File Download
There are no files associated with this item.
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Conference Paper: Ten case studies of the effect of field conditions on speech recognition errors
Title | Ten case studies of the effect of field conditions on speech recognition errors |
---|---|
Authors | |
Issue Date | 1997 |
Citation | Ieee Workshop On Automatic Speech Recognition And Understanding Proceedings, 1997, p. 511-518 How to Cite? |
Abstract | This paper follows ten speech recognition services as they are deployed in live trials and services in the telephone network. We focus in particular on measured recognition accuracy in the lab setting, during the first field deployment, and through several field iterations. We cite factors that contribute to loss of accuracy when systems are used by real customers and relate how these problems are identified and overcome. We observe that a common pattern of performance emerges. We show that with proper planning, careful data collection and analysis, and adequate time for technology updates, field performance can match that of the laboratory. |
Persistent Identifier | http://hdl.handle.net/10722/179576 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Thomson, David L | en_US |
dc.date.accessioned | 2012-12-19T09:59:57Z | - |
dc.date.available | 2012-12-19T09:59:57Z | - |
dc.date.issued | 1997 | en_US |
dc.identifier.citation | Ieee Workshop On Automatic Speech Recognition And Understanding Proceedings, 1997, p. 511-518 | en_US |
dc.identifier.uri | http://hdl.handle.net/10722/179576 | - |
dc.description.abstract | This paper follows ten speech recognition services as they are deployed in live trials and services in the telephone network. We focus in particular on measured recognition accuracy in the lab setting, during the first field deployment, and through several field iterations. We cite factors that contribute to loss of accuracy when systems are used by real customers and relate how these problems are identified and overcome. We observe that a common pattern of performance emerges. We show that with proper planning, careful data collection and analysis, and adequate time for technology updates, field performance can match that of the laboratory. | en_US |
dc.language | eng | en_US |
dc.relation.ispartof | IEEE Workshop on Automatic Speech Recognition and Understanding Proceedings | en_US |
dc.title | Ten case studies of the effect of field conditions on speech recognition errors | en_US |
dc.type | Conference_Paper | en_US |
dc.identifier.email | Thomson, David L: dthomson@hku.hk | en_US |
dc.identifier.authority | Thomson, David L=rp00788 | en_US |
dc.description.nature | link_to_subscribed_fulltext | en_US |
dc.identifier.scopus | eid_2-s2.0-0030635375 | en_US |
dc.identifier.spage | 511 | en_US |
dc.identifier.epage | 518 | en_US |
dc.identifier.scopusauthorid | Thomson, David L=7202586830 | en_US |