Sequence Segmentation Using Joint RNN And Structured Prediction Models

Abstract

We describe and analyze a simple and effective algorithm for sequence segmentation applied to speech processing tasks. We propose a neural architecture that is composed of two modules trained jointly: a recurrent neural network (RNN) module and a structured prediction model. The RNN outputs are considered as feature functions to the structured model. The overall model is trained with a structured loss function which can be designed to the given segmentation task. We demonstrate the effectiveness of our method by applying it to two simple tasks commonly used in phonetic studies: word segmentation and voice onset time segmentation. Results sug- gest the proposed model is superior to previous methods, ob- taining state-of-the-art results on the tested datasets.

Stats

• citations10
• S2 citations—
• github stars0
• HF likes0
• heat score7.81
• arxiv keyadi2016sequence

Related papers

• Sequence Prediction With Neural Segmental Models (2017)0.00
• End-to-end Neural Segmental Models For Speech Recognition (2017)9.23
• Segmental Recurrent Neural Networks For End-to-end Speech Recognition (2016)0.00
• Joint Online Spoken Language Understanding And Language Modeling With Recurrent Neural Networks (2016)13.28
• Blind Phoneme Segmentation With Temporal Prediction Errors (2016)8.35
• End-to-end Training Approaches For Discriminative Segmental Models (2016)5.84
• Unsupervised Speech Segmentation And Variable Rate Representation Learning Using Segmental Contrastive Predictive Coding (2021)9.92
• Dual-path RNN: Efficient Long Sequence Modeling For Time-domain Single-channel Speech Separation (2019)21.06