2 citations · 2 across the 5 of their papers we have counts for
5 papers
AUREXA-SE: Audio-Visual Unified Representation Exchange Architecture with Cross-Attention and Squeezeformer for Speech Enhancement
M. Sajid, Deepanshu Gupta, Yash Modi +7
In this paper, we propose AUREXA-SE (Audio-Visual Unified Representation Exchange Architecture with Cross-Attention and Squeezeformer for Speech Enhancement), a progressive bimodal…
Compact Neural TTS Voices for Accessibility
Kunal Jain, Eoin Murphy, Deepanshu Gupta +5
Contemporary text-to-speech solutions for accessibility applications can typically be classified into two categories: (i) device-based statistical parametric speech synthesis (SPSS…
Positional Description for Numerical Normalization
Deepanshu Gupta, Javier Latorre
We present a Positional Description Scheme (PDS) tailored for digit sequences, integrating placeholder value information for each digit. Given the structural limitations of subword…
EELBERT: Tiny Models through Dynamic Embeddings
Gabrielle Cohn, Rishika Agarwal, Deepanshu Gupta +1
We introduce EELBERT, an approach for compression of transformer-based models (e.g., BERT), with minimal impact on the accuracy of downstream tasks. This is achieved by replacing t…
Languages You Know Influence Those You Learn: Impact of Language Characteristics on Multi-Lingual Text-to-Text Transfer
Benjamin Muller, Deepanshu Gupta, Siddharth Patwardhan +3
Multi-lingual language models (LM), such as mBERT, XLM-R, mT5, mBART, have been remarkably successful in enabling natural language tasks in low-resource languages through cross-lin…