Hugo Van hamme

Multitask Learning with Capsule Networks for Speech-to-Intent Applications

2020

Voice controlled applications can be a great aid to society, especially for physically challenged people. However this requires robustness to all kinds of variations in speech. A spoken language understanding system that learns from interaction …

Graph Connectionist Temporal Classification for Phoneme Recognition

2025 · Lirias

Automatic Phoneme Recognition (APR) systems are often trained using pseudo phoneme-level annotations generated from text through Grapheme-to-Phoneme (G2P) systems. These G2P systems frequently output multiple possible pronunciations per word, but the standard Connectionist Temporal Classification …