Jonathan G. Fiscus  Home/Search
Context Related
| nist.gov/speech/publications...rover.ps Cached: PS.gz PS PDF This document uses CoBlitz to cache paper downloads. If your firewall is blocking outgoing connections to port 3125, you can use these links to download local copies.
Image Update HelpPS.gz PS PDF From: nist.gov/speech/publicati...index (more) (Enter author homepages) |
Rate this article:      (best)Comment on this article |
Abstract: This paper describes a system developed at NIST to produce a composite Automatic Speech Recognition (ASR) system output when the outputs of multiple ASR systems are available, and for which, in many cases, the composite ASR output has lower error rate than any of the individual systems. The system implements a "voting" or rescoring process to reconcile differences in ASR system outputs. We refer to this system as the NIST Recognizer Output Voting Error Reduction (ROVER) system. As additional... (Update)
Cited by: More
Spontaneous Speech Recognition Using a Massively Parallel.. - Takahiro Shinozaki Sadaoki (2001) (Correct)
Recognizing Sloppy Speech - Yu (2004) (Correct)
Duration Normalization For Robust Recognition - Of Spontaneous Speech (Correct)
Active bibliography (related documents): More All
0.0: Acoustic-Feature-Based Frequency Warping for Speaker Normalization - Gouvea (1998) (Correct)
0.0: Language Model Adaptation Using Cross-Lingual Information - Kim, Khudanpur (2003) (Correct)
0.0: Lexical Modeling Of Non-Native Speech For Automatic Speech.. - Livescu, Glass (2000) (Correct)
Similar documents based on text: More All
0.5: Language Resources as by-Product of Evaluation: the.. - Patrick Paroubek Limsi (2000) (Correct)
0.4: 1997 Broadcast News Benchmark Test Results: English.. - Pallett, Fiscus.. (1998) (Correct)
0.4: Improved ROVER using Language Model Information - Schwenk, Gauvain (2000) (Correct)
Related documents from co-citation: More All
22: Finding Consensus Among Words: Lattice-Based Word Error Minimization - Mangu, Brill et al.
13: Explicit word error minimization in N-best list rescoring - Stolcke, Konig et al. - 1997
11: Maximum Likelihood Linear Transformations for HMM-based Speech Recognition - Gales - 1997
BibTeX entry: (Update)
Fiscus, J.G. (1997) A Post-Processing System to Yield Reduced Word Error Rates: Recogniser Output Voting Error Reduction (ROVER). Proc. IEEE ASRU Workshop, pp. 347-352, Santa Barbara. http://citeseer.ist.psu.edu/fiscus97postprocessing.html More
@misc{ fiscus97postprocessing,
author = "J. Fiscus",
title = "A Post-Processing System to Yield Reduced Word Error Rates: Recogniser Output Voting Error Reduction (ROVER)",
booktitle = {Proceedings 1997 IEEE Workshop on Automatic Speech
Recognition and Understanding},
address = {Santa Barbara, CA},
pages = {347--352},
year = 1997,
url = "citeseer.ist.psu.edu/fiscus97postprocessing.html" }
Citations (may not include all citations):11 Tools for the Analysis of Benchmark Speech Recognition Tests (context) - Pallett, al
http://www.nist.gov/speech/software.htm"
The graph only includes citing articles where the year of publication is known.
Documents on the same site (http://www.nist.gov/speech/publications/index.htm): More
The NIST Speaker Recognition Evaluations: 1996-2001 - Martin, Przybocki (1998) (Correct)
NIST Speaker Recognition Evaluation Chronicles - Mark Przybocki Alvin (2004) (Correct)
The Rich Transcription 2005 Spring Meeting - Recognition Evaluation Jonathan (Correct)
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC