Ankit Parag Shah

Publications

• DCASE 2017 Challenge Setup: Tasks, Datasets and Baseline System
• Repeatability and Scalability of Code for Top Level Verification
• An Approach for Self-Training Audio Event Detectors Using Web Data
• Learning Sound Events From Webly Labeled Data
• Accident Forecasting in CCTV Traffic Camera Videos
• Tartan: A retrieval-based socialbot powered by a dynamic finite-state machine architecture
• Activity Recognition on a Large Scale in Short Videos-Moments in Time Dataset
• Natural Language Person Search Using Deep Reinforcement Learning
• Experiments on the DCASE Challenge 2016: Acoustic Scene Classification and Sound Event Detection in Real Life Recordings
• Content-based Representations of audio using Siamese neural networks
• Large-Scale Weakly Labeled Semi-Supervised Sound Event Detection in Domestic Environments
• Framework for evaluation of sound event detection in web videos
• Pipelined implementation of high radix adaptive CORDIC as a coprocessor
• Automated Audio Captioning and Language-Based Audio Retrieval
• An Approach to Ontological Learning from Weak Labels
• Approach to Learning Generalized Audio Representation Through Batch Embedding Covariance Regularization and Constant-Q Transforms
• Conformers are All You Need for Visual Speech Recogntion
• Overview of the Tenth Dialog System Technology Challenge: DSTC10
• Audio-visual scene-aware dialog and reasoning using audio-visual transformers with joint student-teacher learning
• DSTC10-AVSD Submission System with Reasoning using Audio-Visual Transformers with Joint Student-Teacher Learning
• An approach for self-training audio event detectors using web data
• DCASE 2017 challenge setup: Tasks, datasets and baseline system
• On the pragmatism of using binary classifiers over data intensive neural network classifiers for detection of COVID-19 from voice
• Triple Attention Network architecture for MovieQA
• Multimodal behavioral markers exploring suicidal intent in social media videos
• An overview of techniques for biomarker discovery in voice signal
• Feature extraction and evaluation for BioMedical Question Answering
• Content-based Representations of audio using Siamese neural networks
• NELS-Never-Ending Learner of Sounds
• Sound event detection in domestic environments with weakly labeled data and soundscape synthesis
• DCASE 2017 challenge setup: Tasks, datasets and baseline system
• CADP: A Novel Dataset for CCTV Traffic Camera based Accident Analysis
• Framework for evaluation of sound event detection in web videos
• Repeatability and Scalibility of Code at Top level Verification
• An approach for self-training audio event detectors using web data
• Improving Perceptual Quality, Intelligibility, and Acoustics on VoIP Platforms
• Tartan: A retrieval-based socialbot powered by a dynamic finite-state machine architecture
• Overview of Audio Visual Scene-Aware Dialog with Reasoning Track for Natural Language Generation in DSTC10
• Sound event detection in synthetic domestic environments
• Learning Sound Events From Webly Labeled Data
• Pipelined implementation of high radix adaptive CORDIC as a coprocessor
• Reasoning for Audio Visual Scene-Aware DialogTrack in DSTC10
• A Closer Look at Weak Label Learning for Audio Events
• Archive ouverte HAL
• Imprecise label learning: A unified framework for learning with various imprecise label configurations
• Training image classifiers using Semi-Weak Label Data
• Activity Recognition on a Large Scale in Short Videos-Moments in Time Dataset
• Large-Scale Weakly Labeled Semi-Supervised Sound Event Detection in Domestic Environments
• Experiments on the DCASE Challenge 2016: Acoustic scene classification and sound event detection in real life recording
• Hardware Architecture for High Radix Adaptive CORDIC Algorithm