2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

Technical Program

Complete Proceedings

Download Complete Proceedings

1.5 GB Zip Archive
Available from 2 June 2021 through 11 July 2021
Location: Gather.Town
 
Tuesday, 8 June
13:00 - 13:45
Attend  SPE-1: Speech Recognition 1: Neural Transducer Models 1
Attend  SPE-2: Speech Recognition 2: Neural transducer Models 2
Attend  SPE-3: Speech Synthesis 1: Architecture
Attend  SPE-4: Speech Synthesis 2: Controllability
Attend  HLT-1: Language Modeling 1: Fusion and Training for End-to-End ASR
Attend  HLT-2: Language Modeling 2: Neural Language Models
Attend  AUD-1: Audio and Speech Source Separation 1: Speech Separation
Attend  AUD-2: Audio and Speech Source Separation 2: Music and Singing Voice Separation
Attend  Special Session SS-1: Beamforming for Intelligent Surfaces
Attend  IVMSP-1: Object Detection 1
Attend  IVMSP-2: Object Detection 2
Attend  IFS-1: Multimedia Forensics 1
Attend  IFS-2: Multimedia Forensics 2
Attend  MLSP-1: Deep Learning Training Methods 1
Attend  MLSP-2: Deep Learning Training Methods 2
Attend  MLSP-3: Deep Learning Training Methods 3
Attend  BIO-1: Brain-Computer Interfaces
Attend  BIO-2: Biomedical Signal Processing: Detection and Estimation
Attend  BIO-3: Machine Learning for COVID-19 diagnosis
Attend  SPTM-1: Detection Theory and Methods 1
Attend  SPTM-2: Detection Theory and Methods 2
14:00 - 14:45
Attend  SPE-5: Speech Enhancement 1: Speech Separation
Attend  SPE-6: Speech Enhancement 2: Speech Separation and Dereverberation
Attend  SPE-7: Speaker Recognition 1: Benchmark Evaluation
Attend  SPE-8: Speaker Recognition 2: Channel and Domain Robustness
Attend  HLT-3: Dialogue Systems 1: General Topics
Attend  HLT-4: Dialogue Systems 2: Response Generation
Attend  AUD-3: Music Signal Analysis, Processing, and Synthesis 1: Deep Learning
Attend  AUD-4: Music Signal Analysis, Processing, and Synthesis 2: Analysis and Processing
Attend  Special Session SS-2: Deep Learning Methods for Solving Linear Inverse Problems
Attend  Special Session SS-3: Machine Learning in Wireless Networks
Attend  IVMSP-3: Image & Video Coding 1
Attend  IVMSP-4: Image & Video Coding 2
Attend  MMSP-1: Multimedia Signal Processing
Attend  MMSP-2: Deep Learning for Multimedia Analysis and Processing
Attend  MLSP-4: Machine Learning for Classification Applications 1
Attend  MLSP-5: Machine Learning for Classification Applications 2
Attend  MLSP-6: Compressed Sensing and Learning
Attend  MLSP-7: Tensor Signal Processing
Attend  BIO-4: Machine Learning and Signal Processing for Neural Signals
Attend  BIO-5: Neuroimaging and Neural Signal Processing
Attend  SPTM-3: Estimation, Detection and Learning over Networks 1
Attend  SPTM-4: Estimation, Detection and Learning over Networks 2
16:30 - 17:15
Attend  SPE-9: Speech Recognition 3: Transformer Models 1
Attend  SPE-10: Speech Recognition 4: Transformer Models 2
Attend  SPE-11: Voice Conversion 1: Non-parallel Conversion
Attend  SPE-12: Voice Conversion 2: Low-Resource & Cross-Lingual Conversion
Attend  SPCOM-1: Signal Processing for Networks
Attend  SPCOM-2: Information Theory, Coding and Security
Attend  AUD-5: Active Noise Control, Echo Reduction, and Feedback Reduction 1: Echo Cancellation
Attend  AUD-6: Active Noise Control, Echo Reduction, and Feedback Reduction 2: Active Noise Control and Echo Cancellation
Attend  Special Session SS-4: Data Science Methods for COVID-19
Attend  IVMSP-5: Super-resolution 1
Attend  IVMSP-6: Super-resolution 2 & Multi-scale Processing
Attend  ASPS-1: Architectures
Attend  ASPS-2: Algorithm/Architecture Co-design
Attend  MLSP-8: Learning
Attend  MLSP-9: Learning Theory for Neural Networks
Attend  MLSP-10: Deep Learning for Speech and Audio
Attend  MLSP-11: Self-supervised Learning for Speech Processing
Attend  SAM-1: Direction of Arrival Estimation 1
Attend  SAM-2: Direction of Arrival Estimation 2
Attend  SPTM-5: Sampling, Multirate Signal Processing and Digital Signal Processing 1
Attend  SPTM-6: Sampling, Multirate Signal Processing and Digital Signal Processing 2
 
Wednesday, 9 June
13:00 - 13:45
Attend  SPE-13: Speech Recognition 5: New Algorithms
Attend  SPE-14: Speech Recognition 6: New Algorithms for Sparsity/Efficiency
Attend  SPE-15: Speech Synthesis 3: Vocoder
Attend  SPE-16: Speech Synthesis 4: Front-end
Attend  HLT-5: Language Understanding 1: End-to-end Speech Understanding 1
Attend  HLT-6: Language Understanding 2: End-to-end Speech Understanding 2
Attend  AUD-7: Audio and Speech Source Separation 3: Deep Learning
Attend  AUD-8: Audio and Speech Source Separation 4: Multi-Channel Source Separation
Attend  Special Session SS-5: Domain Adaptation for Multimedia Signal Processing
Attend  IVMSP-7: Machine Learning for Image Processing I
Attend  IVMSP-8: Machine Learning for Image Processing II
Attend  IVMSP-9: Zero and Few Short Learning
Attend  IVMSP-10: Metric Learning and Interpretability
Attend  MLSP-12: Federated Learning 1
Attend  MLSP-13: Federated Learning 2
Attend  MLSP-14: Learning Algorithms 1
Attend  MLSP-15: Learning Algorithms 2
Attend  BIO-6: Medical Image Segmentation
Attend  BIO-7: Medical Image Formation and Reconstruction
Attend  SPTM-7: Estimation Theory and Methods 1
Attend  SPTM-8: Estimation Theory and Methods 2
14:00 - 14:45
Attend  SPE-17: Speech Enhancement 3: Target Speech Extraction
Attend  SPE-18: Speech Enhancement 4: Multi-channel Processing
Attend  SPE-19: Speaker Recognition 3: Attention and Adversarial
Attend  SPE-20: Speaker Recognition 4: Applications
Attend  HLT-7: Speech Translation 1: Models
Attend  HLT-8: Speech Translation 2: Aspects
Attend  AUD-9: Music Information Retrieval and Music Language Processing 1: Beat and Melody
Attend  AUD-10: Music Information Retrieval and Music Language Processing 2: Singing Voice
Attend  AUD-11: Auditory Modeling and Hearing Instruments
Attend  Special Session SS-6: Intelligent Sensing and Communications for Emerging Applications
Attend  IVMSP-11: Image & Video Segmentation
Attend  IVMSP-12: Image & Video Interpretation and Understanding
Attend  MMSP-3: Multimedia Synthesis and Enhancement
Attend  MMSP-4: Image, Video and Point Cloud Coding
Attend  MLSP-16: ML and Graphs
Attend  MLSP-17: Graph Neural Networks
Attend  MLSP-18: Matrix Factorization and Applications
Attend  MLSP-19: Non-Negative Matrix Factorization
Attend  BIO-8: Biological Image Analysis
Attend  BIO-9: Medical Image Analysis
Attend  SPTM-9: Estimation, Detection and Learning over Networks 3
Attend  SPTM-10: Distributed Learning over Graphs
15:30 - 16:15
Attend  SPE-21: Speech Recognition 7: Training Methods for End-to-End Modeling
Attend  SPE-22: Speech Recognition 8: Multilingual Speech Recognition
Attend  SPE-23: Speech Emotion 1: Speech Emotion Recognition
Attend  SPE-24: Speech Emotion 2: Neural Networks for Speech Emotion Recognition
Attend  SPE-25: Speech Emotion 3: Emotion Recognition - Representations, Data Augmentation
Attend  SPE-26: Speaker Verification Spoofing and Countermeasures
Attend  AUD-12: Detection and Classification of Acoustic Scenes and Events 1: Few-shot learning
Attend  AUD-13: Detection and Classification of Acoustic Scenes and Events 2: Weak supervision
Attend  AUD-14: Quality and Intelligibility Measures
Attend  Special Session SS-7: Multi-function Radio Frequency System: Radar, Communication, Positioning and Beyond
Attend  IVMSP-13: Image Enhancement and Restoration
Attend  IVMSP-14: Hyperspectral Imaging
Attend  IVMSP-15: Local Descriptors and Texture
Attend  IVMSP-16: Point Clouds and Depth
Attend  MLSP-20: Attention and Autoencoder Networks
Attend  MLSP-21: Generative Neural Networks
Attend  MLSP-22: Sequential Learning
Attend  CI-1: Theory for Computational Imaging
Attend  CI-2: Computational Imaging for Inverse Problems
16:30 - 17:15
Attend  SPE-27: Speech Recognition 9: Confidence Measures
Attend  SPE-28: Speech Recognition 10: Robustness to Human Speech Variability
Attend  SPE-29: Speech Processing 1: Production
Attend  SPE-30: Speech Processing 2: General Topics
Attend  HLT-9: Style and Text Normalization
Attend  HLT-10: Multi-modality in Language
Attend  AUD-15: Modeling, Analysis and Synthesis of Acoustic Environments 1: Soundfield Acquisition and Reproduction
Attend  AUD-16: Modeling, Analysis and Synthesis of Acoustic Environments 2: Spatial Audio
Attend  AUD-17: Modeling, Analysis and Synthesis of Acoustic Environments 3: Acoustic Analysis
Attend  Special Session SS-8: Near-ML Decoding of Error-correcting Codes: Algorithms and Implementation
Attend  IVMSP-17: Looking at People
Attend  IVMSP-18: Faces in Images & Videos
Attend  IFS-3: Forensics and Biometrics
Attend  IFS-4: Surveillance, Biometrics and Security
Attend  MLSP-23: Applications in Music and Audio Processing
Attend  MLSP-24: Applications in Audio and Speech Processing
Attend  SAM-3: MIMO Radar Array Processing
Attend  SAM-4: MIMO and Massive MIMO Array Processing
Attend  SPTM-11: Graphs Neural Networks
Attend  SPTM-12: Sampling, Filtering and Denoising over Graphs
 
Thursday, 10 June
13:00 - 13:45
Attend  SPE-31: Speech Recognition 11: Novel Approaches
Attend  SPE-32: Speech Recognition 12: Self-supervised, Semi-supervised, Unsupervised Training
Attend  SPE-33: Speech Synthesis 5: Prosody & Style
Attend  SPE-34: Speech Synthesis 6: Data Augmentation & Adaptation
Attend  HLT-11: Language Understanding 3: Speech Understanding - General Topics
Attend  HLT-12: Language Understanding 4: Semantic Understanding
Attend  AUD-18: Audio and Speech Source Separation 5: Source Separation
Attend  AUD-19: Audio and Speech Source Separation 6: Topics in Source Separation
Attend  Special Session SS-9: Contactless and Wireless Sensing for Smart Environments
Attend  Special Session SS-10: Computer Audition for Healthcare (CA4H)
Attend  IVMSP-19: Deraining and Dehazing
Attend  IVMSP-20: Denoising and Deblurring
Attend  ASPS-3: IoT
Attend  ASPS-4: Autonomous Systems
Attend  MLSP-25: Reinforcement Learning 1
Attend  MLSP-26: Reinforcement Learning 2
Attend  MLSP-27: Reinforcement Learning 3
Attend  BIO-10: Deep Learning for EEG Analysis
Attend  BIO-11: Deep Learning for Physiological Signals
Attend  SPTM-13: Models, Methods and Algorithms 1
Attend  SPTM-14: Models, Methods and Algorithms 2
14:00 - 14:45
Attend  SPE-35: Speech Enhancement 5: DNS Challenge Task
Attend  SPE-36: Speech Enhancement 6: Multi-modal Processing
Attend  SPE-37: Speaker Recognition 5: Neural Embedding
Attend  SPE-38: Speaker Recognition 6: Self-supervised and Unsupervised Learning
Attend  HLT-13: Information Extraction
Attend  HLT-14: Language Representations
Attend  AUD-20: Music Information Retrieval and Music Language Processing 3: Topics in Music Information Retrieval
Attend  AUD-21: Music Information Retrieval and Music Language Processing 4: Structure and Alignment
Attend  Special Session SS-11: On-device AI for Audio and Speech Applications
Attend  IVMSP-21: Image & Video Quality
Attend  IVMSP-22: Image & Video Sensing, Modeling and Representation
Attend  MMSP-5: Human Centric Multimedia 1
Attend  MMSP-6: Human Centric Multimedia 2
Attend  MLSP-28: ML and Time Series
Attend  MLSP-29: Deep Learning for Time Series
Attend  MLSP-30: Graph Signal Processing
Attend  MLSP-31: Recommendation Systems
Attend  SAM-5: Microphone Array Signal Processing
Attend  SAM-6: Beamforming 1
Attend  SPTM-15: Graph Topology Inference and Clustering
Attend  SPTM-16: Graph Topology Inference
15:30 - 16:15
Attend  SPE-39: Speech Recognition 13: Acoustic Modeling 1
Attend  SPE-40: Speech Recognition 14: Acoustic Modeling 2
Attend  SPE-41: Voice Activity and Disfluency Detection
Attend  SPE-42: Keyword Spotting
Attend  SPCOM-3: Beamforming 2
Attend  SPCOM-4: Channel Estimation for MIMO and Multiuser Systems
Attend  AUD-22: Detection and Classification of Acoustic Scenes and Events 3: Multimodal Scenes and Events
Attend  AUD-23: Detection and Classification of Acoustic Scenes and Events 4: Datasets and metrics
Attend  Special Session SS-12: Recent Advances in mmWave Radar Sensing for Autonomous Vehicles
Attend  IVMSP-23: Applications 1
Attend  IVMSP-24: Applications 2
Attend  IFS-5: Privacy and Information Security
Attend  IFS-6: Anonymization, Security and Privacy
Attend  MLSP-32: Optimization Algorithms for Machine Learning
Attend  MLSP-33: Optimization Methods
Attend  MLSP-34: Subspace Learning and Applications
Attend  MLSP-35: Independent Component Analysis
Attend  CI-3: Computational Photography
Attend  CI-4: Remote Sensing and Coded Aperture Imaging
Attend  SPTM-17: Sampling, Multirate Signal Processing and Digital Signal Processing 3
Attend  SPTM-18: Sampling Theory, Analysis and Methods
16:30 - 17:15
Attend  SPE-43: Speech Recognition 15: Robust Speech Recognition 1
Attend  SPE-44: Speech Recognition 16: Robust Speech Recognition 2
Attend  SPE-45: Speech Analysis
Attend  SPE-46: Corpora and Other Resources
Attend  HLT-15: Language Assessment
Attend  HLT-16: Applications in Natural Language
Attend  AUD-24: Signal Enhancement and Restoration 1: Deep Learning
Attend  AUD-25: Signal Enhancement and Restoration 2: Audio Coding and Restoration
Attend  AUD-26: Signal Enhancement and Restoration 3: Signal Enhancement
Attend  Special Session SS-13: Recent Advances in Multichannel and Multimodal Machine Learning for Speech Applications
Attend  IVMSP-25: Tracking
Attend  IVMSP-26: Attention for Vision
Attend  ASPS-5: Audio & Images
Attend  ASPS-6: Sensing & Sensor Processing
Attend  ASPS-7: Data Science & Machine Learning
Attend  MLSP-36: Pattern Recognition and Classification 1
Attend  MLSP-37: Pattern Recognition and Classification 2
Attend  MLSP-38: Neural Networks for Clustering and Classification
Attend  SAM-7: Detection and Estimation 1
Attend  SAM-8: Detection and Estimation 2
Attend  SAM-9: Detection and Classification
 
Friday, 11 June
11:30 - 12:15
Attend  SPE-47: Speech Recognition 17: Speech Adaptation and Normalization
Attend  SPE-48: Speech Recognition 18: Low Resource ASR
Attend  SPE-49: Speech Synthesis 7: General Topics
Attend  SPE-50: Voice Conversion & Speech Synthesis: Singing Voice & Other Topics
Attend  SPCOM-5: Detection and Decoding
Attend  SPCOM-6: System Design and Optimization
Attend  AUD-27: Acoustic Sensor Array Processing 1: Array Design and Calibration
Attend  AUD-28: Acoustic Sensor Array Processing 2: Beamforming
Attend  AUD-29: Acoustic Sensor Array Processing 3: Acoustic Sensor Arrays
Attend  Special Session SS-14: Robust Sensing and Detection in Congested Spectrum
Attend  IVMSP-27: Multi-modal Signal Processing
Attend  IVMSP-28: Image Synthesis
Attend  IFS-7: Information Hiding, Cryptography and Cybersecurity
Attend  IFS-8: Watermarking and Data Hiding
Attend  MLSP-39: Adversarial Machine Learning
Attend  MLSP-40: Contrastive Learning
Attend  MLSP-41: Deep Learning Optimization
Attend  MLSP-42: Neural Network Pruning
Attend  BIO-12: Feature Extraction and Fusion for Biomedical Applications
Attend  BIO-13: Deep Learning for Biomedical Applications
Attend  SPTM-19: Inference over Graphs
Attend  SPTM-20: Signal Processing over Graphs and Sparsity-Aware Signal Processing
13:00 - 13:45
Attend  SPE-51: Speech Enhancement 7: Single-channel Processing
Attend  SPE-52: Speech Enhancement 8: Echo Cancellation and Other Tasks
Attend  SPE-53: Speaker Diarization
Attend  SPE-54: End-to-End Speaker Diarization and Recognition
Attend  HLT-17: Language Understanding 5: Question Answering and Reading Comprehension
Attend  HLT-18: Language Understanding 6: Summarization and Comprehension
Attend  AUD-30: Detection and Classification of Acoustic Scenes and Events 5: Scenes
Attend  AUD-31: Detection and Classification of Acoustic Scenes and Events 6: Events
Attend  SPCOM-7: Communication-enabled Applications
Attend  Special Session SS-15: Signal Processing for Collaborative Intelligence
Attend  IVMSP-29: Semantic Segmentation
Attend  IVMSP-30: Inverse Problems in Image & Video Processing
Attend  MMSP-7: Multimodal Perception, Integration and Multisensory Fusion
Attend  MMSP-8: Multimedia Retrieval and Signal Detection
Attend  MLSP-43: Biomedical Applications
Attend  MLSP-44: Multimodal Data and Applications
Attend  MLSP-45: Performance Bounds
Attend  MLSP-46: Theory and Applications
Attend  SAM-10: Sparse Array Design and Processing
Attend  SAM-11: Array Calibration and Performance Analysis
Attend  SPTM-21: Optimization Methods for Signal Processing
Attend  SPTM-22: Signal Processing Theory and Methods
14:00 - 14:45
Attend  SPE-55: Language Identification and Low Resource Speech Recognition
Attend  SPE-56: Paralinguistics in Speech
Attend  SPE-57: Speech, Depression and Sleepiness
Attend  SPE-58: Dysarthric Speech Processing
Attend  SPCOM-8: Deep learning for communications
Attend  SPCOM-9: Online and Active Learning for Communications
Attend  AUD-32: Audio for Multimedia and Audio Processing Systems
Attend  AUD-33: Topics in Deep Learning for Speech and Audio
Attend  AUD-34: Acoustic System Identification and Modeling
Attend  Special Session SS-16: Theoretical Foundations of Graph Neural Networks
Attend  IVMSP-31: Applications 3
Attend  IVMSP-32: Applications 4
Attend  IVMSP-33: Action Recognition
Attend  IVMSP-34: Inpaiting and Occlusions Handling
Attend  MLSP-47: Applications of Machine Learning
Attend  MLSP-48: Neural Network Applications
Attend  SAM-12: Tracking and Localization
Attend  SAM-13: Multi-Channel Data Fusion and Processing
Attend  SPTM-23: Bayesian Signal Processing
Attend  SPTM-24: Sparsity-aware Processing