CUED Publications database

Cambridge university transcription systems for the multi-genre broadcast challenge

Woodland, PC and Liu, X and Qian, Y and Zhang, C and Gales, MJF and Karanasou, P and Lanchantin, P and Wang, L (2016) Cambridge university transcription systems for the multi-genre broadcast challenge. In: UNSPECIFIED pp. 639-646..

Full text not available from this repository.

Abstract

© 2015 IEEE. We describe the development of our speech-to-text transcription systems for the 2015 Multi-Genre Broadcast (MGB) challenge. Key features of the systems are: a segmentation system based on deep neural networks (DNNs); the use of HTK 3.5 for building DNN-based hybrid and tandem acoustic models and the use of these models in a joint decoding framework; techniques for adaptation of DNN based acoustic models including parameterised activation function adaptation; alternative acoustic models built using Kaldi; and recurrent neural network language models (RNNLMs) and RNNLM adaptation. The same language models were used with both HTK and Kaldi acoustic models and various combined systems built. The final systems had the lowest error rates on the evaluation data.

Item Type: Conference or Workshop Item (UNSPECIFIED)
Subjects: UNSPECIFIED
Divisions: Div F > Machine Intelligence
Depositing User: Cron Job
Date Deposited: 17 Jul 2017 19:01
Last Modified: 21 Nov 2017 03:50
DOI: