—We present an OCR-driven writer identification algorithm in this paper. Our algorithm learns writer-specific characteristics more precisely from explicit character alignment usi...
A common problem in speech recognition for foreign accented speech is that there is not enough training data for an accent-specific or a speaker-specific recognizer. Speaker ada...
In recent years, adaptation techniques have been given special focus in speaker recognition tasks, mainly targeting speaker and session variation disentangling under the Maximum a...
We investigate language model (LM) adaptation in a meeting recognition application, where the LM is adapted based on recognition output from relevant prior meetings and partial ma...
Abstract. Building visual recognition models that adapt across different domains is a challenging task for computer vision. While feature-learning machines in the form of hierarchi...
Amr Ahmed, Kai Yu, Wei Xu, Yihong Gong, Eric P. Xi...