virtual conference icassp 2021

Towards Data Selection On Tts Data For Children'S Speech Recognition

A Comparison Of Convolutional Neural Networks For Glottal Closure Instant Detection From Raw Speech

Age-Vox-Celeb: Multi-Modal Corpus For Facial And Speech Estimation

Making Punctuation Restoration Robust And Fast With Multi-Task Learning And Knowledge Distillation

Centrality Based Number Of Cluster Estimation In Graph Clustering

On The Adversarial Robustness Of Principal Component Analysis

Fourier Transformation Autoencoders For Anomaly Detection

Sample Efficient Subspace-Based Representations For Nonlinear Meta-Learning

Unsupervised Musical Timbre Transfer For Notification Sounds

Catiloc: Camera Image Transformer For Indoor Localization

Event-Driven Modulo Sampling

Nn-Kog2P: A Novel Grapheme-To-Phoneme Model For Korean Language