James Glass

Learn More
This paper describes a suite of metrics that we use to evaluate our JUPITER system which provides worldwide weather information over the telephone. Since May, 1997, we h a v e made the system available to the general public via a toll-free number and have collected approximately 35,000 utterances to date. These data have proven invaluable for system(More)
Ubiquitous computing environments are characterized by an unbounded amount of noise and crosstalk. In these environments, traditional methods of sound capture are insufficient, and array microphones are needed in order to obtain a clean recording of desired speech. In this work, we have designed, implemented, and tested LOUD, a novel 1020-node microphone(More)
This paper proposes a novel two-layer approach to fundamental frequency modeling for concatenative speech synthesis based on a statistical learning technique called additive models. We define an additive F 0 contour model consisting of long-term, intonational phrase-level, component and short-term, accentual phrase-level, component, along with a(More)
Recording speech and other sound is difficult in environments with a large amount of noise and/or crosstalk. In these environments, array microphones are needed in order to obtain a clean recording of desired speech. In this work, we have designed, implemented, and tested LOUD, a 1020-node microphone array. To the best of our knowledge and as documented by(More)
Continuous word and phrase vectors have proven useful in a number of NLP tasks. Here we describe our experience using them as a source of features for the SemEval-2015 task 3, consisting of two community question answering subtasks: Answer Selection for categorizing answers as potential, good, and bad with regards to their corresponding questions; and(More)
The use of segment-based features and segmentation networks in a segment-based speech recognizer complicates the probabilistic modeling because it alters the sample space of all possible segmentation paths and the feature observation space. This paper describes a novel Baum-Welch training algorithm for segment-based speech recognition which addresses these(More)
Machine translation between Arabic and Hebrew has so far been limited by a lack of parallel corpora, despite the political and cultural importance of this language pair. Previous work relied on manually-crafted grammars or pivoting via English, both of which are unsatisfactory for building a scalable and accurate MT system. In this work, we compare standard(More)
This paper presents ongoing language understanding experiments conducted as part of a larger effort to create a nutrition dialogue system that automatically extracts food concepts from a user's spoken meal description. We first discuss the technical approaches to understanding, including three methods for incorporating word vector features into conditional(More)