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

Spoken Language Understanding (SLP-UNDE)

Novel realizations of speech-driven head movements with generative adversarial networks


Head movement is an integral part of face-to-face communications. It is important to investigate methodologies to generate naturalistic movements for conversational agents (CAs). The predominant method for head movement generation is using rules based on the meaning of the message. However, the variations of head movements by these methods are bounded by the predefined dictionary of gestures. Speech-driven methods offer an alternative approach, learning the relationship between speech and head movements from real recordings.

Paper Details

Authors:
Najmeh Sadoughi, Carlos Busso
Submitted On:
20 May 2020 - 10:23am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

Sadoughi_2018-poster.pdf

(10)

Subscribe

[1] Najmeh Sadoughi, Carlos Busso, "Novel realizations of speech-driven head movements with generative adversarial networks", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5412. Accessed: Jul. 09, 2020.
@article{5412-20,
url = {http://sigport.org/5412},
author = {Najmeh Sadoughi; Carlos Busso },
publisher = {IEEE SigPort},
title = {Novel realizations of speech-driven head movements with generative adversarial networks},
year = {2020} }
TY - EJOUR
T1 - Novel realizations of speech-driven head movements with generative adversarial networks
AU - Najmeh Sadoughi; Carlos Busso
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5412
ER -
Najmeh Sadoughi, Carlos Busso. (2020). Novel realizations of speech-driven head movements with generative adversarial networks. IEEE SigPort. http://sigport.org/5412
Najmeh Sadoughi, Carlos Busso, 2020. Novel realizations of speech-driven head movements with generative adversarial networks. Available at: http://sigport.org/5412.
Najmeh Sadoughi, Carlos Busso. (2020). "Novel realizations of speech-driven head movements with generative adversarial networks." Web.
1. Najmeh Sadoughi, Carlos Busso. Novel realizations of speech-driven head movements with generative adversarial networks [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5412

Combining Acoustics, Content and Interaction Features to Find Hot Spots in Meetings


Involvement hot spots have been proposed as a useful concept for meeting analysis and studied off and on for over 15 years. These are regions of meetings that are marked by high participant involvement, as judged by human annotators. However, prior work was either not conducted in a formal machine learning setting, or focused on only a subset of possible meeting features or downstream applications (such as summarization). In this paper we investigate to what extent various acoustic, linguistic and pragmatic aspects of the meetings, both in isolation and jointly, can help detect hot spots.

Paper Details

Authors:
Dave Makhervaks, William Hinthorn, Dimitrios Dimitriadis, Andreas Stolcke
Submitted On:
15 May 2020 - 1:11am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ConferencePresentation.pdf

(14)

Subscribe

[1] Dave Makhervaks, William Hinthorn, Dimitrios Dimitriadis, Andreas Stolcke, "Combining Acoustics, Content and Interaction Features to Find Hot Spots in Meetings", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5334. Accessed: Jul. 09, 2020.
@article{5334-20,
url = {http://sigport.org/5334},
author = {Dave Makhervaks; William Hinthorn; Dimitrios Dimitriadis; Andreas Stolcke },
publisher = {IEEE SigPort},
title = {Combining Acoustics, Content and Interaction Features to Find Hot Spots in Meetings},
year = {2020} }
TY - EJOUR
T1 - Combining Acoustics, Content and Interaction Features to Find Hot Spots in Meetings
AU - Dave Makhervaks; William Hinthorn; Dimitrios Dimitriadis; Andreas Stolcke
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5334
ER -
Dave Makhervaks, William Hinthorn, Dimitrios Dimitriadis, Andreas Stolcke. (2020). Combining Acoustics, Content and Interaction Features to Find Hot Spots in Meetings. IEEE SigPort. http://sigport.org/5334
Dave Makhervaks, William Hinthorn, Dimitrios Dimitriadis, Andreas Stolcke, 2020. Combining Acoustics, Content and Interaction Features to Find Hot Spots in Meetings. Available at: http://sigport.org/5334.
Dave Makhervaks, William Hinthorn, Dimitrios Dimitriadis, Andreas Stolcke. (2020). "Combining Acoustics, Content and Interaction Features to Find Hot Spots in Meetings." Web.
1. Dave Makhervaks, William Hinthorn, Dimitrios Dimitriadis, Andreas Stolcke. Combining Acoustics, Content and Interaction Features to Find Hot Spots in Meetings [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5334

WHAT IS BEST FOR SPOKEN LANGUAGE UNDERSTANDING: SMALL BUT TASK-DEPENDANT EMBEDDINGS OR HUGE BUT OUT-OF-DOMAIN EMBEDDINGS?


Word embeddings are shown to be a great asset for several Natural Language and Speech Processing tasks. While they are already evaluated on various NLP tasks, their evaluation on spoken or natural language understanding (SLU) is less studied. The goal of this study is two-fold: firstly, it focuses on semantic evaluation of common word embeddings approaches for SLU task; secondly, it investigates the use of two different data sets to train the embeddings: small and task-dependent corpus or huge and out-of-domain corpus.

Paper Details

Authors:
Sahar Ghannay ; Antoine Neuraz ; Sophie Rosset
Submitted On:
14 May 2020 - 6:43am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Slides_paper_number_ 3443.pdf

(10)

Subscribe

[1] Sahar Ghannay ; Antoine Neuraz ; Sophie Rosset, "WHAT IS BEST FOR SPOKEN LANGUAGE UNDERSTANDING: SMALL BUT TASK-DEPENDANT EMBEDDINGS OR HUGE BUT OUT-OF-DOMAIN EMBEDDINGS?", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5279. Accessed: Jul. 09, 2020.
@article{5279-20,
url = {http://sigport.org/5279},
author = {Sahar Ghannay ; Antoine Neuraz ; Sophie Rosset },
publisher = {IEEE SigPort},
title = {WHAT IS BEST FOR SPOKEN LANGUAGE UNDERSTANDING: SMALL BUT TASK-DEPENDANT EMBEDDINGS OR HUGE BUT OUT-OF-DOMAIN EMBEDDINGS?},
year = {2020} }
TY - EJOUR
T1 - WHAT IS BEST FOR SPOKEN LANGUAGE UNDERSTANDING: SMALL BUT TASK-DEPENDANT EMBEDDINGS OR HUGE BUT OUT-OF-DOMAIN EMBEDDINGS?
AU - Sahar Ghannay ; Antoine Neuraz ; Sophie Rosset
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5279
ER -
Sahar Ghannay ; Antoine Neuraz ; Sophie Rosset. (2020). WHAT IS BEST FOR SPOKEN LANGUAGE UNDERSTANDING: SMALL BUT TASK-DEPENDANT EMBEDDINGS OR HUGE BUT OUT-OF-DOMAIN EMBEDDINGS?. IEEE SigPort. http://sigport.org/5279
Sahar Ghannay ; Antoine Neuraz ; Sophie Rosset, 2020. WHAT IS BEST FOR SPOKEN LANGUAGE UNDERSTANDING: SMALL BUT TASK-DEPENDANT EMBEDDINGS OR HUGE BUT OUT-OF-DOMAIN EMBEDDINGS?. Available at: http://sigport.org/5279.
Sahar Ghannay ; Antoine Neuraz ; Sophie Rosset. (2020). "WHAT IS BEST FOR SPOKEN LANGUAGE UNDERSTANDING: SMALL BUT TASK-DEPENDANT EMBEDDINGS OR HUGE BUT OUT-OF-DOMAIN EMBEDDINGS?." Web.
1. Sahar Ghannay ; Antoine Neuraz ; Sophie Rosset. WHAT IS BEST FOR SPOKEN LANGUAGE UNDERSTANDING: SMALL BUT TASK-DEPENDANT EMBEDDINGS OR HUGE BUT OUT-OF-DOMAIN EMBEDDINGS? [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5279

Multitask Learning with Capsule Networks for Speech-to-Intent Applications


Voice controlled applications can be a great aid to society, especially for physically challenged people. However this requires robustness to all kinds of variations in speech. A spoken language understanding system that learns from interaction with and demonstrations from the user, allows the use of such a system in different settings and for different types of speech, even for deviant or impaired speech, while also allowing the user to choose a phrasing.

Paper Details

Authors:
Jakob Poncelet, Hugo Van hamme
Submitted On:
14 May 2020 - 5:07am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP2020 Presentation Slides

(17)

Subscribe

[1] Jakob Poncelet, Hugo Van hamme, "Multitask Learning with Capsule Networks for Speech-to-Intent Applications", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5275. Accessed: Jul. 09, 2020.
@article{5275-20,
url = {http://sigport.org/5275},
author = {Jakob Poncelet; Hugo Van hamme },
publisher = {IEEE SigPort},
title = {Multitask Learning with Capsule Networks for Speech-to-Intent Applications},
year = {2020} }
TY - EJOUR
T1 - Multitask Learning with Capsule Networks for Speech-to-Intent Applications
AU - Jakob Poncelet; Hugo Van hamme
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5275
ER -
Jakob Poncelet, Hugo Van hamme. (2020). Multitask Learning with Capsule Networks for Speech-to-Intent Applications. IEEE SigPort. http://sigport.org/5275
Jakob Poncelet, Hugo Van hamme, 2020. Multitask Learning with Capsule Networks for Speech-to-Intent Applications. Available at: http://sigport.org/5275.
Jakob Poncelet, Hugo Van hamme. (2020). "Multitask Learning with Capsule Networks for Speech-to-Intent Applications." Web.
1. Jakob Poncelet, Hugo Van hamme. Multitask Learning with Capsule Networks for Speech-to-Intent Applications [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5275

Multimodal One-shot Learning of Speech and Images


Image a robot is shown new concepts visually together with spoken tags, e.g. "milk", "eggs", "butter". After seeing one paired audiovisual example per class, it is shown a new set of unseen instances of these objects, and asked to pick the "milk". Without receiving any hard labels, could it learn to match the new continuous speech input to the correct visual instance? Although unimodal one-shot learning has been studied, where one labelled example in a single modality is given per class, this example motivates multimodal one-shot learning.

Paper Details

Authors:
Ryan Eloff, Herman A. Engelbrecht, Herman Kamper
Submitted On:
10 May 2019 - 6:38pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

icassp2019_poster_multimodal_oneshot

(78)

Keywords

Additional Categories

Subscribe

[1] Ryan Eloff, Herman A. Engelbrecht, Herman Kamper, "Multimodal One-shot Learning of Speech and Images", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4421. Accessed: Jul. 09, 2020.
@article{4421-19,
url = {http://sigport.org/4421},
author = {Ryan Eloff; Herman A. Engelbrecht; Herman Kamper },
publisher = {IEEE SigPort},
title = {Multimodal One-shot Learning of Speech and Images},
year = {2019} }
TY - EJOUR
T1 - Multimodal One-shot Learning of Speech and Images
AU - Ryan Eloff; Herman A. Engelbrecht; Herman Kamper
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4421
ER -
Ryan Eloff, Herman A. Engelbrecht, Herman Kamper. (2019). Multimodal One-shot Learning of Speech and Images. IEEE SigPort. http://sigport.org/4421
Ryan Eloff, Herman A. Engelbrecht, Herman Kamper, 2019. Multimodal One-shot Learning of Speech and Images. Available at: http://sigport.org/4421.
Ryan Eloff, Herman A. Engelbrecht, Herman Kamper. (2019). "Multimodal One-shot Learning of Speech and Images." Web.
1. Ryan Eloff, Herman A. Engelbrecht, Herman Kamper. Multimodal One-shot Learning of Speech and Images [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4421

Context-aware Neural-based Dialog Act Classification On Automatically Generated Transcriptions


This paper presents our latest investigations on dialog act (DA) classification on automatically generated transcriptions. We propose a novel approach that combines convolutional neural networks (CNNs) and conditional random fields (CRFs) for context modeling in DA classification. We explore the impact of transcriptions generated from different automatic speech recognition systems such as hybrid TDNN/HMM and End-to-End systems on the final performance. Experimental results on two benchmark datasets (MRDA and SwDA) show that the combination CNN and CRF improves consistently the accuracy.

Paper Details

Authors:
Daniel Ortega, Chia-Yu Li, Gisela Vallejo, Pavel Denisov, Ngoc Thang Vu
Submitted On:
10 May 2019 - 6:42am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP_2019_Ortega_poster.pdf

(90)

Subscribe

[1] Daniel Ortega, Chia-Yu Li, Gisela Vallejo, Pavel Denisov, Ngoc Thang Vu, "Context-aware Neural-based Dialog Act Classification On Automatically Generated Transcriptions", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4301. Accessed: Jul. 09, 2020.
@article{4301-19,
url = {http://sigport.org/4301},
author = {Daniel Ortega; Chia-Yu Li; Gisela Vallejo; Pavel Denisov; Ngoc Thang Vu },
publisher = {IEEE SigPort},
title = {Context-aware Neural-based Dialog Act Classification On Automatically Generated Transcriptions},
year = {2019} }
TY - EJOUR
T1 - Context-aware Neural-based Dialog Act Classification On Automatically Generated Transcriptions
AU - Daniel Ortega; Chia-Yu Li; Gisela Vallejo; Pavel Denisov; Ngoc Thang Vu
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4301
ER -
Daniel Ortega, Chia-Yu Li, Gisela Vallejo, Pavel Denisov, Ngoc Thang Vu. (2019). Context-aware Neural-based Dialog Act Classification On Automatically Generated Transcriptions. IEEE SigPort. http://sigport.org/4301
Daniel Ortega, Chia-Yu Li, Gisela Vallejo, Pavel Denisov, Ngoc Thang Vu, 2019. Context-aware Neural-based Dialog Act Classification On Automatically Generated Transcriptions. Available at: http://sigport.org/4301.
Daniel Ortega, Chia-Yu Li, Gisela Vallejo, Pavel Denisov, Ngoc Thang Vu. (2019). "Context-aware Neural-based Dialog Act Classification On Automatically Generated Transcriptions." Web.
1. Daniel Ortega, Chia-Yu Li, Gisela Vallejo, Pavel Denisov, Ngoc Thang Vu. Context-aware Neural-based Dialog Act Classification On Automatically Generated Transcriptions [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4301

QUESTION ANSWERING FOR SPOKEN LECTURE PROCESSING


This paper presents a question answering (QA) system developed for spoken lecture processing. The questions are presented to the system in written form and the answers are returned from lecture videos. In contrast to the widely studied reading comprehension style QA – the machine understands a passage of text and answers the questions related to that passage – our task introduces the challenge of searching the answers on longer text where the text corresponds to the erroneous transcripts of the lecture videos.

Paper Details

Authors:
Merve Unlu, Ebru Arisoy, Murat Saraclar
Submitted On:
9 May 2019 - 5:35pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP2019merve_poster.pdf

(103)

Subscribe

[1] Merve Unlu, Ebru Arisoy, Murat Saraclar, "QUESTION ANSWERING FOR SPOKEN LECTURE PROCESSING", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4243. Accessed: Jul. 09, 2020.
@article{4243-19,
url = {http://sigport.org/4243},
author = {Merve Unlu; Ebru Arisoy; Murat Saraclar },
publisher = {IEEE SigPort},
title = {QUESTION ANSWERING FOR SPOKEN LECTURE PROCESSING},
year = {2019} }
TY - EJOUR
T1 - QUESTION ANSWERING FOR SPOKEN LECTURE PROCESSING
AU - Merve Unlu; Ebru Arisoy; Murat Saraclar
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4243
ER -
Merve Unlu, Ebru Arisoy, Murat Saraclar. (2019). QUESTION ANSWERING FOR SPOKEN LECTURE PROCESSING. IEEE SigPort. http://sigport.org/4243
Merve Unlu, Ebru Arisoy, Murat Saraclar, 2019. QUESTION ANSWERING FOR SPOKEN LECTURE PROCESSING. Available at: http://sigport.org/4243.
Merve Unlu, Ebru Arisoy, Murat Saraclar. (2019). "QUESTION ANSWERING FOR SPOKEN LECTURE PROCESSING." Web.
1. Merve Unlu, Ebru Arisoy, Murat Saraclar. QUESTION ANSWERING FOR SPOKEN LECTURE PROCESSING [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4243

QUESTION ANSWERING FOR SPOKEN LECTURE PROCESSING


This paper presents a question answering (QA) system developed for spoken lecture processing. The questions are presented to the system in written form and the answers are returned from lecture videos. In contrast to the widely studied reading comprehension style QA – the machine understands a passage of text and answers the questions related to that passage – our task introduces the challenge of searching the answers on longer text where the text corresponds to the erroneous transcripts of the lecture videos.

Paper Details

Authors:
Merve Unlu, Ebru Arisoy, Murat Saraclar
Submitted On:
9 May 2019 - 5:35pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP2019merve_poster.pdf

(85)

Subscribe

[1] Merve Unlu, Ebru Arisoy, Murat Saraclar, "QUESTION ANSWERING FOR SPOKEN LECTURE PROCESSING", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4242. Accessed: Jul. 09, 2020.
@article{4242-19,
url = {http://sigport.org/4242},
author = {Merve Unlu; Ebru Arisoy; Murat Saraclar },
publisher = {IEEE SigPort},
title = {QUESTION ANSWERING FOR SPOKEN LECTURE PROCESSING},
year = {2019} }
TY - EJOUR
T1 - QUESTION ANSWERING FOR SPOKEN LECTURE PROCESSING
AU - Merve Unlu; Ebru Arisoy; Murat Saraclar
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4242
ER -
Merve Unlu, Ebru Arisoy, Murat Saraclar. (2019). QUESTION ANSWERING FOR SPOKEN LECTURE PROCESSING. IEEE SigPort. http://sigport.org/4242
Merve Unlu, Ebru Arisoy, Murat Saraclar, 2019. QUESTION ANSWERING FOR SPOKEN LECTURE PROCESSING. Available at: http://sigport.org/4242.
Merve Unlu, Ebru Arisoy, Murat Saraclar. (2019). "QUESTION ANSWERING FOR SPOKEN LECTURE PROCESSING." Web.
1. Merve Unlu, Ebru Arisoy, Murat Saraclar. QUESTION ANSWERING FOR SPOKEN LECTURE PROCESSING [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4242

REVISITING HIDDEN MARKOV MODELS FOR SPEECH EMOTION RECOGNITION

Paper Details

Authors:
Dehua Tao, Guangyan Zhang, P. C. Ching and Tan Lee
Submitted On:
9 May 2019 - 2:14am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

ICASSP2019_Poster_symao.pdf

(81)

Subscribe

[1] Dehua Tao, Guangyan Zhang, P. C. Ching and Tan Lee, "REVISITING HIDDEN MARKOV MODELS FOR SPEECH EMOTION RECOGNITION", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4152. Accessed: Jul. 09, 2020.
@article{4152-19,
url = {http://sigport.org/4152},
author = {Dehua Tao; Guangyan Zhang; P. C. Ching and Tan Lee },
publisher = {IEEE SigPort},
title = {REVISITING HIDDEN MARKOV MODELS FOR SPEECH EMOTION RECOGNITION},
year = {2019} }
TY - EJOUR
T1 - REVISITING HIDDEN MARKOV MODELS FOR SPEECH EMOTION RECOGNITION
AU - Dehua Tao; Guangyan Zhang; P. C. Ching and Tan Lee
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4152
ER -
Dehua Tao, Guangyan Zhang, P. C. Ching and Tan Lee. (2019). REVISITING HIDDEN MARKOV MODELS FOR SPEECH EMOTION RECOGNITION. IEEE SigPort. http://sigport.org/4152
Dehua Tao, Guangyan Zhang, P. C. Ching and Tan Lee, 2019. REVISITING HIDDEN MARKOV MODELS FOR SPEECH EMOTION RECOGNITION. Available at: http://sigport.org/4152.
Dehua Tao, Guangyan Zhang, P. C. Ching and Tan Lee. (2019). "REVISITING HIDDEN MARKOV MODELS FOR SPEECH EMOTION RECOGNITION." Web.
1. Dehua Tao, Guangyan Zhang, P. C. Ching and Tan Lee. REVISITING HIDDEN MARKOV MODELS FOR SPEECH EMOTION RECOGNITION [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4152

USING DEEP-Q NETWORK TO SELECT CANDIDATES FROM N-BEST SPEECH RECOGNITION HYPOTHESES FOR ENHANCING DIALOGUE STATE TRACKING

Paper Details

Authors:
Richard Tzong-Han Tsai, Chia-Hao Chen, Chun-Kai Wu, Yu-Cheng Hsiao, Hung-Yi Lee
Submitted On:
11 April 2019 - 4:05am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

ICASSP 2019#2338.pdf

(128)

Subscribe

[1] Richard Tzong-Han Tsai, Chia-Hao Chen, Chun-Kai Wu, Yu-Cheng Hsiao, Hung-Yi Lee, "USING DEEP-Q NETWORK TO SELECT CANDIDATES FROM N-BEST SPEECH RECOGNITION HYPOTHESES FOR ENHANCING DIALOGUE STATE TRACKING", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/3888. Accessed: Jul. 09, 2020.
@article{3888-19,
url = {http://sigport.org/3888},
author = {Richard Tzong-Han Tsai; Chia-Hao Chen; Chun-Kai Wu; Yu-Cheng Hsiao; Hung-Yi Lee },
publisher = {IEEE SigPort},
title = {USING DEEP-Q NETWORK TO SELECT CANDIDATES FROM N-BEST SPEECH RECOGNITION HYPOTHESES FOR ENHANCING DIALOGUE STATE TRACKING},
year = {2019} }
TY - EJOUR
T1 - USING DEEP-Q NETWORK TO SELECT CANDIDATES FROM N-BEST SPEECH RECOGNITION HYPOTHESES FOR ENHANCING DIALOGUE STATE TRACKING
AU - Richard Tzong-Han Tsai; Chia-Hao Chen; Chun-Kai Wu; Yu-Cheng Hsiao; Hung-Yi Lee
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/3888
ER -
Richard Tzong-Han Tsai, Chia-Hao Chen, Chun-Kai Wu, Yu-Cheng Hsiao, Hung-Yi Lee. (2019). USING DEEP-Q NETWORK TO SELECT CANDIDATES FROM N-BEST SPEECH RECOGNITION HYPOTHESES FOR ENHANCING DIALOGUE STATE TRACKING. IEEE SigPort. http://sigport.org/3888
Richard Tzong-Han Tsai, Chia-Hao Chen, Chun-Kai Wu, Yu-Cheng Hsiao, Hung-Yi Lee, 2019. USING DEEP-Q NETWORK TO SELECT CANDIDATES FROM N-BEST SPEECH RECOGNITION HYPOTHESES FOR ENHANCING DIALOGUE STATE TRACKING. Available at: http://sigport.org/3888.
Richard Tzong-Han Tsai, Chia-Hao Chen, Chun-Kai Wu, Yu-Cheng Hsiao, Hung-Yi Lee. (2019). "USING DEEP-Q NETWORK TO SELECT CANDIDATES FROM N-BEST SPEECH RECOGNITION HYPOTHESES FOR ENHANCING DIALOGUE STATE TRACKING." Web.
1. Richard Tzong-Han Tsai, Chia-Hao Chen, Chun-Kai Wu, Yu-Cheng Hsiao, Hung-Yi Lee. USING DEEP-Q NETWORK TO SELECT CANDIDATES FROM N-BEST SPEECH RECOGNITION HYPOTHESES FOR ENHANCING DIALOGUE STATE TRACKING [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/3888

Pages