Edinburgh Research Explorer

A system for automatic alignment of broadcast media captions using weighted finite-state transducers

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Original languageEnglish
Title of host publication2015 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU 2015)
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages675-680
Number of pages6
ISBN (Print)978-1-4799-7291-3
DOIs
Publication statusPublished - 2015

Abstract

We describe our system for alignment of broadcast media captions in the 2015 MGB Challenge. A precise time alignment of previously-generated subtitles to media data is important in the process of caption generation by broadcasters. However,this task is challenging due to the highly diverse, often noisy content of the audio, and because the subtitles are frequently not a verbatim representation of the actual words spoken. Our system employs a two-pass approach with appropriately constrained weighted finite state transducers (WFSTs) to enable good alignment even when the audio quality would be challenging for conventional ASR. The system achieves an f-score of 0.8965 on the MGB Challenge development set.

Download statistics

No data available

ID: 23593216