Keshav Bhandari

Keshav Bhandari

PhD Student at Queen Mary University of London

Posts by Collection

portfolio

Augmentations to improve rare bird call classification for a highly imbalanced multi-label soundscape environment

Published:

In this study, we present a deep learning solution to classify multiple bird vocalizations in a multi-label multi-species soundscape environment without a clear distinction between foreground and background species. Specifically, we focus on testing the effectiveness of various data augmentation methods to improve the classification of rare bird calls against some of the key challenges typical to a soundscape dataset - multiple overlapping bird calls, high environmental noise and high class imbalance.

Bird Sound Denoiser

Published:

In this project, I applied Facebook’s Demucs - state-of-the-art audio denoiser to remove noisy environmental background sounds from a bird sound dataset. These sounds consist of insects such as crickets, rain, wind, machines, vehicles, etc. which were synthetically added in to a clean set through a source separation task.

Click to read more and listen to the audio samples.

Audioneme - Detecting Speech Disorder in Children

Published:

Auditory perceptual analysis (APA) is the main method for clinical assessment of speech-language deficits, which are one of the most prevalent childhood disabilities. However, results from APA are susceptible to intra- and inter-rater variability. In addition, there are other limitations of manual or hand transcription-based speech disorder diagnostic methods. To address these limitations, there is increased interest in developing automated methods that quantify speech patterns for diagnosing speech disorders in children. In this project, I fine-tuned Facebook’s Wav2Vec2 on child speech data in conjunction with the utterance transcriptions to automate screening and assessment of speech disorders and speech intelligibility in children. The dataset for this project consisted of weakly labeled utterances comprising ~15,000 recordings of children with and without speech disorder.

GitHub: https://github.com/keshavbhandari/Audioneme

Efficient Scaling and Pre-Training of Language Models with Electra and Reformers

Published:

In this paper, we repurpose a highly efficient Reformer encoder architecture to serve as the foundational blocks for the Electra pre-training methodology, thereby allowing the network to scale to 8 times the size of its transformer counterpart while maintaining the same memory requirements. The subsequent downstream performance of this scaled up architecture is at par with the transformer based Electra benchmark, while being pre-trained using only a third of the data.

Download paper here.
GitHub: https://github.com/keshavbhandari/ElectraReformer

publications

talks

teaching