G
Geoffrey Zweig
Researcher at IBM
Publications - 29
Citations - 1735
Geoffrey Zweig is an academic researcher from IBM. The author has contributed to research in topics: Word error rate & Vocabulary. The author has an hindex of 18, co-authored 29 publications receiving 1678 citations.
Papers
More filters
Proceedings ArticleDOI
fMPE: discriminatively trained features for speech recognition
TL;DR: In this paper, a matrix projection from posteriors of Gaussians to a normal size feature space is used to train a matrix and then add the projected features to normal features such as PLP.
Proceedings ArticleDOI
Hybrid Code Networks: practical and efficient end-to-end dialog control with supervised and reinforcement learning
TL;DR: This work introduces Hybrid Code Networks (HCNs), which combine an RNN with domain-specific knowledge encoded as software and system action templates, and considerably reduce the amount of training data required, while retaining the key benefit of inferring a latent representation of dialog state.
Posted Content
Hybrid Code Networks: practical and efficient end-to-end dialog control with supervised and reinforcement learning
TL;DR: This paper proposed Hybrid Code Networks (HCNs), which combine an RNN with domain-specific knowledge encoded as software and system action templates to reduce the amount of training data required, while retaining the key benefit of inferring a latent representation of dialog state.
Journal ArticleDOI
Advances in speech transcription at IBM under the DARPA EARS program
Stanley F. Chen,Brian Kingsbury,Lidia Mangu,Daniel Povey,George Saon,Hagen Soltau,Geoffrey Zweig +6 more
TL;DR: This paper describes the technical and system building advances made in IBM's speech recognition technology over the course of the Defense Advanced Research Projects Agency (DARPA) Effective Affordable Reusable Speech-to-Text (EARS) program and presents results on English conversational telephony test data from the 2003 and 2004 NIST evaluations.
Proceedings ArticleDOI
The IBM 2004 conversational telephony system for rich transcription
TL;DR: Technical advances in IBM's conversational telephony submission to the DARPA-sponsored 2004 rich transcription evaluation (RT-04) reduced the error rate by approximately 21% relative, on the 2003 test set, over the best-performing system in last year's evaluation, and produced the best results on the RT-04 current and progress CTS data.