Efficient Segmental Cascades For Speech Recognition

Abstract

Discriminative segmental models offer a way to incorporate flexible feature functions into speech recognition. However, their appeal has been limited by their computational requirements, due to the large number of possible segments to consider. Multi-pass cascades of segmental models introduce features of increasing complexity in different passes, where in each pass a segmental model rescores lattices produced by a previous (simpler) segmental model. In this paper, we explore several ways of making segmental cascades efficient and practical: reducing the feature set in the first pass, frame subsampling, and various pruning approaches. In experiments on phonetic recognition, we find that with a combination of such techniques, it is possible to maintain competitive performance while greatly reducing decoding, pruning, and training time.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keytang2016efficient

Related papers

• Sequence Prediction With Neural Segmental Models (2017)0.00
• Segmental Recurrent Neural Networks For End-to-end Speech Recognition (2016)0.00
• End-to-end Neural Segmental Models For Speech Recognition (2017)9.23
• Multitask Learning With CTC And Segmental CRF For Speech Recognition (2017)0.00
• Tight Integrated End-to-end Training For Cascaded Speech Translation (2020)8.35
• End-to-end Training Approaches For Discriminative Segmental Models (2016)5.84
• CTC Blank Triggered Dynamic Layer-skipping For Efficient Ctc-based Speech Recognition (2024)0.00
• Constrained Convolutional-recurrent Networks To Improve Speech Quality With Low Impact On Recognition Accuracy (2018)5.24