1.1k citations
- Menlo SchoolUS21 papers
- Stanford UniversityUS9 papers
- University of California, BerkeleyUS9 papers
- University of PennsylvaniaUS7 papers
- Michigan State UniversityUS6 papers
- Space Telescope Science InstituteUS6 papers
- University College LondonGB6 papers
- University of California San DiegoUS6 papers
- University of Illinois Urbana-ChampaignUS6 papers
- Oak Ridge National LaboratoryUS5 papers
- Purdue University West LafayetteUS5 papers
- Brown UniversityUS4 papers
8 papers · 1 filter
An Efficient Probabilistic Context-Free Parsing Algorithm that Computes Prefix Probabilities
Andreas Stolcke
We describe an extension of Earley's parser for stochastic context-free grammars that computes the following quantities given a stochastic context-free grammar and an input string:…
The Speech-Language Interface in the Spoken Language Translator
David Carter, Manny Rayner
The Spoken Language Translator is a prototype for practically useful systems capable of translating continuous spoken language within restricted domains. The prototype system trans…
Improving Language Models by Clustering Training Sentences
David Carter
Many of the kinds of language model used in speech understanding suffer from imperfect modeling of intra-sentential contextual influences. I argue that this problem can be addresse…
Training and Scaling Preference Functions for Disambiguation
Hiyan Alshawi, David Carter
We present an automatic method for weighting the contributions of preference functions used in disambiguation. Initial scaling factors are derived as the solution to a least-square…
Combining Knowledge Sources to Reorder N-Best Speech Hypothesis Lists
Manny Rayner, David Carter, Vassilios Digalakis +1
A simple and general method is described that can combine different knowledge sources to reorder N-best lists of hypotheses produced by a speech recognizer. The method is automatic…
Estimating Performance of Pipelined Spoken Language Translation Systems
Manny Rayner, David Carter, Patti Price +1
Most spoken language translation systems developed to date rely on a pipelined architecture, in which the main stages are speech recognition, linguistic analysis, transfer, generat…