Sequence Prediction With Neural Segmental Models

Abstract

Segments that span contiguous parts of inputs, such as phonemes in speech, named entities in sentences, actions in videos, occur frequently in sequence prediction problems. Segmental models, a class of models that explicitly hypothesizes segments, have allowed the exploration of rich segment features for sequence prediction. However, segmental models suffer from slow decoding, hampering the use of computationally expensive features. In this thesis, we introduce discriminative segmental cascades, a multi-pass inference framework that allows us to improve accuracy by adding higher-order features and neural segmental features while maintaining efficiency. We also show that instead of including more features to obtain better accuracy, segmental cascades can be used to speed up training and decoding. Segmental models, similarly to conventional speech recognizers, are typically trained in multiple stages. In the first stage, a frame classifier is trained with manual alignments, and then

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keytang2017sequence

Related papers

• Efficient Segmental Cascades For Speech Recognition (2016)0.00
• End-to-end Neural Segmental Models For Speech Recognition (2017)9.23
• End-to-end Training Approaches For Discriminative Segmental Models (2016)5.84
• Sequence Segmentation Using Joint RNN And Structured Prediction Models (2016)7.81
• Blind Phoneme Segmentation With Temporal Prediction Errors (2016)8.35
• Segmental Recurrent Neural Networks For End-to-end Speech Recognition (2016)0.00
• Unsupervised Speech Segmentation And Variable Rate Representation Learning Using Segmental Contrastive Predictive Coding (2021)9.92
• Segmental Contrastive Predictive Coding For Unsupervised Word Segmentation (2021)0.00