The use of dynamic reliability scoring in speech recognition

Mou, Xiaolong; Zue, Victor W.

doi:10.21437/icslp.2000-856

Search citation statements

Order By: Relevance

Paper Sections

Select...

Introduction1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2001

Publication Types

Select...

Other1

Relationship

Self Cite0

Independent1

Authors

Journals

Cited by 1 publication

(1 citation statement)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To reorder n-best hypothesis list, the additional information can be integrated to the recognizer itself or used sequentially by the reordering module after the recognition phase which is also called the post-processing approach. The integrated approach was applied in [3], where additional information from reliability models of acoustic units was used to adjust the scores of recognizer search paths. Some postprocessing approaches are described in [4] and [5].…”

Section: Introductionmentioning

confidence: 99%

N-best speech hypotheses reordering using linear regression

Chotimongkol

Rudnicky

2001

7th European Conference on Speech Communication and Technology (Eurospeech 2001)

View full text Add to dashboard Cite

We propose a hypothesis reordering technique to improve speech recognition accuracy in a dialog system. For such systems, additional information external to the decoding process itself is available, in particular features derived from the parse and the dialog. Such features can be combined with recognizer features by means of a linear regression model to predict the most likely entry in the hypothesis list. We introduce the use of concept error rate as an alternative accuracy measurement and compare it withy the use of word error rate. The proposed model performs better than human subjects performing the same hypothesis reordering task.

show abstract

Section: Introductionmentioning

confidence: 99%