AIConfPaper
← Search

SUBHANKAR GHOSH

10 accepted papers

2025

Koel-TTS: Enhancing LLM based Speech Generation with Preference Alignment and Classifier Free Guidance

Shehzeen Samarah Hussain, Paarth Neekhara, Xuesong Yang, Edresson Casanova, Subhankar Ghosh, Roy Fejgin +3
EMNLP 2025

Autoregressive speech token generation models produce speech with remarkable variety and naturalness but often suffer from hallucinations and undesired vocalizations that do not conform to conditioning inputs. To address these challenges, we introduce Koel-TTS, an encoder-decoder transformer model f

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

Low Frame-rate Speech Codec: a Codec Designed for Fast High-quality Speech LLM Training and Inference

Edresson Casanova, Ryan Langman, Paarth Neekhara, Shehzeen Hussain, Jason Li, Subhankar Ghosh +2
ICASSP 2025accepted

Large language models (LLMs) have significantly advanced audio processing through audio codecs that convert audio into discrete tokens, enabling the application of language modeling techniques to audio data. However, audio codecs often operate at high frame rates, resulting in slow training and infe…

Cited by 0Source ↗Scholar ↗
2025

TTS-Transducer: End-to-End Speech Synthesis with Neural Transducer

Vladimir Bataev, Subhankar Ghosh, Vitaly Lavrukhin, Jason Li
ICASSP 2025accepted

This work introduces TTS-Transducer – a novel architecture for text-to-speech, leveraging the strengths of audio codec models and neural transducers. Transducers, renowned for their superior quality and robustness in speech recognition, are employed to learn monotonic alignments and allow for avoidi…

Cited by 0Source ↗Scholar ↗
2024

Conformal Prediction for Class-wise Coverage via Augmented Label Rank Calibration

Yuanjie Shi, SUBHANKAR GHOSH, Taha Belkhouja, Jana Doppa, Yan Yan
NeurIPS 2024poster

Conformal prediction (CP) is an emerging uncertainty quantification framework that allows us to construct a prediction set to cover the true label with a pre-specified marginal or conditional probability. Although the valid coverage guarantee has been extensively studied for classification problems,…

Cited by 2Source ↗PDF ↗code ↗Scholar ↗
2024

SALM: Speech-Augmented Language Model with in-Context Learning for Speech Recognition and Translation

Zhehuai Chen, He Huang, Andrei Andrusenko, Oleksii Hrinchuk, Krishna C. Puvvada, Jason Li +3
ICASSP 2024accepted

We present a novel Speech Augmented Language Model (SALM) with multitask and in-context learning capabilities. SALM comprises a frozen text LLM, a audio encoder, a modality adapter module, and LoRA layers to accommodate speech input and associated task instructions. The unified SALM not only achieve…

Cited by 0Source ↗Scholar ↗
2023

Improving Uncertainty Quantification of Deep Classifiers via Neighborhood Conformal Prediction: Novel Algorithm and Theoretical Analysis

Subhankar Ghosh, Taha Belkhouja, Yan Yan, Janardhan Rao Doppa
AAAI 2023technical

Safe deployment of deep neural networks in high-stake real-world applications require theoretically sound uncertainty quantification. Conformal prediction (CP) is a principled framework for uncertainty quantification of deep models in the form of prediction set for classification tasks with a user-s…

Cited by 19Source ↗PDF ↗code ↗Scholar ↗
2023

Probabilistically robust conformal prediction

Subhankar Ghosh, Yuanjie Shi, Taha Belkhouja, Yan Yan, Jana Doppa, Brian Jones
UAI 2023poster

Conformal prediction (CP) is a framework to quantify uncertainty of machine learning classifiers including deep neural networks. Given a testing example and a trained classifier, CP produces a prediction set of candidate labels with a user-specified coverage (i.e., true class label is contained wit…

Cited by 21Source ↗PDF ↗code ↗Scholar ↗
2023

Vani: Very-Lightweight Accent-Controllable TTS for Native And Non-Native Speakers With Identity Preservation

Rohan Badlani, Akshit Arora, Subhankar Ghosh, Rafael Valle, Kevin J. Shih, João Felipe Santos +2
ICASSP 2023accepted

We introduce VANI, a very lightweight multi-lingual accent controllable speech synthesis system. Our model builds upon disentanglement strategies proposed in RADMMM[1] and supports explicit control of accent, language, speaker and fine-grained F<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xml…

Cited by 0Source ↗Scholar ↗
2022

TIPS: Text-Induced Pose Synthesis

Prasun Roy, Subhankar Ghosh, Saumik Bhattacharya, Umapada Pal, Michael Blumenstein
ECCV 2022poster

"In computer vision, human pose synthesis and transfer deal with probabilistic image generation of a person in a previously unseen pose from an already available observation of that person. Though researchers have recently proposed several methods to achieve this task, most of these techniques deriv…

Cited by 11Source ↗PDF ↗code ↗Scholar ↗
2020

STEFANN: Scene Text Editor Using Font Adaptive Neural Network

Prasun Roy, Saumik Bhattacharya, Subhankar Ghosh, Umapada Pal
CVPR 2020poster

Textual information in a captured scene plays an important role in scene interpretation and decision making. Though there exist methods that can successfully detect and interpret complex text regions present in a scene, to the best of our knowledge, there is no significant prior work that aims to mo…

Cited by 91PDF ↗code ↗Scholar ↗