1 code implementation • COLING (WNUT) 2022 • Ramaneswaran S, Sean Benhur, Sreyan Ghosh
Sentiment classification is a fundamental NLP task of detecting the sentiment polarity of a given text.
no code implementations • 30 Mar 2024 • Chandra Kiran Reddy Evuru, Sreyan Ghosh, Sonal Kumar, Ramaneswaran S, Utkarsh Tyagi, Dinesh Manocha
We present CoDa (Constrained Generation based Data Augmentation), a controllable, effective, and training-free data augmentation technique for low-resource (data-scarce) NLP.
no code implementations • 30 Mar 2024 • Sonal Kumar, Sreyan Ghosh, S Sakshi, Utkarsh Tyagi, Dinesh Manocha
We curate Compun, a novel benchmark with 400 unique and commonly used CNs, to evaluate the effectiveness of VLMs in interpreting CNs.
no code implementations • 3 Feb 2024 • Sreyan Ghosh, Chandra Kiran Reddy Evuru, Sonal Kumar, Ramaneswaran S, Deepali Aneja, Zeyu Jin, Ramani Duraiswami, Dinesh Manocha
Our findings reveal that responses generated solely from pre-trained knowledge consistently outperform responses by models that learn any form of new knowledge from IT on open-source datasets.
1 code implementation • 20 Dec 2023 • Ashish Seth, Sreyan Ghosh, S. Umesh, Dinesh Manocha
Specifically, first, we perform vanilla continued pre-training on an initial SSL pre-trained model on the target domain ASR dataset and call it the teacher.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
1 code implementation • 20 Dec 2023 • Ashish Seth, Sreyan Ghosh, S. Umesh, Dinesh Manocha
Continued pre-training (CP) offers multiple advantages, like target domain adaptation and the potential to exploit the continuous stream of unlabeled data available online.
no code implementations • 30 Nov 2023 • Anton Ratnarajah, Sreyan Ghosh, Sonal Kumar, Purva Chiniya, Dinesh Manocha
We propose AV-RIR, a novel multi-modal multi-task learning approach to accurately estimate the RIR from a given reverberant speech signal and the visual cues of its corresponding environment.
1 code implementation • 24 Oct 2023 • Sreyan Ghosh, Chandra Kiran Evuru, Sonal Kumar, S Ramaneswaran, S Sakshi, Utkarsh Tyagi, Dinesh Manocha
We present DALE, a novel and effective generative Data Augmentation framework for low-resource LEgal NLP.
no code implementations • 12 Oct 2023 • Sreyan Ghosh, Ashish Seth, Sonal Kumar, Utkarsh Tyagi, Chandra Kiran Evuru, S. Ramaneswaran, S. Sakshi, Oriol Nieto, Ramani Duraiswami, Dinesh Manocha
In this paper, we propose CompA, a collection of two expert-annotated benchmarks with a majority of real-world audio samples, to evaluate compositional reasoning in ALMs.
1 code implementation • 18 Sep 2023 • Sreyan Ghosh, Sonal Kumar, Chandra Kiran Reddy Evuru, Ramani Duraiswami, Dinesh Manocha
We present RECAP (REtrieval-Augmented Audio CAPtioning), a novel and effective audio captioning system that generates captions conditioned on an input audio and other captions similar to the audio retrieved from a datastore.
no code implementations • ICCV 2023 • Sanjoy Chowdhury, Sreyan Ghosh, Subhrajyoti Dasgupta, Anton Ratnarajah, Utkarsh Tyagi, Dinesh Manocha
We present AdVerb, a novel audio-visual dereverberation framework that uses visual cues in addition to the reverberant sound to estimate clean audio.
no code implementations • 19 Aug 2023 • Sreyan Ghosh, Chandra Kiran Reddy Evuru, Sonal Kumar, Utkarsh Tyagi, Sakshi Singh, Sanjoy Chowdhury, Dinesh Manocha
This paper presents ASPIRE (Language-guided data Augmentation for SPurIous correlation REmoval), a simple yet effective solution for expanding the training dataset with synthetic images without spurious features.
1 code implementation • 1 Jun 2023 • Sreyan Ghosh, Utkarsh Tyagi, Manan Suri, Sonal Kumar, S Ramaneswaran, Dinesh Manocha
In addition, we demonstrate the application of ACLM to other domains that suffer from data scarcity (e. g., biomedical).
1 code implementation • 18 May 2023 • Sreyan Ghosh, Utkarsh Tyagi, Sonal Kumar, Dinesh Manocha
Though data augmentation has shown to be highly effective for low-resource NER in general, existing data augmentation techniques fail to produce factual and diverse augmentations for BioNER.
1 code implementation • 10 Mar 2023 • Ashish Seth, Sreyan Ghosh, S. Umesh, Dinesh Manocha
Unlike prior works, which directly fine-tune a self-supervised pre-trained encoder on a target dataset, we use the encoder to generate pseudo-labels for unsupervised fine-tuning before the actual fine-tuning step.
1 code implementation • 2 Mar 2023 • Sreyan Ghosh, Manan Suri, Purva Chiniya, Utkarsh Tyagi, Sonal Kumar, Dinesh Manocha
The tremendous growth of social media users interacting in online conversations has led to significant growth in hate speech, affecting people from various demographics.
no code implementations • 27 Nov 2022 • Sreyan Ghosh, Utkarsh Tyagi, Sonal Kumar, Manan Suri, Rajiv Ratn Shah
Based on early-fusion and self-attention-based multimodal interaction between text and acoustic modalities, in this paper, we propose a novel multimodal architecture for disfluency detection from individual utterances.
1 code implementation • 2 Nov 2022 • Vasista Sai Lodagala, Sreyan Ghosh, S. Umesh
In this paper, we propose a new Self-Supervised Learning (SSL) algorithm called data2vec-aqc, for speech representation learning from unlabeled speech data.
Automatic Speech Recognition (ASR) Representation Learning +1
1 code implementation • 2 Nov 2022 • Ashish Seth, Sreyan Ghosh, S. Umesh, Dinesh Manocha
We present a new Self-Supervised Learning (SSL) approach to pre-train encoders on unlabeled audio data that reduces the need for large amounts of labeled data for audio and speech classification.
1 code implementation • 2 Nov 2022 • Sreyan Ghosh, Ashish Seth, S. Umesh, Dinesh Manocha
We present Multiscale Audio Spectrogram Transformer (MAST) for audio classification, which brings the concept of multiscale feature hierarchies to the Audio Spectrogram Transformer (AST).
1 code implementation • 5 Oct 2022 • Vasista Sai Lodagala, Sreyan Ghosh, S. Umesh
While Self-Supervised Learning has helped reap the benefit of the scale from the available unlabeled data, the learning paradigms are continuously being bettered.
1 code implementation • 31 Mar 2022 • Lodagala V S V Durga Prasad, Sreyan Ghosh, S. Umesh
To alleviate this issue, we propose PADA (Pruning Assisted Domain Adaptation) and zero out redundant weights from models pre-trained on large amounts of out-of-domain (OOD) data.
1 code implementation • 31 Mar 2022 • Sreyan Ghosh, Utkarsh Tyagi, S Ramaneswaran, Harshvardhan Srivastava, Dinesh Manocha
In this paper, we propose MMER, a novel Multimodal Multi-task learning approach for Speech Emotion Recognition.
Ranked #2 on Speech Emotion Recognition on IEMOCAP (using extra training data)
no code implementations • 31 Mar 2022 • Ashish Seth, Lodagala V S V Durga Prasad, Sreyan Ghosh, S. Umesh
Self-supervised learning (SSL) to learn high-level speech representations has been a popular approach to building Automatic Speech Recognition (ASR) systems in low-resource settings.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
1 code implementation • 31 Mar 2022 • Sreyan Ghosh, S Ramaneswaran, Utkarsh Tyagi, Harshvardhan Srivastava, Samden Lepcha, S Sakshi, Dinesh Manocha
Expression of emotions is a crucial part of daily human communication.
1 code implementation • 30 Mar 2022 • Sreyan Ghosh, Sonal Kumar, Yaman Kumar Singla, Rajiv Ratn Shah, S. Umesh
Existing approaches in disfluency detection focus on solving a token-level classification task for identifying and removing disfluencies in text.
1 code implementation • 25 Mar 2022 • Sreyan Ghosh, Ashish Seth, and Deepak Mittal, Maneesh Singh, S. Umesh
Inspired by the recent progress in self-supervised learning for computer vision, in this paper we introduce DeLoRes, a new general-purpose audio representation learning approach.
no code implementations • 18 Dec 2021 • Zaki Mustafa Farooqi, Sreyan Ghosh, Rajiv Ratn Shah
In the current era of the internet, where social media platforms are easily accessible for everyone, people often have to deal with threats, identity attacks, hate, and bullying due to their association with a cast, creed, gender, religion, or even acceptance or rejection of a notion.
1 code implementation • 17 Oct 2021 • Sreyan Ghosh, Sandesh V Katta, Ashish Seth, S. Umesh
We introduce DECAR, a self-supervised pre-training approach for learning general-purpose audio representations.
1 code implementation • 14 Oct 2021 • Sreyan Ghosh, Samden Lepcha, S Sakshi, Rajiv Ratn Shah, S. Umesh
We believe that our dataset would act as a benchmark for the relatively new and un-explored Spoken Language Processing task of detecting toxicity from spoken utterances and boost further research in this space.
1 code implementation • SEMEVAL 2021 • Sreyan Ghosh, Sonal Kumar
We also explore a dependency parsing approach where we extract spans from the input sentence under the supervision of target span boundaries and rank our spans using a biaffine model.
1 code implementation • 10 Jan 2021 • Sreyan Ghosh, Sonal Kumar, Harsh Jalan, Hemant Yadav, Rajiv Ratn Shah
This paper describes our proposed system for the AAAI-CAD21 shared task: Predicting Emphasis in Presentation Slides.
1 code implementation • 22 May 2020 • Hemant Yadav, Sreyan Ghosh, Yi Yu, Rajiv Ratn Shah
Named entity recognition (NER) from text has been a widely studied problem and usually extracts semantic information from text.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +4