@inproceedings{a211ceeb20f645f793c09ba64d1e107d,
title = "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 suggest the proposed model is superior to previous methods, obtaining state-of-the-art results on the tested datasets.",
keywords = "Sequence segmentation, recurrent neural networks (RNNs), structured prediction, voice onset time, word segmentation",
author = "Yossi Adi and Joseph Keshet and Emily Cibelli and Matthew Goldrick",
note = "Funding Information: Supported in part by NIH grant 1R21HD077140 Publisher Copyright: {\textcopyright} 2017 IEEE.; 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 ; Conference date: 05-03-2017 Through 09-03-2017",
year = "2017",
month = jun,
day = "16",
doi = "10.1109/ICASSP.2017.7952591",
language = "English (US)",
series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "2422--2426",
booktitle = "2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings",
address = "United States",
}