Sorry, you need to enable JavaScript to visit this website.

Spoken Language Understanding (SLP-UNDE)

Lexico-acoustic Neural-based Models for Dialog Act Classification


Recent works have proposed neural models for dialog act classification in spoken dialogs.
However, they have not explored the role and the usefulness of acoustic information.
We propose a neural model that processes both lexical and acoustic features for classification.
Our results on two benchmark datasets reveal that acoustic features are helpful in improving the overall accuracy.

Paper Details

Authors:
Daniel Ortega, Ngoc Thang Vu
Submitted On:
14 April 2018 - 12:45am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

icassp-2018-poster.pdf

(123)

Subscribe

[1] Daniel Ortega, Ngoc Thang Vu, "Lexico-acoustic Neural-based Models for Dialog Act Classification", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2796. Accessed: Jul. 19, 2019.
@article{2796-18,
url = {http://sigport.org/2796},
author = {Daniel Ortega; Ngoc Thang Vu },
publisher = {IEEE SigPort},
title = {Lexico-acoustic Neural-based Models for Dialog Act Classification},
year = {2018} }
TY - EJOUR
T1 - Lexico-acoustic Neural-based Models for Dialog Act Classification
AU - Daniel Ortega; Ngoc Thang Vu
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2796
ER -
Daniel Ortega, Ngoc Thang Vu. (2018). Lexico-acoustic Neural-based Models for Dialog Act Classification. IEEE SigPort. http://sigport.org/2796
Daniel Ortega, Ngoc Thang Vu, 2018. Lexico-acoustic Neural-based Models for Dialog Act Classification. Available at: http://sigport.org/2796.
Daniel Ortega, Ngoc Thang Vu. (2018). "Lexico-acoustic Neural-based Models for Dialog Act Classification." Web.
1. Daniel Ortega, Ngoc Thang Vu. Lexico-acoustic Neural-based Models for Dialog Act Classification [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2796

Joint Verification-Identification in End-to-End Multi-Scale CNN Framework for Topic Identification


We present an end-to-end multi-scale Convolutional Neural
Network (CNN) framework for topic identification (topic ID).
In this work, we examined multi-scale CNN for classification
using raw text input. Topical word embeddings are learnt at
multiple scales using parallel convolutional layers. A technique
to integrate verification and identification objectives is
examined to improve topic ID performance. With this approach,
we achieved significant improvement in identification
task. We evaluated our framework on two contrasting

Paper Details

Authors:
Raghavendra Pappagari, Jesus Villalba, Najim Dehak
Submitted On:
13 April 2018 - 4:16pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Final.pdf

(147)

Subscribe

[1] Raghavendra Pappagari, Jesus Villalba, Najim Dehak, "Joint Verification-Identification in End-to-End Multi-Scale CNN Framework for Topic Identification", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2758. Accessed: Jul. 19, 2019.
@article{2758-18,
url = {http://sigport.org/2758},
author = {Raghavendra Pappagari; Jesus Villalba; Najim Dehak },
publisher = {IEEE SigPort},
title = {Joint Verification-Identification in End-to-End Multi-Scale CNN Framework for Topic Identification},
year = {2018} }
TY - EJOUR
T1 - Joint Verification-Identification in End-to-End Multi-Scale CNN Framework for Topic Identification
AU - Raghavendra Pappagari; Jesus Villalba; Najim Dehak
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2758
ER -
Raghavendra Pappagari, Jesus Villalba, Najim Dehak. (2018). Joint Verification-Identification in End-to-End Multi-Scale CNN Framework for Topic Identification. IEEE SigPort. http://sigport.org/2758
Raghavendra Pappagari, Jesus Villalba, Najim Dehak, 2018. Joint Verification-Identification in End-to-End Multi-Scale CNN Framework for Topic Identification. Available at: http://sigport.org/2758.
Raghavendra Pappagari, Jesus Villalba, Najim Dehak. (2018). "Joint Verification-Identification in End-to-End Multi-Scale CNN Framework for Topic Identification." Web.
1. Raghavendra Pappagari, Jesus Villalba, Najim Dehak. Joint Verification-Identification in End-to-End Multi-Scale CNN Framework for Topic Identification [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2758

A Joint Multi-Task Learning Framework For Spoken Language Understanding

Paper Details

Authors:
Cunliang Kong,Yan Zhao
Submitted On:
13 April 2018 - 5:34am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

A Joint Multi-Task Learning Framework For Spoken Language.pdf

(23)

Subscribe

[1] Cunliang Kong,Yan Zhao, "A Joint Multi-Task Learning Framework For Spoken Language Understanding", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2669. Accessed: Jul. 19, 2019.
@article{2669-18,
url = {http://sigport.org/2669},
author = {Cunliang Kong;Yan Zhao },
publisher = {IEEE SigPort},
title = {A Joint Multi-Task Learning Framework For Spoken Language Understanding},
year = {2018} }
TY - EJOUR
T1 - A Joint Multi-Task Learning Framework For Spoken Language Understanding
AU - Cunliang Kong;Yan Zhao
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2669
ER -
Cunliang Kong,Yan Zhao. (2018). A Joint Multi-Task Learning Framework For Spoken Language Understanding. IEEE SigPort. http://sigport.org/2669
Cunliang Kong,Yan Zhao, 2018. A Joint Multi-Task Learning Framework For Spoken Language Understanding. Available at: http://sigport.org/2669.
Cunliang Kong,Yan Zhao. (2018). "A Joint Multi-Task Learning Framework For Spoken Language Understanding." Web.
1. Cunliang Kong,Yan Zhao. A Joint Multi-Task Learning Framework For Spoken Language Understanding [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2669

PSEUDO-SUPERVISED APPROACH FOR TEXT CLUSTERING BASED ON CONSENSUS ANALYSIS


In recent years, neural networks (NN) have achieved remarkable performance improvement in text classification due to
their powerful ability to encode discriminative features by incorporating label information into model training. Inspired
by the success of NN in text classification, we propose a pseudo-supervised neural network approach for text clustering.
The neural network is trained in a supervised fashion with pseudo-labels, which are provided by the cluster labels

Paper Details

Authors:
Peixin Chen, Wu Guo, Lirong Dai, Zhenhua Ling
Submitted On:
13 April 2018 - 4:05am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP-Chen Peixin_v2.pdf

(21)

Keywords

Additional Categories

Subscribe

[1] Peixin Chen, Wu Guo, Lirong Dai, Zhenhua Ling, "PSEUDO-SUPERVISED APPROACH FOR TEXT CLUSTERING BASED ON CONSENSUS ANALYSIS", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2647. Accessed: Jul. 19, 2019.
@article{2647-18,
url = {http://sigport.org/2647},
author = {Peixin Chen; Wu Guo; Lirong Dai; Zhenhua Ling },
publisher = {IEEE SigPort},
title = {PSEUDO-SUPERVISED APPROACH FOR TEXT CLUSTERING BASED ON CONSENSUS ANALYSIS},
year = {2018} }
TY - EJOUR
T1 - PSEUDO-SUPERVISED APPROACH FOR TEXT CLUSTERING BASED ON CONSENSUS ANALYSIS
AU - Peixin Chen; Wu Guo; Lirong Dai; Zhenhua Ling
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2647
ER -
Peixin Chen, Wu Guo, Lirong Dai, Zhenhua Ling. (2018). PSEUDO-SUPERVISED APPROACH FOR TEXT CLUSTERING BASED ON CONSENSUS ANALYSIS. IEEE SigPort. http://sigport.org/2647
Peixin Chen, Wu Guo, Lirong Dai, Zhenhua Ling, 2018. PSEUDO-SUPERVISED APPROACH FOR TEXT CLUSTERING BASED ON CONSENSUS ANALYSIS. Available at: http://sigport.org/2647.
Peixin Chen, Wu Guo, Lirong Dai, Zhenhua Ling. (2018). "PSEUDO-SUPERVISED APPROACH FOR TEXT CLUSTERING BASED ON CONSENSUS ANALYSIS." Web.
1. Peixin Chen, Wu Guo, Lirong Dai, Zhenhua Ling. PSEUDO-SUPERVISED APPROACH FOR TEXT CLUSTERING BASED ON CONSENSUS ANALYSIS [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2647

Improving Semi-Supervised Classification for Low-Resource Speech Interaction Applications


We propose a semi-supervised learning method to improve classification performance in scenarios with limited labeled
data. We employ adaptation strategies such as entropy-filtering and self-training, and show that our method achieves

Paper Details

Authors:
Pavlos Papadopoulos, Ruchir Travadi, Daniel Bone, Shrikanth Narayanan
Submitted On:
12 April 2018 - 6:08pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

ICASSP2018_Poster.pdf

(191)

Subscribe

[1] Pavlos Papadopoulos, Ruchir Travadi, Daniel Bone, Shrikanth Narayanan, "Improving Semi-Supervised Classification for Low-Resource Speech Interaction Applications", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2507. Accessed: Jul. 19, 2019.
@article{2507-18,
url = {http://sigport.org/2507},
author = {Pavlos Papadopoulos; Ruchir Travadi; Daniel Bone; Shrikanth Narayanan },
publisher = {IEEE SigPort},
title = {Improving Semi-Supervised Classification for Low-Resource Speech Interaction Applications},
year = {2018} }
TY - EJOUR
T1 - Improving Semi-Supervised Classification for Low-Resource Speech Interaction Applications
AU - Pavlos Papadopoulos; Ruchir Travadi; Daniel Bone; Shrikanth Narayanan
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2507
ER -
Pavlos Papadopoulos, Ruchir Travadi, Daniel Bone, Shrikanth Narayanan. (2018). Improving Semi-Supervised Classification for Low-Resource Speech Interaction Applications. IEEE SigPort. http://sigport.org/2507
Pavlos Papadopoulos, Ruchir Travadi, Daniel Bone, Shrikanth Narayanan, 2018. Improving Semi-Supervised Classification for Low-Resource Speech Interaction Applications. Available at: http://sigport.org/2507.
Pavlos Papadopoulos, Ruchir Travadi, Daniel Bone, Shrikanth Narayanan. (2018). "Improving Semi-Supervised Classification for Low-Resource Speech Interaction Applications." Web.
1. Pavlos Papadopoulos, Ruchir Travadi, Daniel Bone, Shrikanth Narayanan. Improving Semi-Supervised Classification for Low-Resource Speech Interaction Applications [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2507

CONVOLUTIONAL NEURAL NETWORKS AND MULTITASK STRATEGIES FOR SEMANTIC MAPPING OF NATURAL LANGUAGE INPUT TO A STRUCTURED DATABASE


In this work, we investigate mapping both natural language food and quantity descriptions to matching USDA database entries. We demonstrate that a convolutional neural network (CNN) model with a softmax layer on top to directly predict the most likely database matches outperforms our previous state-of-the-art approach of learning binary classification and subsequently ranking database entries using similarity scores with the learned embeddings.

Paper Details

Authors:
Mandy Korpusik, James Glass
Submitted On:
12 April 2018 - 12:21pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

icassp_2018.pdf

(364)

Subscribe

[1] Mandy Korpusik, James Glass, "CONVOLUTIONAL NEURAL NETWORKS AND MULTITASK STRATEGIES FOR SEMANTIC MAPPING OF NATURAL LANGUAGE INPUT TO A STRUCTURED DATABASE", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2431. Accessed: Jul. 19, 2019.
@article{2431-18,
url = {http://sigport.org/2431},
author = {Mandy Korpusik; James Glass },
publisher = {IEEE SigPort},
title = {CONVOLUTIONAL NEURAL NETWORKS AND MULTITASK STRATEGIES FOR SEMANTIC MAPPING OF NATURAL LANGUAGE INPUT TO A STRUCTURED DATABASE},
year = {2018} }
TY - EJOUR
T1 - CONVOLUTIONAL NEURAL NETWORKS AND MULTITASK STRATEGIES FOR SEMANTIC MAPPING OF NATURAL LANGUAGE INPUT TO A STRUCTURED DATABASE
AU - Mandy Korpusik; James Glass
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2431
ER -
Mandy Korpusik, James Glass. (2018). CONVOLUTIONAL NEURAL NETWORKS AND MULTITASK STRATEGIES FOR SEMANTIC MAPPING OF NATURAL LANGUAGE INPUT TO A STRUCTURED DATABASE. IEEE SigPort. http://sigport.org/2431
Mandy Korpusik, James Glass, 2018. CONVOLUTIONAL NEURAL NETWORKS AND MULTITASK STRATEGIES FOR SEMANTIC MAPPING OF NATURAL LANGUAGE INPUT TO A STRUCTURED DATABASE. Available at: http://sigport.org/2431.
Mandy Korpusik, James Glass. (2018). "CONVOLUTIONAL NEURAL NETWORKS AND MULTITASK STRATEGIES FOR SEMANTIC MAPPING OF NATURAL LANGUAGE INPUT TO A STRUCTURED DATABASE." Web.
1. Mandy Korpusik, James Glass. CONVOLUTIONAL NEURAL NETWORKS AND MULTITASK STRATEGIES FOR SEMANTIC MAPPING OF NATURAL LANGUAGE INPUT TO A STRUCTURED DATABASE [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2431

Semantic Mapping of Natural Language Input to Database Entries via Convolutional Neural Networks


Natural language processing research has made major advances with the concept of representing words, sentences, paragraphs, and even documents by embedded vector representations. We apply this idea to the problem of relating foods, as expressed in natural language meal descriptions, to corresponding database entries. We generate fixed-length embeddings for U.S.

Paper Details

Authors:
Zachary Collins, Jim Glass
Submitted On:
3 March 2017 - 12:34pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:

Document Files

icassp_17.pdf

(315)

Subscribe

[1] Zachary Collins, Jim Glass, "Semantic Mapping of Natural Language Input to Database Entries via Convolutional Neural Networks", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/1616. Accessed: Jul. 19, 2019.
@article{1616-17,
url = {http://sigport.org/1616},
author = {Zachary Collins; Jim Glass },
publisher = {IEEE SigPort},
title = {Semantic Mapping of Natural Language Input to Database Entries via Convolutional Neural Networks},
year = {2017} }
TY - EJOUR
T1 - Semantic Mapping of Natural Language Input to Database Entries via Convolutional Neural Networks
AU - Zachary Collins; Jim Glass
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/1616
ER -
Zachary Collins, Jim Glass. (2017). Semantic Mapping of Natural Language Input to Database Entries via Convolutional Neural Networks. IEEE SigPort. http://sigport.org/1616
Zachary Collins, Jim Glass, 2017. Semantic Mapping of Natural Language Input to Database Entries via Convolutional Neural Networks. Available at: http://sigport.org/1616.
Zachary Collins, Jim Glass. (2017). "Semantic Mapping of Natural Language Input to Database Entries via Convolutional Neural Networks." Web.
1. Zachary Collins, Jim Glass. Semantic Mapping of Natural Language Input to Database Entries via Convolutional Neural Networks [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/1616

THE SHEFFIELD SEARCH AND RESCUE CORPUS


As part of an ongoing research into extracting mission-critical information from Search and Rescue speech communications, a corpus of unscripted, goal-oriented, two-party spoken conversations has been designed and collected. The Sheffield Search and Rescue (SSAR) corpus comprises about 12 hours of data from 96 conversations by 24 native speakers of British English with a southern accent. Each conversation is about a collaborative task of exploring and estimating a simulated indoor environment.

Paper Details

Authors:
Saeid Mokaram, Roger K. Moore
Submitted On:
28 February 2017 - 5:01am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Poster: THE SHEFFIELD SEARCH AND RESCUE CORPUS

(331)

Subscribe

[1] Saeid Mokaram, Roger K. Moore, "THE SHEFFIELD SEARCH AND RESCUE CORPUS", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/1494. Accessed: Jul. 19, 2019.
@article{1494-17,
url = {http://sigport.org/1494},
author = {Saeid Mokaram; Roger K. Moore },
publisher = {IEEE SigPort},
title = {THE SHEFFIELD SEARCH AND RESCUE CORPUS},
year = {2017} }
TY - EJOUR
T1 - THE SHEFFIELD SEARCH AND RESCUE CORPUS
AU - Saeid Mokaram; Roger K. Moore
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/1494
ER -
Saeid Mokaram, Roger K. Moore. (2017). THE SHEFFIELD SEARCH AND RESCUE CORPUS. IEEE SigPort. http://sigport.org/1494
Saeid Mokaram, Roger K. Moore, 2017. THE SHEFFIELD SEARCH AND RESCUE CORPUS. Available at: http://sigport.org/1494.
Saeid Mokaram, Roger K. Moore. (2017). "THE SHEFFIELD SEARCH AND RESCUE CORPUS." Web.
1. Saeid Mokaram, Roger K. Moore. THE SHEFFIELD SEARCH AND RESCUE CORPUS [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/1494

EEG Evidence for a Three-Phase Recurrent Process during Spoken Word Processing

Paper Details

Authors:
Bin Zhao, Jianwu Dang, Gaoyan Zhang
Submitted On:
15 October 2016 - 10:03am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ISCSLP 2016_Bin Zhao.pdf

(70)

Subscribe

[1] Bin Zhao, Jianwu Dang, Gaoyan Zhang, "EEG Evidence for a Three-Phase Recurrent Process during Spoken Word Processing", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/1236. Accessed: Jul. 19, 2019.
@article{1236-16,
url = {http://sigport.org/1236},
author = {Bin Zhao; Jianwu Dang; Gaoyan Zhang },
publisher = {IEEE SigPort},
title = {EEG Evidence for a Three-Phase Recurrent Process during Spoken Word Processing},
year = {2016} }
TY - EJOUR
T1 - EEG Evidence for a Three-Phase Recurrent Process during Spoken Word Processing
AU - Bin Zhao; Jianwu Dang; Gaoyan Zhang
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/1236
ER -
Bin Zhao, Jianwu Dang, Gaoyan Zhang. (2016). EEG Evidence for a Three-Phase Recurrent Process during Spoken Word Processing. IEEE SigPort. http://sigport.org/1236
Bin Zhao, Jianwu Dang, Gaoyan Zhang, 2016. EEG Evidence for a Three-Phase Recurrent Process during Spoken Word Processing. Available at: http://sigport.org/1236.
Bin Zhao, Jianwu Dang, Gaoyan Zhang. (2016). "EEG Evidence for a Three-Phase Recurrent Process during Spoken Word Processing." Web.
1. Bin Zhao, Jianwu Dang, Gaoyan Zhang. EEG Evidence for a Three-Phase Recurrent Process during Spoken Word Processing [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/1236

Dialog State Tracking for Interview Coaching Using Two-Level LSTM


This study presents an approach to dialog state tracking (DST) in an interview conversation by using the long short-term memory (LSTM) and artificial neural network (ANN). First, the techniques of word embedding are employed for word representation by using the word2vec model. Then, each input sentence is represented by a sentence hidden vector using the LSTM-based sentence model. The sentence hidden vectors for each sentence are fed to the LSTM-based answer model to map the interviewee’s answer to an answer hidden vector.

Paper Details

Authors:
Ming-Hsiang Su, Kun-Yi Huang, Tsung-Hsien Yang, and Tsui-Ching Huang
Submitted On:
14 October 2016 - 11:52pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ISCSLP-2016-1012-MH.pdf

(339)

Subscribe

[1] Ming-Hsiang Su, Kun-Yi Huang, Tsung-Hsien Yang, and Tsui-Ching Huang, "Dialog State Tracking for Interview Coaching Using Two-Level LSTM", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/1215. Accessed: Jul. 19, 2019.
@article{1215-16,
url = {http://sigport.org/1215},
author = {Ming-Hsiang Su; Kun-Yi Huang; Tsung-Hsien Yang; and Tsui-Ching Huang },
publisher = {IEEE SigPort},
title = {Dialog State Tracking for Interview Coaching Using Two-Level LSTM},
year = {2016} }
TY - EJOUR
T1 - Dialog State Tracking for Interview Coaching Using Two-Level LSTM
AU - Ming-Hsiang Su; Kun-Yi Huang; Tsung-Hsien Yang; and Tsui-Ching Huang
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/1215
ER -
Ming-Hsiang Su, Kun-Yi Huang, Tsung-Hsien Yang, and Tsui-Ching Huang. (2016). Dialog State Tracking for Interview Coaching Using Two-Level LSTM. IEEE SigPort. http://sigport.org/1215
Ming-Hsiang Su, Kun-Yi Huang, Tsung-Hsien Yang, and Tsui-Ching Huang, 2016. Dialog State Tracking for Interview Coaching Using Two-Level LSTM. Available at: http://sigport.org/1215.
Ming-Hsiang Su, Kun-Yi Huang, Tsung-Hsien Yang, and Tsui-Ching Huang. (2016). "Dialog State Tracking for Interview Coaching Using Two-Level LSTM." Web.
1. Ming-Hsiang Su, Kun-Yi Huang, Tsung-Hsien Yang, and Tsui-Ching Huang. Dialog State Tracking for Interview Coaching Using Two-Level LSTM [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/1215

Pages