Research Area
Year Published

125 Results

September 4, 2014

#TagSpace: Semantic Embeddings from Hashtags

Empirical Methods in Natural Language Processing

We describe a convolutional neural network that learns feature representations for short textual posts using hashtags as a supervised signal. The proposed approach is trained on up to 5.5 billion words predicting 100,000 possible hashtags.

By: Jason Weston, Sumit Chopra, Keith Adams

December 8, 2013

Using Web Text to Improve Keyword Spotting in Speech

Automatic Speech Recognition and Understanding Workshop (ASRU)

For low resource languages, collecting sufficient training data to build acoustic and language models is time consuming and often expensive. In this paper, we investigate the use of online text resour…

By: Ankur Gandhe, Long Qin, Florian Metze, Alexander Rudnicky, Ian Lane, Matthias Eck

May 20, 2013

Machine Learning Paradigms for Speech Recognition: An Overview

IEEE/ACM Transactions on Audio, Speech, and Language Processing

Automatic Speech Recognition (ASR) has historically been a driving force behind many machine learning (ML) techniques, including the ubiquitously used hidden Markov model, discriminative learning, Bay…

By: Li Deng, Xiao Li

December 1, 2011

Performance of an online translation tool when applied to patient educational material

Journal of Hospital Medicine

We evaluate the accuracy of state-of-the-art online machine translation systems for translating patient educational material.

By: Raman R. Khanna, Leah S. Karliner, Matthias Eck, Eric Vittinghoff, Christopher J. Koenig, Margaret C. Fang

June 1, 2010

Tools for Collecting Speech Corpora via Mechanical Turk

NAACL HLT 2010 Workshop on Creating Speech and Language Data with Amazon's Mechanical Turk

To rapidly port speech applications to new languages one of the most difficult tasks is the initial collection of sufficient speech corpora.

By: Ian Lane, Alex Waibel, Matthias Eck, Kay Rottmann