End-to-end Spoken Language Understanding (SLU) systems, without speech-to-text conversion, are more promising in low resource scenarios. They can be more effective when there is not enough labeled data to train reliable speech recognition and language understanding systems, or where running SLU on edge is preferred over cloud based services. In this paper, we present an approach for bootstrapping end-to-end SLU in low resource scenarios. We show that incorporating layers extracted from pre-trained acoustic models, instead of using the typical Mel filter bank features, lead to better performing SLU models. Moreover, the layers extracted from a model pre-trained on one language perform well even for (a) SLU tasks on a different language and also (b) on utterances from speakers with speech disorder.

No abstract

No abstract

No abstract

Cough sounds as a descriptor have been used for detecting various respiratory ailments based on its intensity, duration of intermediate phase between two cough sounds, repetitions, dryness etc. However, COVID-19 diagnosis using only cough sounds is challenging because of cough being a common symptom among many non COVID-19 health diseases and inherent data imbalance within the available datasets. As one of the approach in this direction, we explore the robustness of multi-domain representation by performing the early fusion over a wide set of temporal, spectral and tempo-spectral handcrafted features, followed by training a Support Vector Machine (SVM) classifier. In our second approach, using a contrastive loss function we learn a latent space from Mel Filter Cepstral Coefficients (MFCCs) where representations belonging to samples having similar cough characteristics are closer. This helps learn representations for the highly varied COVIDnegative class (healthy and symptomatic COVID-negative), by learning multiple smaller clusters. Using only the DiCOVA data, multi-domain features yields an absolute improvement of 0.74% and 1.07%, whereas our second approach shows an improvement of 2.09% and 3.98%, over the blind test and validation set, respectively, when compared with challenge baseline.