341 citations · 501 across the 66 of their papers we have counts for
13 papers · 1 filter
Self-Influence Guided Data Reweighting for Language Model Pre-training
Megh Thakkar, Tolga Bolukbasi, Sriram Ganapathy +3
Language Models (LMs) pre-trained with self-supervision on large text corpora have become the default starting point for developing models for various NLP tasks. Once the pre-train…
Summary of the DISPLACE Challenge 2023 - DIarization of SPeaker and LAnguage in Conversational Environments
Shikha Baghel, Shreyas Ramoji, Somil Jain +4
In multi-lingual societies, where multiple languages are spoken in a small geographic vicinity, informal conversations often involve mix of languages. Existing speech technologies…
Accented Speech Recognition With Accent-specific Codebooks
Darshan Prabhu, Preethi Jyothi, Sriram Ganapathy +1
Speech accents pose a significant challenge to state-of-the-art automatic speech recognition (ASR) systems. Degradation in performance across underrepresented accents is a severe d…
Speech enhancement with frequency domain auto-regressive modeling
Anurenjan Purushothaman, Debottam Dutta, Rohit Kumar +1
Speech applications in far-field real world settings often deal with signals that are corrupted by reverberation. The task of dereverberation constitutes an important step to impro…
Multimodal Modeling For Spoken Language Identification
Shikhar Bharadwaj, Min Ma, Shikhar Vashishth +10
Spoken language identification refers to the task of automatically predicting the spoken language in a given utterance. Conventionally, it is modeled as a speech-based language ide…
Representation Learning With Hidden Unit Clustering For Low Resource Speech Applications
Varun Krishna, Tarun Sai, Sriram Ganapathy
The representation learning of speech, without textual resources, is an area of significant interest for many low resource speech applications. In this paper, we describe an approa…
MASR: Multi-label Aware Speech Representation
Anjali Raj, Shikhar Bharadwaj, Sriram Ganapathy +2
In the recent years, speech representation learning is constructed primarily as a self-supervised learning (SSL) task, using the raw audio signal alone, while ignoring the side-inf…
Enhancing the EEG Speech Match Mismatch Tasks With Word Boundaries
Akshara Soman, Vidhi Sinha, Sriram Ganapathy
Recent studies have shown that the underlying neural mechanisms of human speech comprehension can be analyzed using a match-mismatch classification of the speech stimulus and the n…
Label Aware Speech Representation Learning For Language Identification
Shikhar Vashishth, Shikhar Bharadwaj, Sriram Ganapathy +5
Speech representation learning approaches for non-semantic tasks such as language recognition have either explored supervised embedding extraction methods using a classifier model…
Coswara: A respiratory sounds and symptoms dataset for remote screening of SARS-CoV-2 infection
Debarpan Bhattacharya, Neeraj Kumar Sharma, Debottam Dutta +8
This paper presents the Coswara dataset, a dataset containing diverse set of respiratory sounds and rich meta-data, recorded between April-2020 and February-2022 from 2635 individu…
HCAM -- Hierarchical Cross Attention Model for Multi-modal Emotion Recognition
Soumya Dutta, Sriram Ganapathy
Emotion recognition in conversations is challenging due to the multi-modal nature of the emotion expression. We propose a hierarchical cross-attention model (HCAM) approach to mult…
DISPLACE Challenge: DIarization of SPeaker and LAnguage in Conversational Environments
Shikha Baghel, Shreyas Ramoji, Sidharth +8
In multilingual societies, social conversations often involve code-mixed speech. The current speech technology may not be well equipped to extract information from multi-lingual mu…
Supervised Hierarchical Clustering using Graph Neural Networks for Speaker Diarization
Prachi Singh, Amrit Kaul, Sriram Ganapathy
Conventional methods for speaker diarization involve windowing an audio file into short segments to extract speaker embeddings, followed by an unsupervised clustering of the embedd…