16 citations · 28 across the 11 of their papers we have counts for
11 papers
Length Aware Speech Translation for Video Dubbing
Harveen Singh Chadha, Aswin Shanmugam Subramanian, Vikas Joshi +4
In video dubbing, aligning translated audio with the source audio is a significant challenge. Our focus is on achieving this efficiently, tailored for real-time, on-device video du…
Addressing speaker gender bias in large scale speech translation systems
Shubham Bansal, Vikas Joshi, Harveen Chadha +2
This study addresses the issue of speaker gender bias in Speech Translation (ST) systems, which can lead to offensive and inaccurate translations. The masculine bias often found in…
Speaker Recognition in the Wild
Neeraj Chhimwal, Anirudh Gupta, Rishabh Gaur +4
In this paper, we propose a pipeline to find the number of speakers, as well as audios belonging to each of these now identified speakers in a source of audio data where number of…
indic-punct: An automatic punctuation restoration and inverse text normalization framework for Indic languages
Anirudh Gupta, Neeraj Chhimwal, Ankur Dhuriya +4
Automatic Speech Recognition (ASR) generates text which is most of the times devoid of any punctuation. Absence of punctuation is text can affect readability. Also, down stream NLP…
Effectiveness of text to speech pseudo labels for forced alignment and cross lingual pretrained models for low resource speech recognition
Anirudh Gupta, Rishabh Gaur, Ankur Dhuriya +4
In the recent years end to end (E2E) automatic speech recognition (ASR) systems have achieved promising results given sufficient resources. Even for languages where not a lot of la…
Is Word Error Rate a good evaluation metric for Speech Recognition in Indic Languages?
Priyanshi Shah, Harveen Singh Chadha, Anirudh Gupta +4
We propose a new method for the calculation of error rates in Automatic Speech Recognition (ASR). This new metric is for languages that contain half characters and where the same c…
Improving Speech Recognition for Indic Languages using Language Model
Ankur Dhuriya, Harveen Singh Chadha, Anirudh Gupta +4
We study the effect of applying a language model (LM) on the output of Automatic Speech Recognition (ASR) systems for Indic languages. We fine-tune wav2vec models for In…
Code Switched and Code Mixed Speech Recognition for Indic languages
Harveen Singh Chadha, Priyanshi Shah, Ankur Dhuriya +3
Training multilingual automatic speech recognition (ASR) systems is challenging because acoustic and lexical information is typically language specific. Training multilingual syste…
Vakyansh: ASR Toolkit for Low Resource Indic languages
Harveen Singh Chadha, Anirudh Gupta, Priyanshi Shah +4
We present Vakyansh, an end to end toolkit for Speech Recognition in Indic languages. India is home to almost 121 languages and around 125 crore speakers. Yet most of the languages…
Toxicity Detection for Indic Multilingual Social Media Content
Manan Jhaveri, Devanshu Ramaiya, Harveen Singh Chadha
Toxic content is one of the most critical issues for social media platforms today. India alone had 518 million social media users in 2020. In order to provide a good experience to…
CLSRIL-23: Cross Lingual Speech Representations for Indic Languages
Anirudh Gupta, Harveen Singh Chadha, Priyanshi Shah +4
We present a CLSRIL-23, a self supervised learning based audio pre-trained model which learns cross lingual speech representations from raw audio across 23 Indic languages. It is b…