1 |
Re-synchronization using the Hand Preceding Model for Multi-modal Fusion in Automatic Continuous Cued Speech Recognition
|
|
|
|
In: ISSN: 1520-9210 ; IEEE Transactions on Multimedia ; https://hal.archives-ouvertes.fr/hal-02433830 ; IEEE Transactions on Multimedia, Institute of Electrical and Electronics Engineers, 2021, 23, pp.292-305. ⟨10.1109/TMM.2020.2976493⟩ (2021)
|
|
BASE
|
|
Show details
|
|
2 |
Att-HACK: An Expressive Speech Database with Social Attitudes
|
|
|
|
In: Speech Prosody ; https://hal.archives-ouvertes.fr/hal-02508362 ; Speech Prosody, May 2020, Tokyo, Japan (2020)
|
|
BASE
|
|
Show details
|
|
3 |
SLOGD: Speaker Location Guided Deflation Approach to Speech Separation
|
|
|
|
In: ICASSP 2020 - 45th International Conference on Acoustics, Speech, and Signal Processing ; https://hal.inria.fr/hal-02355613 ; ICASSP 2020 - 45th International Conference on Acoustics, Speech, and Signal Processing, May 2020, Barcelona, Spain (2020)
|
|
BASE
|
|
Show details
|
|
4 |
Speaker detection in the wild: Lessons learned from JSALT 2019
|
|
|
|
In: Odyssey 2020 The Speaker and Language Recognition Workshop ; https://hal.archives-ouvertes.fr/hal-02417632 ; Odyssey 2020 The Speaker and Language Recognition Workshop, Nov 2020, Tokyo, Japan (2020)
|
|
BASE
|
|
Show details
|
|
5 |
Adapting a FrameNet Semantic Parser for Spoken Language Understanding Using Adversarial Learning
|
|
|
|
In: Interspeech 2019 ; https://hal.archives-ouvertes.fr/hal-02298417 ; Interspeech 2019, Sep 2019, Graz, Austria. pp.799-803, ⟨10.21437/Interspeech.2019-2732⟩ (2019)
|
|
BASE
|
|
Show details
|
|
6 |
Usage-Based Learning in Human Interaction with an Adaptive Virtual Assistant
|
|
|
|
In: ISSN: 2379-8920 ; EISSN: 2379-8939 ; IEEE Transactions on Cognitive and Developmental Systems ; https://hal.archives-ouvertes.fr/hal-02414815 ; IEEE Transactions on Cognitive and Developmental Systems, Institute of Electrical and Electronics Engineers, Inc, 2019 (2019)
|
|
BASE
|
|
Show details
|
|
7 |
A Perceptual Study of CV Syllables in both Spoken and Whistled Speech: a Tashlhiyt Berber Perspective
|
|
|
|
In: Interspeech 2019 - 20th Annual Conference of the International Speech Communication Association ; https://hal.archives-ouvertes.fr/hal-02371794 ; Interspeech 2019 - 20th Annual Conference of the International Speech Communication Association, Sep 2019, Graz, Austria. ⟨10.21437/Interspeech.2019-2251⟩ (2019)
|
|
BASE
|
|
Show details
|
|
8 |
Sequence Covering for Efficient Host-Based Intrusion Detection
|
|
|
|
In: ISSN: 1556-6013 ; IEEE Transactions on Information Forensics and Security ; https://hal.archives-ouvertes.fr/hal-01653650 ; IEEE Transactions on Information Forensics and Security, Institute of Electrical and Electronics Engineers, 2019, 14 (4), pp.994-1006. ⟨10.1109/TIFS.2018.2868614⟩ ; https://ieeexplore.ieee.org/document/8454473 (2019)
|
|
BASE
|
|
Show details
|
|
9 |
A Multimodal Real-Time MRI Articulatory Corpus of French for Speech Research
|
|
|
|
In: INTERSPEECH 2019 - 20th Annual Conference of the International Speech Communication Association ; https://hal.inria.fr/hal-02167756 ; INTERSPEECH 2019 - 20th Annual Conference of the International Speech Communication Association, Sep 2019, Graz, Austria (2019)
|
|
BASE
|
|
Show details
|
|
10 |
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
|
|
11 |
Perception of prosodic boundaries by naïve listeners in three different types of subordinate syntactic constructions
|
|
|
|
In: 9th International Conference on Speech Prosody 2018 ; https://hal.archives-ouvertes.fr/hal-02117498 ; 9th International Conference on Speech Prosody 2018, Jun 2018, Poznań, Poland. pp.104-108, ⟨10.21437/SpeechProsody.2018-21⟩ (2018)
|
|
BASE
|
|
Show details
|
|
12 |
Sampling strategies in Siamese Networks for unsupervised speech representation learning
|
|
|
|
In: Interspeech 2018 ; https://hal.archives-ouvertes.fr/hal-01888725 ; Interspeech 2018, Sep 2018, Hyderabad, India (2018)
|
|
BASE
|
|
Show details
|
|
13 |
End-to-End Speech Recognition From the Raw Waveform
|
|
|
|
In: Interspeech 2018 ; https://hal.archives-ouvertes.fr/hal-01888739 ; Interspeech 2018, Sep 2018, Hyderabad, India. ⟨10.21437/Interspeech.2018-2414⟩ (2018)
|
|
BASE
|
|
Show details
|
|
14 |
Studying Vowel Variation in French-Algerian Arabic Code-switched Speech
|
|
|
|
In: Interspeech 2018 ; https://halshs.archives-ouvertes.fr/halshs-02130906 ; Interspeech 2018, Sep 2018, Hyderabad, India. pp.2753-2757, ⟨10.21437/Interspeech.2018-2381⟩ (2018)
|
|
BASE
|
|
Show details
|
|
15 |
Impact of fluency and segmental categorization in L2: the case of French final fricatives uttered by German speakers
|
|
|
|
In: Speech Prosody 2018 ; https://hal.inria.fr/hal-01926657 ; Speech Prosody 2018, Jun 2018, Poznan, Poland. ⟨10.21437/speechprosody.2018-189⟩ (2018)
|
|
BASE
|
|
Show details
|
|
16 |
A Methodology for the Automatic Extraction and Generation of Non-Verbal Signals Sequences Conveying Interpersonal Attitudes
|
|
|
|
In: ISSN: 1949-3045 ; IEEE Transactions on Affective Computing ; https://hal.archives-ouvertes.fr/hal-01793271 ; IEEE Transactions on Affective Computing, Institute of Electrical and Electronics Engineers, 2017, XX, pp.1 - 1. ⟨10.1109/TAFFC.2017.2753777⟩ (2017)
|
|
BASE
|
|
Show details
|
|
17 |
Automatic Prediction of Speech Evaluation Metrics for Dysarthric Speech
|
|
|
|
In: Interspeech ; https://hal.archives-ouvertes.fr/hal-01771613 ; Interspeech, Aug 2017, Stockholm, Sweden (2017)
|
|
BASE
|
|
Show details
|
|
18 |
A Speaker Adaptive DNN Training Approach for Speaker-Independent Acoustic Inversion
|
|
|
|
In: Interspeech 2017 ; https://hal.archives-ouvertes.fr/hal-02166128 ; Interspeech 2017, Aug 2017, Stockholm, Sweden. pp.984-988, ⟨10.21437/Interspeech.2017-804⟩ (2017)
|
|
Abstract:
International audience ; We address the speaker-independent acoustic inversion (AI) problem, also referred to as acoustic-to-articulatory mapping. The scarce availability of multi-speaker articulatory data makes it difficult to learn a mapping which generalizes from a limited number of training speakers and reliably reconstructs the artic-ulatory movements of unseen speakers. In this paper, we propose a Multi-task Learning (MTL)-based approach that explicitly separates the modeling of each training speaker AI peculiarities from the modeling of AI characteristics that are shared by all speakers. Our approach stems from the well known Reg-ularized MTL approach and extends it to feed-forward deep neural networks (DNNs). Given multiple training speakers, we learn for each an acoustic-to-articulatory mapping represented by a DNN. Then, through an iterative procedure, we search for a canonical speaker-independent DNN that is "sim-ilar" to all speaker-dependent DNNs. The degree of similarity is controlled by a regularization parameter. We report experiments on the University of Wisconsin X-ray Microbeam Database under different training/testing experimental settings. The results obtained indicate that our MTL-trained canonical DNN largely outperforms a standardly trained (i.e., single task learning-based) speaker independent DNN.
|
|
Keyword:
[SCCO.LING]Cognitive science/Linguistics; [SCCO]Cognitive science; acoustic-to-articulatory map- ping; Index Terms: acoustic inversion; multi-task learning; XRMB
|
|
URL: https://doi.org/10.21437/Interspeech.2017-804 https://hal.archives-ouvertes.fr/hal-02166128 https://hal.archives-ouvertes.fr/hal-02166128/file/0804.pdf https://hal.archives-ouvertes.fr/hal-02166128/document
|
|
BASE
|
|
Hide details
|
|
19 |
How Does the Absence of Shared Knowledge Between Interlocutors Affect the Production of French Prosodic Forms?
|
|
|
|
In: Interspeech 2017 ; https://hal.archives-ouvertes.fr/hal-01727288 ; Interspeech 2017, Aug 2017, Stockholm, Sweden. ⟨10.21437/Interspeech.2017-1430⟩ (2017)
|
|
BASE
|
|
Show details
|
|
20 |
“My Excellent College Entrance Examination Achievement” — Noun Phrase Use of Chinese EFL Students’ Writing
|
|
|
|
In: English Publications (2017)
|
|
BASE
|
|
Show details
|
|
|
|