Streaming Bilingual End-to-End ASR model using Attention over Multiple Softmax

no code implementations • 22 Jan 2024 • Aditya Patil, Vikas Joshi, Purvi Agrawal, Rupesh Mehta

Even with several advancements in multilingual modeling, it is challenging to recognize multiple languages using a single neural model, without knowing the input language and most multilingual models assume the availability of the input language.

Can AI Put Gamma-Ray Astrophysicists Out of a Job?

no code implementations • 31 Mar 2023 • Samuel T. Spencer, Vikas Joshi, Alison M. W. Mitchell

In what will likely be a litany of generative-model-themed arXiv submissions celebrating April the 1st, we evaluate the capacity of state-of-the-art transformer models to create a paper detailing the detection of a Pulsar Wind Nebula with a non-existent Imaging Atmospheric Cherenkov Telescope (IACT) Array.

WavFT: Acoustic model finetuning with labelled and unlabelled data

no code implementations • 1 Apr 2022 • Utkarsh Chauhan, Vikas Joshi, Rupesh R. Mehta

Unsupervised and self-supervised learning methods have leveraged unlabelled data to improve the pretrained models.

Self-Supervised Learning

Transfer Learning Approaches for Streaming End-to-End Speech Recognition System

no code implementations • 12 Aug 2020 • Vikas Joshi, Rui Zhao, Rupesh R. Mehta, Kshitiz Kumar, Jinyu Li

Transfer learning (TL) is widely used in conventional hybrid automatic speech recognition (ASR) system, to transfer the knowledge from source to target language.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Learning not to Discriminate: Task Agnostic Learning for Improving Monolingual and Code-switched Speech Recognition

no code implementations • 9 Jun 2020 • Gurunath Reddy Madhumani, Sanket Shah, Basil Abraham, Vikas Joshi, Sunayana Sitaram

Recently, we showed that monolingual ASR systems fine-tuned on code-switched data deteriorate in performance on monolingual speech recognition, which is not desirable as ASR systems deployed in multilingual scenarios should recognize both monolingual and code-switched speech with high accuracy.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Learning to Recognize Code-switched Speech Without Forgetting Monolingual Speech Recognition

no code implementations • 1 Jun 2020 • Sanket Shah, Basil Abraham, Gurunath Reddy M, Sunayana Sitaram, Vikas Joshi

In this work, we show that fine-tuning ASR models on code-switched speech harms performance on monolingual speech.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Modified SPLICE and its Extension to Non-Stereo Data for Noise Robust Speech Recognition

no code implementations • 15 Jul 2013 • D. S. Pavan Kumar, N. Vishnu Prasad, Vikas Joshi, S. Umesh

In this paper, a modification to the training process of the popular SPLICE algorithm has been proposed for noise robust speech recognition.

Robust Speech Recognition speech-recognition