1 code implementation • 12 Feb 2021 • G. Sun, C. Zhang, P. C. Woodland
To encode the cross-utterance information, the R-TLM incorporates an LSTM module together with a segment-wise recurrence in some of the Transformer blocks.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 12 Feb 2021 • G. Sun, D. Liu, C. Zhang, P. C. Woodland
Recent speaker diarisation systems often convert variable length speech segments into fixed-length vector representations for speaker clustering, which are known as speaker embeddings.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +4
no code implementations • 19 Aug 2020 • G. Sun, C. Zhang, P. C. Woodland
A cross-utterance LM (CULM) is proposed in this paper, which augments the input to a standard long short-term memory (LSTM) LM with a context vector derived from past and future utterances using an extraction network.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 3 Oct 2018 • Adnan Haider, P. C. Woodland
This paper presents a new optimisation approach to train Deep Neural Networks (DNNs) with discriminative sequence criteria.