Speech & natural language publications
-
WikiWalk: Random walks on Wikipedia for semantic relatedness
This paper evaluates methods for building the graph, including link selection strategies, and two methods for representing input texts as distributions over the graph nodes: one based on a dictionary…
-
Impact of Prior Channel Information for Speaker Identification
In this work, we apply JFA to a very diverse set of recording conditions and conversation modes in NIST 2008 SRE, showing that having channel matched development data will give…
-
Using Syntax in Large-Scale Audio Document Translation
In this paper, we investigate the effect of using syntax in a large-scale audio document translation task targeting broadcast news and broadcast conversations.
-
Combining Semantic and Syntactic Information Sources for 5-W Question Answering
This paper focuses on combining answers generated by a semantic parser that produces semantic role labels (SRLs) and those generated by syntactic parser that produces function tags for answering 5-W…
-
Who, What, When, Where, Why? Comparing Multiple Approaches to the Cross-Lingual 5W Task
In this paper, we present an error analysis of a new cross-lingual task: the 5W task, a sentence-level understanding task which seeks to return the English 5W's (Who, What, When,…
-
Efficient data selection for machine translation
In this paper, we introduce two methods for efficient selection of training data to be translated by humans. Our methods are motivated by active learning and aim to choose new…
-
Phonetic Name Matching for Cross-Lingual Spoken Sentence Retrieval
This paper proposes a simple method of fuzzy matching between query names and phones of candidate audio segments.
-
The CALO meeting speech recognition and understanding system
This paper summarizes the CALO-MA architecture and its speech recognition and understanding components, which include realtime and offline speech transcription, dialog act segmentation and tagging, question-answer pair identification, action item…
-
Strategies for building a Farsi-English SMT system from limited resources
In this paper we will focus on the kinds of improvements for a Farsi-to- English translation system achieved by means of algorithmic changes, adding raw, domain-unspecific resources, and unsupervised morphological…
-
Phone-based cepstral polynomial SVM system for speaker recognition
In this paper, we present a complete analysis of the phone-based cepstral system with polynomial features. We start from a simpler system that does not use phones or states and…
-
MUESLI: Multiple utterance error correction for a spoken language interface
We propose a method for using all available information to help correct recognition errors in tasks that use constrained grammars of the kind used in the domain of Command and…
-
Development of the SRI/Nightingale Arabic ASR System
We describe the large vocabulary automatic speech recognition system developed for Modern Standard Arabic used for the 2007 GALE evaluation as part of the speech translation system.