Abstract
Recently, there have been many efforts in developing confidence measures for speech recognition output. Usually, these measures are applied to the final result of the decoder. However, using these measures early in the search process can guide the search to more promising paths. In this paper we use a confidence metric, the Average Best_Base_Phoneme Rank, to dynamically tune the contribution of the language model score. The advantage of this metric is that it uses information already available during the decoder search. The performance of this guided search approach was tested in two experiments for the ATIS and WSJ data sets and results show significant reductions in recognition error rates.
| Original language | English (US) |
|---|---|
| Title of host publication | ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings |
| Volume | 4 |
| State | Published - 2002 |
| Event | 2002 IEEE International Conference on Acoustic, Speech, and Signal Processing - Orlando, FL, United States Duration: May 13 2002 → May 17 2002 |
Other
| Other | 2002 IEEE International Conference on Acoustic, Speech, and Signal Processing |
|---|---|
| Country | United States |
| City | Orlando, FL |
| Period | 5/13/02 → 5/17/02 |
Fingerprint
ASJC Scopus subject areas
- Electrical and Electronic Engineering
- Signal Processing
- Acoustics and Ultrasonics
Cite this
Confidence measures as a search guide in speech recognition. / Abdou, Sherif; Scordilis, Michael S.
ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. Vol. 4 2002.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Confidence measures as a search guide in speech recognition
AU - Abdou, Sherif
AU - Scordilis, Michael S
PY - 2002
Y1 - 2002
N2 - Recently, there have been many efforts in developing confidence measures for speech recognition output. Usually, these measures are applied to the final result of the decoder. However, using these measures early in the search process can guide the search to more promising paths. In this paper we use a confidence metric, the Average Best_Base_Phoneme Rank, to dynamically tune the contribution of the language model score. The advantage of this metric is that it uses information already available during the decoder search. The performance of this guided search approach was tested in two experiments for the ATIS and WSJ data sets and results show significant reductions in recognition error rates.
AB - Recently, there have been many efforts in developing confidence measures for speech recognition output. Usually, these measures are applied to the final result of the decoder. However, using these measures early in the search process can guide the search to more promising paths. In this paper we use a confidence metric, the Average Best_Base_Phoneme Rank, to dynamically tune the contribution of the language model score. The advantage of this metric is that it uses information already available during the decoder search. The performance of this guided search approach was tested in two experiments for the ATIS and WSJ data sets and results show significant reductions in recognition error rates.
UR - http://www.scopus.com/inward/record.url?scp=0036288695&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0036288695&partnerID=8YFLogxK
M3 - Conference contribution
VL - 4
BT - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
ER -