Sequence segmentation using joint RNN and structured prediction models

Yossi Adi; Joseph Keshet; Emily Cibelli; Matthew Goldrick

doi:10.1109/ICASSP.2017.7952591

Sequence segmentation using joint RNN and structured prediction models

Yossi Adi, Joseph Keshet, Emily Cibelli, Matthew Goldrick

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

19 Scopus citations

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.

Original language	English
Title of host publication	2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	2422-2426
Number of pages	5
ISBN (Electronic)	9781509041176
DOIs	https://doi.org/10.1109/ICASSP.2017.7952591
State	Published - 16 Jun 2017
Externally published	Yes
Event	2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - New Orleans, United States Duration: 5 Mar 2017 → 9 Mar 2017

Publication series

Name	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
ISSN (Print)	1520-6149

Conference

Conference	2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017
Country/Territory	United States
City	New Orleans
Period	5/03/17 → 9/03/17

Bibliographical note

Publisher Copyright:
© 2017 IEEE.

Keywords

Sequence segmentation
recurrent neural networks (RNNs)
structured prediction
voice onset time
word segmentation

Access to Document

10.1109/ICASSP.2017.7952591

Cite this

Adi, Y., Keshet, J., Cibelli, E., & Goldrick, M. (2017). Sequence segmentation using joint RNN and structured prediction models. In 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings (pp. 2422-2426). Article 7952591 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP.2017.7952591

Adi, Yossi ; Keshet, Joseph ; Cibelli, Emily et al. / Sequence segmentation using joint RNN and structured prediction models. 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 2422-2426 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

@inproceedings{83a418df458a414790cfb4e3341d6027,

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 = "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 = "אנגלית",

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 = "ארצות הברית",

}

Adi, Y, Keshet, J, Cibelli, E & Goldrick, M 2017, Sequence segmentation using joint RNN and structured prediction models. in 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings., 7952591, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 2422-2426, 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017, New Orleans, United States, 5/03/17. https://doi.org/10.1109/ICASSP.2017.7952591

Sequence segmentation using joint RNN and structured prediction models. / Adi, Yossi; Keshet, Joseph; Cibelli, Emily et al.
2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. p. 2422-2426 7952591 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Sequence segmentation using joint RNN and structured prediction models

AU - Adi, Yossi

AU - Keshet, Joseph

AU - Cibelli, Emily

AU - Goldrick, Matthew

PY - 2017/6/16

Y1 - 2017/6/16

N2 - 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.

AB - 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.

KW - Sequence segmentation

KW - recurrent neural networks (RNNs)

KW - structured prediction

KW - voice onset time

KW - word segmentation

UR - http://www.scopus.com/inward/record.url?scp=85023771111&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2017.7952591

DO - 10.1109/ICASSP.2017.7952591

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:85023771111

T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

SP - 2422

EP - 2426

BT - 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017

Y2 - 5 March 2017 through 9 March 2017

ER -

Adi Y, Keshet J, Cibelli E, Goldrick M. Sequence segmentation using joint RNN and structured prediction models. In 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2017. p. 2422-2426. 7952591. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). doi: 10.1109/ICASSP.2017.7952591

Sequence segmentation using joint RNN and structured prediction models

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this