Many signals of interest are corrupted by faults of an unknown type. We propose an approach that uses Gaussian processes and a general “fault bucket” to capture a priori uncha...
Michael A. Osborne, Roman Garnett, Kevin Swersky, ...
This paper presents a measure to verify the quality of automatically aligned phone labels. The measure is based on a similarity cost between automatically generated phonetic segme...
Annotation of large multilingual corpora remains a challenge to the data-driven approach to speech research, especially for under-resourced languages. This paper presents crosslan...
We present a visual saliency detection method and its applications. The proposed method does not require prior knowledge (learning) or any pre-processing step. Local visual descri...
Extraction of bilingual audio and text data is crucial for designing Speech to Speech (S2S) systems. In this work, we propose an automatic method to segment multilingual audio str...
Andreas Tsiartas, Prasanta Kumar Ghosh, Panayiotis...