Repository logo

Confidence Estimation and Deletion Prediction Using Bidirectional Recurrent Neural Networks

Accepted version


Conference Object

Change log


Ragni, A 
Li, Q 
Gales, MJF 
Wang, Y 


The standard approach to assess reliability of automatic speech transcriptions is through the use of confidence scores. If accurate, these scores provide a flexible mechanism to flag transcription errors for upstream and downstream applications. One challenging type of errors that recognisers make are deletions. These errors are not accounted for by the standard confidence estimation schemes and are hard to rectify in the upstream and downstream processing. High deletion rates are prominent in limited resource and highly mismatched training/testing conditions studied under IARPA Babel and Material programs. This paper looks at the use of bidirectional recurrent neural networks to yield confidence estimates in predicted as well as deleted words. Several simple schemes are examined for combination. To assess usefulness of this approach, the combined confidence score is examined for untranscribed data selection that favours transcriptions with lower deletion errors. Experiments are conducted using IARPA Babel/Material program languages.



confidence score, deletion error, bidirectional recurrent neural network

Journal Title

2018 IEEE Spoken Language Technology Workshop, SLT 2018 - Proceedings

Conference Name

2018 IEEE Spoken Language Technology Workshop (SLT)

Journal ISSN


Volume Title


ALTA Institute, Cambridge University; The Office of the Director of National Intelligence (ODNI), Intelligence Advanced Research Projects Activity (IARPA) via Air Force Research Laboratory (AFRL)