Search Results for author:
Found 25 papers, 0 papers with code
Performance of BERT on Persuasion for Good
We consider the task of automatically classifying the persuasion strategy employed by an utterance in a dialog.
Improving NMT via Filtered Back Translation
This is further followed by fine-tuning on the domain-specific corpus.
Domain Adaptation for NMT via Filtered Iterative Back-Translation
In comparison, in this work, we observe that a simpler filtering approach based on a domain classifier, applied only to the pseudo-training data can consistently perform better, providing performance gains of 1. 40, 1. 82 and 0. 76 in terms of BLEU score for Medical, Law and IT in one direction, and 1. 28, 1. 60 and 1. 60 in the other direction in low resource scenario over competitive baselines.
MRI2Speech: Speech Synthesis from Articulatory Movements Recorded by Real-time MRI
Previous real-time MRI (rtMRI)-based speech synthesis models depend heavily on noisy ground-truth speech.
Advancing NAM-to-Speech Conversion with Novel Methods and the MultiNAM Dataset
To address this issue, we focus on learning phoneme-level alignments from paired whispers and text and employ a Text-to-Speech (TTS) system to simulate the ground-truth.
Persuasion Games using Large Language Models
We employ simulated personas and generate conversations in insurance, banking, and retail domains to evaluate the proficiency of large language models (LLMs) in recognizing, adjusting to, and influencing various personality types.
Towards Improving NAM-to-Speech Synthesis Intelligibility using Self-Supervised Speech Models
Moreover, we present a methodology for augmenting the existing CSTR NAM TIMIT Plus corpus, setting a benchmark with a Word Error Rate (WER) of 42. 57% to gauge the intelligibility of the synthesized speech.
Towards Mitigating Perceived Unfairness in Contracts from a Non-Legal Stakeholder's Perspective
It outperformed chain of thought prompting using Vicuna-13B by a margin of 9%.
Can Physics Informed Neural Operators Self Improve?
Physics Informed Neural Operators (PINO) overcome this constraint by utilizing a physics loss for the training, however the accuracy of PINO trained without data does not match the performance obtained by training with data.
How important are specialized transforms in Neural Operators?
Simulating physical systems using Partial Differential Equations (PDEs) has become an indispensible part of modern industrial process optimization.
HyperLoRA for PDEs
Physics-informed neural networks (PINNs) have been widely used to develop neural surrogates for solutions of Partial Differential Equations.
Synthesis of Mathematical programs from Natural Language Specifications
Several decision problems that are encountered in various business domains can be modeled as mathematical programs, i. e. optimization problems.
DeepEpiSolver: Unravelling Inverse problems in Covid, HIV, Ebola and Disease Transmission
We then use a neural network to learn the mapping between spread trajectories and coefficients of SIDR in an offline manner.
Symbolic Regression for PDEs using Pruned Differentiable Programs
Furthermore, on an average, pruning improves the accuracy of DPA by 7. 81% .
Real-time Health Monitoring of Heat Exchangers using Hypernetworks and PINNs
We demonstrate a Physics-informed Neural Network (PINN) based model for real-time health monitoring of a heat exchanger, that plays a critical role in improving energy efficiency of thermal power plants.
Physics Informed Symbolic Networks
We use this approximation to define multilayer symbolic networks.
I Know Therefore I Score: Label-Free Crafting of Scoring Functions using Constraints Based on Domain Expertise
The approach incorporates insights and business rules from domain experts in the form of easily observable and specifiable constraints, which are used as weak supervision by a machine learning model.
Layer-wise training of deep networks using kernel similarity
The hierarchical feature representation built by deep networks enable compact and precise encoding of the data.
Knowledge distillation using unlabeled mismatched images
Current approaches for Knowledge Distillation (KD) either directly use training data or sample from the training data distribution.
Ashwin: Plug-and-Play System for Machine-Human Image Annotation
We present an end-to-end machine-human image annotation system where each component can be attached in a plug-and-play fashion.
Feasibility of Post-Editing Speech Transcriptions with a Mismatched Crowd
However, it is yet to be established whether a mismatched worker has sufficiently fine-granular speech perception to choose among the phonetically proximate options that are likely to be generated from the trellis of an ASRU.
