Paper Info
Title
The 2015 sheffield system for transcription of Multi-Genre Broadcast media
Abstract
We describe the University of Sheffield system for participation in the 2015 Multi-Genre Broadcast (MGB) challenge task of transcribing multi-genre broadcast shows. Transcription was one of four tasks proposed in the MGB challenge, with the aim of advancing the state of the art of automatic speech recognition, speaker diarisation and automatic alignment of subtitles for broadcast media. Four topics are investigated in this work: Data selection techniques for training with unreliable data, automatic speech segmentation of broadcast media shows, acoustic modelling and adaptation in highly variable environments, and language modelling of multi-genre shows. The final system operates in multiple passes, using an initial unadapted decoding stage to refine segmentation, followed by three adapted passes: a hybrid DNN pass with input features normalised by speaker-based cepstral normalisation, another hybrid stage with input features normalised by speaker feature-MLLR transformations, and finally a bottleneck-based tandem stage with noise and speaker factorisation. The combination of these three system outputs provides a final error rate of 27.5% on the official development set, consisting of 47 multi-genre shows.
Year
DOI
Venue
2015
10.1109/ASRU.2015.7404854
2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)
Keywords
DocType
Volume
Multi-genre broadcasts,automatic speech recognition,data selection,speech segmentation,acoustic adaptation,language adaptation
Journal
abs/1512.06643
Citations 
PageRank 
References 
6
0.46
20
Authors
8
Name
Order
Citations
PageRank
Oscar Saz114216.30
Mortaza Doulaty2335.35
Salil Deena3273.61
Rosanna Milner4112.59
Raymond W. M. Ng534021.61
Madina Hasan6135.35
Yulan Liu760.46
Thomas Hain8184.50