We explore morphology-based and sub-word language modeling approaches proposed for morphologically rich languages, and evaluate and contrast them for Turkish broadcast news transc...
Robustness is one of the most important topics for automatic speech recognition (ASR) in practical applications. Monaural speech separation based on computational auditory scene a...
Recently there has been interest in the use of classifiers based on the product of experts (PoE) framework. PoEs offer an alternative to the standard mixture of experts (MoE) fram...
Prosodic information has been successfully used for speaker recognition for more than a decade. The best-performing prosodic system to date has been one based on features extracte...
Luciana Ferrer, Nicolas Scheffer, Elizabeth Shribe...
Modern speech recognition applications are becoming very complex program packages. To understand the error behaviour of the ASR systems, a special diagnosis - a procedure or a tool...