5 papers
SALSA: Speedy ASR-LLM Synchronous Aggregation
Ashish Mittal, Darshan Prabhu, Sunita Sarawagi +1
Harnessing pre-trained LLMs to improve ASR systems, particularly for low-resource languages, is now an emerging area of research. Existing methods range from using LLMs for ASR err…
Improving RNN-Transducers with Acoustic LookAhead
Vinit S. Unni, Ashish Mittal, Preethi Jyothi +1
RNN-Transducers (RNN-Ts) have gained widespread acceptance as an end-to-end model for speech to text conversion because of their high accuracy and streaming capabilities. A typical…
Partitioned Gradient Matching-based Data Subset Selection for Compute-Efficient Robust ASR Training
Ashish Mittal, Durga Sivasubramanian, Rishabh Iyer +2
Training state-of-the-art ASR systems such as RNN-T often has a high associated financial and environmental cost. Training with a subset of training data could mitigate this proble…
Adaptive Discounting of Implicit Language Models in RNN-Transducers
Vinit Unni, Shreya Khare, Ashish Mittal +3
RNN-Transducer (RNN-T) models have become synonymous with streaming end-to-end ASR systems. While they perform competitively on a number of evaluation categories, rare words pose a…
Unified Semantic Parsing with Weak Supervision
Priyanka Agrawal, Parag Jain, Ayushi Dalmia +3
Semantic parsing over multiple knowledge bases enables a parser to exploit structural similarities of programs across the multiple domains. However, the fundamental challenge lies…