| 1 |
Multi-Lingual Dialogue Act Recognition with Deep Learning Methods
|
|
|
|
In: Interspeech 2019 ; https://hal.archives-ouvertes.fr/hal-02319818 ; Interspeech 2019, Sep 2019, Graz, Austria. ⟨10.21437/Interspeech.2019-1691⟩ (2019)
|
|
BASE
|
|
Show details
|
|
|
| 2 |
Multi-lingual Dialogue Act Recognition with Deep Learning Methods ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 3 |
On the Effects of Using word2vec Representations in Neural Networks for Dialogue Act Recognition
|
|
|
|
In: ISSN: 0885-2308 ; EISSN: 1095-8363 ; Computer Speech and Language ; https://hal.archives-ouvertes.fr/hal-01581410 ; Computer Speech and Language, Elsevier, 2018, 47, pp.175 - 193. ⟨10.1016/j.csl.2017.07.009⟩ (2018)
|
|
BASE
|
|
Show details
|
|
|
| 5 |
Deep Neural Networks for Czech Multi-label Document Classification ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 6 |
Investigation of word senses over time using linguistic corpora
|
|
|
|
BASE
|
|
Show details
|
|
|
| 7 |
Dialogue act recognition approaches
|
|
|
|
In: ISSN: 1335-9150 ; Computing and Informatics ; https://hal.inria.fr/inria-00431396 ; Computing and Informatics, Slovak University Press, Bratislava, 2010, 29 (2), pp.227--250 (2010)
|
|
BASE
|
|
Show details
|
|
|
| 8 |
Lexical Structure for Dialogue Act Recognition
|
|
|
|
In: ISSN: 1796-2048 ; Journal of Multimedia ; https://hal.inria.fr/inria-00184475 ; Journal of Multimedia, Academy Publisher, 2007, 2 (3), pp.1-8 (2007)
|
|
BASE
|
|
Show details
|
|
|
| 9 |
Automatic Recognition of Dialogue Acts ; Reconnaissance automatique des actes de dialogue
|
|
|
|
In: https://tel.archives-ouvertes.fr/tel-01748248 ; Modeling and Simulation. Université Henri Poincaré - Nancy 1, 2007. English. ⟨NNT : 2007NAN10114⟩ (2007)
|
|
BASE
|
|
Show details
|
|
|
| 10 |
Sentence Modality Recognition In French Based On Prosody ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 11 |
Sentence Modality Recognition In French Based On Prosody ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 12 |
Automatic Recognition of Dialogue Acts ; Reconnaissance automatique des actes de dialogue
|
|
|
|
BASE
|
|
Show details
|
|
|
| 13 |
Automatic dialog acts recognition based on sentence structure
|
|
|
|
In: IEEE International Conference on Acoustics, Speech, and Signal Processing - ICASSP/2006 ; https://hal.archives-ouvertes.fr/hal-00078245 ; 2006, pp.61-64 (2006)
|
|
BASE
|
|
Show details
|
|
|
| 14 |
Automatic Dialog Acts Recognition based on Words Clusters
|
|
|
|
In: 9th Western Pacific Acoustics Conference - WESPAC IX 2006 ; https://hal.archives-ouvertes.fr/hal-00086310 ; 2006, 6 p (2006)
|
|
BASE
|
|
Show details
|
|
|
| 15 |
Sentence structure for dialog act recognition in Czech
|
|
|
|
In: 2nd IEEE International Conference on Information et Communication Technologies: from Theory to Applications - ICTTA´06 ; https://hal.archives-ouvertes.fr/hal-00078247 ; 2006 (2006)
|
|
BASE
|
|
Show details
|
|
|
| 16 |
Combination of classifiers for automatic recognition of dialog acts
|
|
|
|
In: Proceedings of the 9th European Conference on Speech Communication and Technology - Interspeech - Eurospeech 2005 - Lisbon, Portugal ; https://hal.archives-ouvertes.fr/hal-00013940 ; 2005, pp.825-828 (2005)
|
|
Abstract:
This paper deals with automatic dialog acts (DAs) recognition in Czech. The dialog acts are sentence-level labels that represent different states of a dialogue, depending on the application. Our work focuses on two applications: a multimodal reservation system and an animated talking head for hearing-impaired people. In that context, we consider the following DAs: statements, orders, yes/no questions and other questions. We propose to use both lexical and prosodic information for DAs recognition. The main goal of this paper is to compare different methods to combine the results of both classifiers. On a Czech corpus simulating a reservation of train tickets, the lexical information only gives about 92 % of classification accuracy, while prosody gives only about 45 % of accuracy. When both classifiers are combined with a multilayer perceptron, the lowest (lexical) word error rate further decreases by 26 %. We show that this improvement is close to the optimal one, given the correlation of the lexical and prosodic features. The other combination schemes do not outperform the lexical-only results.
|
|
Keyword:
[INFO.INFO-HC]Computer Science [cs]/Human-Computer Interaction [cs.HC]
|
|
URL: https://hal.archives-ouvertes.fr/hal-00013940
|
|
BASE
|
|
Hide details
|
|
|
| 17 |
Analysis of Importance of the prosodic Features for Automatic Sentence Modality Recognition in French in real Conditions
|
|
|
|
In: WSEAS International Conference on Electronics, Control and Signal Processing - ICECS'04 ; https://hal.inria.fr/inria-00100102 ; WSEAS International Conference on Electronics, Control and Signal Processing - ICECS'04, Nov 2004, Crete, Greece, pp.1820-1824 (2004)
|
|
BASE
|
|
Show details
|
|
|
|
|
