Single channel blind source separation based on probabilistic matrix factorisation

Long Short-Term Memory Recurrent Neural Network-Based Acoustic Model Using Connectionist Temporal Classification on a Large-Scale Training Corpus

Spectral energy based voice activity detection for real-time voice interface

Maximum Likelihood-based Automatic Lexicon Generation for AI Assistant-based Interaction with Mobile Devices

Noise reduction based on robust speech and non-speech detection in vehicular environments

Illumination-Robust Foreground Extraction for Text Area Detection in Outdoor Environment

Multistage data selection-based unsupervised speaker adaptation for personalized speech emotion recognition

Implementation of a large-scale language model adaptation in a cloud environment

Unsupervised noise reduction scheme for voice-based information retrieval in mobile environments

Efficient Head Pose Determination and Its Application to Face Recognition on Multi-Pose Face DB