The MGB Challenge: Evaluating Multi-Genre Broadcast Media Recognition

Peter Bell, MJF Gales, Thomas Hain, Jonathan Kilgour, Pierre Lanchantin, Xunying Liu, Andrew McParland, Steve Renals, Oscar Saz, Mirjam Wester, PC Woodland

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


This paper describes the Multi-Genre Broadcast (MGB) Challenge at ASRU~2015, an evaluation focused on speech recognition, speaker diarization, and lightly supervised alignment of BBC TV recordings. The challenge training data covered the whole range of seven weeks BBC TV output across four channels, resulting in about 1,600 hours of broadcast audio. In addition several hundred million words of BBC subtitle text was provided for language modelling. A novel aspect of the evaluation was the exploration of speech recognition and speaker diarization in a longitudinal setting – i.e. recognition of several episodes of the same show, and speaker diarization across these episodes, linking speakers. The longitudinal tasks also offered the opportunity for systems to make use of supplied metadata including show title, genre tag, and date/time of transmission. This paper describes the task data and evaluation process used in the MGB challenge, and summarises the results obtained.
Original languageEnglish
Title of host publicationAutomatic Speech Recognition and Understanding (ASRU), 2015 IEEE Workshop on
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages687 - 693
Number of pages7
ISBN (Electronic)978-1-4799-7291-3
ISBN (Print)978-1-4799-7290-6
Publication statusPublished - 2015

Fingerprint Dive into the research topics of 'The MGB Challenge: Evaluating Multi-Genre Broadcast Media Recognition'. Together they form a unique fingerprint.

Cite this