Discriminative Segmental Cascades for Feature-Rich Phone Recognition

Abstract

Discriminative segmental models, such as segmental conditional random fields (SCRFs) and segmental structured support vector machines (SSVMs), have had success in speech recognition via both lattice rescoring and first-pass decoding. However, such models suffer from slow decoding, hampering the use of computationally expensive features, such as segment neural networks or other high-order features. A typical solution is to use approximate decoding, either by beam pruning in a single pass or by beam pruning to generate a lattice followed by a second pass. In this work, we study discriminative segmental models trained with a hinge loss (i.e., segmental structured SVMs). We show that beam search is not suitable for learning rescoring models in this approach, though it gives good approximate decoding performance when the model is already well-trained. Instead, we consider an approach inspired by structured prediction cascades, which use max-marginal pruning to generate lattices. We obtain a high-accuracy phonetic recognition system with several expensive feature types: a segment neural network, a second-order language model, and second-order phone boundary features.

References in corpus (2)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Do Deep Nets Really Need to be Deep?

Cited by in corpus (8)

• The History Began from AlexNet: A Comprehensive Survey on Deep Learning Approaches
• Sequence Prediction with Neural Segmental Models
• Lexicon-Free Fingerspelling Recognition from Video: Data, Models, and Signer Adaptation
• End-to-End Training Approaches for Discriminative Segmental Models
• American Sign Language fingerspelling recognition from video: Methods for unrestricted recognition and signer-independence
• Signer-independent Fingerspelling Recognition with Deep Neural Network Adaptation
• Whole-Word Segmental Speech Recognition with Acoustic Word Embeddings
• Efficient Segmental Cascades for Speech Recognition