1 code implementation • ICON 2021 • Sai Muralidhar Jayanthi, Varsha Embar, Karthik Raghunathan
The wide applicability of pretrained transformer models (PTMs) for natural language tasks is well demonstrated, but their ability to comprehend short phrases of text is less explored.
no code implementations • 9 Feb 2024 • Konstantin Kolokolov, Pavel Pekichev, Karthik Raghunathan
We propose a novel neural network architecture based on conformer transducer that adds contextual information flow to the ASR systems.
1 code implementation • 15 Dec 2021 • Sai Muralidhar Jayanthi, Varsha Embar, Karthik Raghunathan
The wide applicability of pretrained transformer models (PTMs) for natural language tasks is well demonstrated, but their ability to comprehend short phrases of text is less explored.
no code implementations • IJCNLP 2019 • Arushi Raghuvanshi, Vijay Ramakrishnan, Varsha Embar, Lucien Carroll, Karthik Raghunathan
Large vocabulary domain-agnostic Automatic Speech Recognition (ASR) systems often mistranscribe domain-specific words and phrases.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +5
no code implementations • EMNLP 2018 • Arushi Raghuvanshi, Lucien Carroll, Karthik Raghunathan
We demonstrate an end-to-end approach for building conversational interfaces from prototype to production that has proven to work well for a number of applications across diverse verticals.