Interspeech 2016

Abstract

Improving the performance of distant speech recognition is of considerable current interest, driven by a desire to bring speech recognition into people's homes. Standard approaches to this task aim to enhance the signal prior to recognition, typically using beamforming techniques on multiple channels. Only few real-world recordings are available that allow experimentation with such techniques. This has become even more pertinent with recent works with deep neural networks aiming to learn beamforming from data. Such approaches require large multichannel training sets, ideally with location annotation for moving speakers, which is scarce in existing corpora. This paper presents a freely available and new extended corpus of English speech recordings in a natural setting, with moving speakers. The data is recorded with diverse microphone arrays, and uniquely, with ground truth location tracking. It extends the 8.0 hour Sheffield Wargames Corpus released in Interspeech 2013, with a further 16.6 hours of fully annotated data, including 6.1 hours of female speech to improve gender bias. Additional blog-based language model data is provided alongside, as well as a Kaldi baseline system. Results are reported with a standard Kaldi configuration, and a baseline meeting recognition system.

A Neural Network Architecture for Detecting Grammatical Errors in Statistical Machine Translation

“…Despite their similarities, LSTMs and GRUs have been shown to outperform each other in particular NLP tasks. LSTMs, for example, seem to be a better approach for language modelling (Irie et al, 2016). GRUs, on the other hand, have been shown to perform better in the task of word-level quality estimation of machine translation (Patel and Sasikumar, 2016).…”