Abstract-- Traditional methods of spoken utterance classification (SUC) adopt two independently trained phases. In the first phase, an automatic speech recognition (ASR) module ret...
Sibel Yaman, Li Deng, Dong Yu, Ye-Yi Wang, Alex Ac...
We present an algorithm to automatically estimate three-dimensional light positions from an unordered set of images. We collect images using a single stationary camera while manua...
Most problems in computational geometry are algebraic. A general approach to address nonrobustness in such problems is Exact Geometric Computation (EGC). There are now general lib...
This paper presents trainable methods for generating letter to sound rules from a given lexicon for use in pronouncing out-ofvocabulary words and as a method for lexicon compressi...
When automatic speech recognition (ASR) and speaker verification (SV) are applied in adverse acoustic environments, endpoint detection and energy normalization can be crucial to th...