1 |
An Overview of Indian Spoken Language Recognition from Machine Learning Perspective
|
|
|
|
In: ISSN: 2375-4699 ; EISSN: 2375-4702 ; ACM Transactions on Asian and Low-Resource Language Information Processing ; https://hal.inria.fr/hal-03616853 ; ACM Transactions on Asian and Low-Resource Language Information Processing, ACM, In press, ⟨10.1145/3523179⟩ (2022)
|
|
BASE
|
|
Show details
|
|
2 |
BERT-based Semantic Model for Rescoring N-best Speech Recognition List
|
|
|
|
In: INTERSPEECH 2021 ; https://hal.archives-ouvertes.fr/hal-03248881 ; INTERSPEECH 2021, Aug 2021, Brno, Czech Republic ; https://www.interspeech2021.org/ (2021)
|
|
BASE
|
|
Show details
|
|
3 |
Introduction of semantic model to help speech recognition
|
|
|
|
In: TSD 2020 - Twenty-third International Conference on Text, Speech and Dialogue ; https://hal.archives-ouvertes.fr/hal-02862245 ; TSD 2020 - Twenty-third International Conference on Text, Speech and Dialogue, Sep 2020, Brno, Czech Republic (2020)
|
|
BASE
|
|
Show details
|
|
4 |
RNN Language Model Estimation for Out-of-Vocabulary Words
|
|
|
|
In: Lecture Notes in Artificial Intelligence ; https://hal.archives-ouvertes.fr/hal-03054936 ; Lecture Notes in Artificial Intelligence, Springer, In press, 12598, ⟨10.1007/978-3-030-66527-2_15⟩ (2020)
|
|
BASE
|
|
Show details
|
|
5 |
Acoustic impacts of geometric approximation at the level of velum and epiglottis on French vowels
|
|
|
|
In: ICPhS 2019 - International Congress of Phonetic Sciences ; https://hal.inria.fr/hal-02180566 ; ICPhS 2019 - International Congress of Phonetic Sciences, Aug 2019, Melbourne, Australia (2019)
|
|
BASE
|
|
Show details
|
|
6 |
An integrative platform to capture the orchestration of gesture and speech
|
|
|
|
In: GeSpIn 2019 - Gesture and Speech in Interaction ; https://hal.inria.fr/hal-02278345 ; GeSpIn 2019 - Gesture and Speech in Interaction, Sep 2019, Paderborn, Germany (2019)
|
|
BASE
|
|
Show details
|
|
7 |
Effect of head posture on phonation of French vowels
|
|
|
|
In: ICPhS 2019 - Proceedings of International Congress of Phonetic Sciences ; https://hal.inria.fr/hal-02180486 ; ICPhS 2019 - Proceedings of International Congress of Phonetic Sciences, Aug 2019, Melbourne, Australia (2019)
|
|
BASE
|
|
Show details
|
|
8 |
Phoneme-to-Articulatory mapping using bidirectional gated RNN
|
|
|
|
In: Interspeech 2018 - 19th Annual Conference of the International Speech Communication Association ; https://hal.inria.fr/hal-01862587 ; Interspeech 2018 - 19th Annual Conference of the International Speech Communication Association, Sep 2018, Hyderabad, India (2018)
|
|
BASE
|
|
Show details
|
|
9 |
A French-Spanish Multimodal Speech Communication Corpus Incorporating Acoustic Data, Facial, Hands and Arms Gestures Information
|
|
|
|
In: Interspeech 2018 - 19th Annual Conference of the International Speech Communication Association ; https://hal.inria.fr/hal-01862585 ; Interspeech 2018 - 19th Annual Conference of the International Speech Communication Association, Sep 2018, Hyderabad, India (2018)
|
|
BASE
|
|
Show details
|
|
10 |
Topic segmentation in ASR transcripts using bidirectional rnns for change detection
|
|
|
|
In: ASRU 2017 - IEEE Automatic Speech Recognition and Understanding Workshop ; https://hal.archives-ouvertes.fr/hal-01599682 ; ASRU 2017 - IEEE Automatic Speech Recognition and Understanding Workshop, Dec 2017, Okinawa, Japan (2017)
|
|
Abstract:
International audience ; Topic segmentation methods are mostly based on the idea of lexical cohesion, in which lexical distributions are analysed across the document and segment boundaries are marked in areas of low cohesion. We propose a novel approach for topic segmentation in speech recognition transcripts by measuring lexical cohesion using bidirectional Recurrent Neural Networks (RNN). The bidirectional RNNs capture context in the past and the following set of words. The past and following contexts are compared to perform topic change detection. In contrast to existing works based on sequence and discrim-inative models for topic segmentation, our approach does not use a segmented corpus nor (pseudo) topic labels for training. Our model is trained using news articles obtained from the internet. Evaluation on ASR transcripts of French TV broadcast news programs demonstrates the effectiveness of our proposed approach.
|
|
Keyword:
[INFO.INFO-HC]Computer Science [cs]/Human-Computer Interaction [cs.HC]; recurrent neural networks; topic segmentation
|
|
URL: https://hal.archives-ouvertes.fr/hal-01599682/file/draft_20Sep2017.pdf https://hal.archives-ouvertes.fr/hal-01599682 https://hal.archives-ouvertes.fr/hal-01599682/document
|
|
BASE
|
|
Hide details
|
|
11 |
Out-of-Vocabulary Word Probability Estimation using RNN Language Model
|
|
|
|
In: 8th Language & Technology Conference ; https://hal.archives-ouvertes.fr/hal-01623784 ; 8th Language & Technology Conference, Nov 2017, Poznan, Poland (2017)
|
|
BASE
|
|
Show details
|
|
12 |
Articulatory model of the epiglottis
|
|
|
|
In: The 11th International Seminar on Speech Production ; https://hal.inria.fr/hal-01643227 ; The 11th International Seminar on Speech Production, Oct 2017, Tianjin, China (2017)
|
|
BASE
|
|
Show details
|
|
13 |
How Diachronic Text Corpora Affect Context based Retrieval of OOV Proper Names for Audio News
|
|
|
|
In: LREC 2016 ; https://hal.archives-ouvertes.fr/hal-01331714 ; LREC 2016, May 2016, Portoroz, Slovenia (2016)
|
|
BASE
|
|
Show details
|
|
14 |
Improved Neural Bag-of-Words Model to Retrieve Out-of-Vocabulary Words in Speech Recognition
|
|
|
|
In: INTERSPEECH 2016 ; https://hal.archives-ouvertes.fr/hal-01384488 ; INTERSPEECH 2016, Sep 2016, San Francisco, United States. ⟨10.21437/Interspeech.2016-1219⟩ (2016)
|
|
BASE
|
|
Show details
|
|
15 |
Dynamic adjustment of language models for automatic speech recognition using word similarity
|
|
|
|
In: IEEE Workshop on Spoken Language Technology (SLT 2016) ; https://hal.archives-ouvertes.fr/hal-01384365 ; IEEE Workshop on Spoken Language Technology (SLT 2016), Dec 2016, San Diego, CA, United States ; http://www.slt2016.org/ (2016)
|
|
BASE
|
|
Show details
|
|
16 |
Document Level Semantic Context for Retrieving OOV Proper Names
|
|
|
|
In: 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) ; https://hal.archives-ouvertes.fr/hal-01331716 ; 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) , Mar 2016, Shanghai, China. pp.6050-6054, ⟨10.1109/ICASSP.2016.7472839⟩ (2016)
|
|
BASE
|
|
Show details
|
|
17 |
OOV Proper Name Retrieval using Topic and Lexical Context Model
|
|
|
|
In: IEEE International Conference on Acoustics, Speech and Signal Processing ; https://hal.archives-ouvertes.fr/hal-01184963 ; IEEE International Conference on Acoustics, Speech and Signal Processing, 2015, Brisbane, Australia (2015)
|
|
BASE
|
|
Show details
|
|
18 |
Continuous Word Representation using Neural Networks for Proper Name Retrieval from Diachronic Documents
|
|
|
|
In: Interspeech 2015 ; https://hal.archives-ouvertes.fr/hal-01184951 ; Interspeech 2015, Sep 2015, Dresden, Germany (2015)
|
|
BASE
|
|
Show details
|
|
19 |
Neural Networks Revisited for Proper Name Retrieval from Diachronic Documents
|
|
|
|
In: proceedings of LTC2015 ; LTC Language & Technology Conference ; https://hal.archives-ouvertes.fr/hal-01240480 ; LTC Language & Technology Conference, Nov 2015, Poznan, Poland. pp.120-124 (2015)
|
|
BASE
|
|
Show details
|
|
20 |
Study of Entity-Topic Models for OOV Proper Name Retrieval
|
|
|
|
In: Interspeech 2015 ; https://hal.archives-ouvertes.fr/hal-01184955 ; Interspeech 2015, Sep 2015, Dresden, Germany (2015)
|
|
BASE
|
|
Show details
|
|
|
|