrelation and Deep Learning

Hussain¹,

Diyan²,

Gogate³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Current deep learning (DL) based approaches to speech intelligibility enhancement in noisy environments are often trained to minimise the feature distance between noisefree speech and enhanced speech signals. Despite improving the speech quality, such approaches do not deliver required levels of speech intelligibility in everyday noisy environments . Intelligibility-oriented (I-O) loss functions have recently been developed to train DL approaches for robust speech enhancement. Here, we formulate, for the first time, a novel canonical correlation based I-O loss function to more effectively train DL algorithms. Specifically, we present a canonicalcorrelation based short-time objective intelligibility (CC-STOI) cost function to train a fully convolutional neural network (FCN) model. We carry out comparative simulation experiments to show that our CC-STOI based speech enhancement framework outperforms state-of-the-art DL models trained with conventional distance-based and STOI-based loss functions, using objective and subjective evaluation measures for case of both unseen speakers and noises. Ongoing future work is evaluating the proposed approach for design of robust hearingassistive technology.

show abstract

Section: Introductionmentioning

confidence: 99%