Publications (21)
SLICER: Learning universal audio representations using low-resource self-supervised pre-training
Ashish Seth, Sreyan Ghosh, S. Umesh +1
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…
DeToxy: A Large-Scale Multimodal Dataset for Toxicity Classification in Spoken Utterances
Sreyan Ghosh, Samden Lepcha, S Sakshi +2
Toxic speech, also known as hate speech, is regarded as one of the crucial issues plaguing online social media today. Most recent work on toxic speech detection is constrained to t…
DECAR: Deep Clustering for learning general-purpose Audio Representations
Sreyan Ghosh, Sandesh V Katta, Ashish Seth +1
We introduce DECAR, a self-supervised pre-training approach for learning general-purpose audio representations. Our system is based on clustering: it utilizes an offline clustering…
FusDom: Combining In-Domain and Out-of-Domain Knowledge for Continuous Self-Supervised Learning
Ashish Seth, Sreyan Ghosh, S. Umesh +1
Continued pre-training (CP) offers multiple advantages, like target domain adaptation and the potential to exploit the continuous stream of unlabeled data available online. However…
Channel-Aware Pretraining of Joint Encoder-Decoder Self-Supervised Model for Telephonic-Speech ASR
Vrunda N. Sukhadia, A. Arunkumar, S. Umesh
This paper proposes a novel technique to obtain better downstream ASR performance from a joint encoder-decoder self-supervised model when trained with speech pooled from two differ…
data2vec-aqc: Search for the right Teaching Assistant in the Teacher-Student training setup
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. Our goal is to improve…
The Tag-Team Approach: Leveraging CLS and Language Tagging for Enhancing Multilingual ASR
Kaousheik Jayakumar, Vrunda N. Sukhadia, A Arunkumar +1
Building a multilingual Automated Speech Recognition (ASR) system in a linguistically diverse country like India can be a challenging task due to the differences in scripts and the…
Domain Adaptation of low-resource Target-Domain models using well-trained ASR Conformer Models
Vrunda N. Sukhadia, S. Umesh
In this paper, we investigate domain adaptation for low-resource Automatic Speech Recognition (ASR) of target-domain data, when a well-trained ASR model trained with a large datase…
Analyzing the factors affecting usefulness of Self-Supervised Pre-trained Representations for Speech Recognition
Ashish Seth, Lodagala V S V Durga Prasad, Sreyan Ghosh +1
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 setting…
Span Classification with Structured Information for Disfluency Detection in Spoken Utterances
Sreyan Ghosh, Sonal Kumar, Yaman Kumar Singla +2
Existing approaches in disfluency detection focus on solving a token-level classification task for identifying and removing disfluencies in text. Moreover, most works focus on leve…
DeLoRes: Decorrelating Latent Spaces for Low-Resource Audio Representation Learning
Sreyan Ghosh, Ashish Seth, and Deepak Mittal +2
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. O…
UNFUSED: UNsupervised Finetuning Using SElf supervised Distillation
Ashish Seth, Sreyan Ghosh, S. Umesh +1
In this paper, we introduce UnFuSeD, a novel approach to leverage self-supervised learning and reduce the need for large amounts of labeled data for audio classification. Unlike pr…
Investigation of Speaker-adaptation methods in Transformer based ASR
Vishwas M. Shetty, Metilda Sagaya Mary N J, S. Umesh
End-to-end models are fast replacing the conventional hybrid models in automatic speech recognition. Transformer, a sequence-to-sequence model, based on self-attention popularly us…
Building Robust and Scalable Multilingual ASR for Indian Languages
Arjun Gangwar, Kaousheik Jayakumar, S. Umesh
This paper describes the systems developed by SPRING Lab, Indian Institute of Technology Madras, for the ASRU MADASR 2.0 challenge. The systems developed focuses on adapting ASR sy…
PADA: Pruning Assisted Domain Adaptation for Self-Supervised Speech Representations
Lodagala V S V Durga Prasad, Sreyan Ghosh, S. Umesh
While self-supervised speech representation learning (SSL) models serve a variety of downstream tasks, these models have been observed to overfit to the domain from which the unlab…
Investigation of Ensemble features of Self-Supervised Pretrained Models for Automatic Speech Recognition
A Arunkumar, Vrunda N Sukhadia, S. Umesh
Self-supervised learning (SSL) based models have been shown to generate powerful representations that can be used to improve the performance of downstream speech tasks. Several sta…
Modified SPLICE and its Extension to Non-Stereo Data for Noise Robust Speech Recognition
D. S. Pavan Kumar, N. Vishnu Prasad, Vikas Joshi +1
In this paper, a modification to the training process of the popular SPLICE algorithm has been proposed for noise robust speech recognition. The modification is based on feature co…
MAST: Multiscale Audio Spectrogram Transformers
Sreyan Ghosh, Ashish Seth, S. Umesh +1
We present Multiscale Audio Spectrogram Transformer (MAST) for audio classification, which brings the concept of multiscale feature hierarchies to the Audio Spectrogram Transformer…
EZ-VC: Easy Zero-shot Any-to-Any Voice Conversion
Advait Joglekar, Divyanshu Singh, Rooshil Rohit Bhatia +1
Voice Conversion research in recent times has increasingly focused on improving the zero-shot capabilities of existing methods. Despite remarkable advancements, current architectur…
CCC-wav2vec 2.0: Clustering aided Cross Contrastive Self-supervised learning of speech representations
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. We present a new…
Stable Distillation: Regularizing Continued Pre-training for Low-Resource Automatic Speech Recognition
Ashish Seth, Sreyan Ghosh, S. Umesh +1
Continued self-supervised (SSL) pre-training for adapting existing SSL models to the target domain has shown to be extremely effective for low-resource Automatic Speech Recognition…