Segmental Recurrent Neural Networks For End-to-end Speech Recognition

Abstract

We study the segmental recurrent neural network for end-to-end acoustic modelling. This model connects the segmental conditional random field (CRF) with a recurrent neural network (RNN) used for feature extraction. Compared to most previous CRF-based acoustic models, it does not rely on an external system to provide features or segmentation boundaries. Instead, this model marginalises out all the possible segmentations, and features are extracted from the RNN trained together with the segmental CRF. In essence, this model is self-contained and can be trained end-to-end. In this paper, we discuss practical training and decoding issues as well as the method to speed up the training in the context of speech recognition. We performed experiments on the TIMIT dataset. We achieved 17.3 phone error rate (PER) from the first-pass decoding --- the best reported result using CRFs, despite the fact that we only used a zeroth-order CRF and without using any language model.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keylu2016segmental

Related papers

• Multitask Learning With CTC And Segmental CRF For Speech Recognition (2017)0.00
• End-to-end Neural Segmental Models For Speech Recognition (2017)9.23
• Wavecrn: An Efficient Convolutional Recurrent Neural Network For End-to-end Speech Enhancement (2020)14.02
• End-to-end Training Approaches For Discriminative Segmental Models (2016)5.84
• Self-attention Transducers For End-to-end Speech Recognition (2019)11.93
• Efficient Segmental Cascades For Speech Recognition (2016)0.00
• Sequence Segmentation Using Joint RNN And Structured Prediction Models (2016)7.81
• Exploring Architectures, Data And Units For Streaming End-to-end Speech Recognition With Rnn-transducer (2018)16.21