© 2 0 0 3 m a s s a c h u s e t t s i n s t i t u t e o f t e c h n o l o g y, c a m b r i d g e , m a 0 2 1 3 9 u s a — w w w. a i. m i t. e d u m a s s a c h u s e t t s i n s t i t u t e o f t e c h n o l o g y — a r t i f i c i a l i n t e l l i g e n c e l a b o r a t o r y @ MIT Abstract The central challenge in face recognition lies in understanding the role different facial features pla...

Attention-based encoder-decoder (AED) models have achieved promising performance in speech recognition. However, because of the end-to-end training, an AED model is usually trained with speech-text paired data. It challenging to incorporate external text-only data into models. Another issue that it does not use right context a text token while predicting token. To alleviate above two issues, we...

We investigate the adaptation of structured classifiers to new domains. In particular, the problem of using a supervised Named-Entity Recognition (NER) system on data from a different source than the training data. We present a Semi-Markov Model, trained with the perceptron algorithm, coupled with an external dictionary with the goal of improving generalization on the novel domain. Preliminary ...

We explore the use of Wikipedia as external knowledge to improve named entity recognition (NER). Our method retrieves the corresponding Wikipedia entry for each candidate word sequence and extracts a category label from the first sentence of the entry, which can be thought of as a definition part. These category labels are used as features in a CRF-based NE tagger. We demonstrate using the CoNL...

Semi-implantable transcutaneous bone conduction devices are treatment options for conductive and mixed hearing loss (CHL/MHL). For counseling of patients, realistic simulation of the functional result is desirable. This study compared speech recognition in noise with a semi-implantable transcutaneous bone conduction device to external stimulation with a bone conduction device fixed by a headban...