Zobrazeno 1 - 10
of 107
pro vyhledávání: '"Georges Linarès"'
Publikováno v:
EURASIP Journal on Audio, Speech, and Music Processing, Vol 2010 (2010)
Spoken utterance retrieval was largely studied in the last decades, with the purpose of indexing large audio databases or of detecting keywords in continuous speech streams. While the indexing of closed corpora can be performed via a batch process, o
Externí odkaz:
https://doaj.org/article/a8f21253182c4ac88471e7199e30dcf7
Publikováno v:
EURASIP Journal on Audio, Speech, and Music Processing, Vol 2009 (2009)
Speech recognition applications are known to require a significant amount of resources. However, embedded speech recognition only authorizes few KB of memory, few MIPS, and small amount of training data. In order to fit the resource constraints of em
Externí odkaz:
https://doaj.org/article/3dcb7b2dfa59413ca547718d48c622de
Publikováno v:
IEEE/ACM Transactions on Audio, Speech and Language Processing
IEEE/ACM Transactions on Audio, Speech and Language Processing, Institute of Electrical and Electronics Engineers, 2020, 28, pp.198-210. ⟨10.1109/TASLP.2019.2950596⟩
IEEE/ACM Transactions on Audio, Speech and Language Processing, Institute of Electrical and Electronics Engineers, 2020, 28, pp.198-210. ⟨10.1109/TASLP.2019.2950596⟩
International audience; Machine learning (ML) and deep learning with deep neural networks (DNN), have drastically improved the performances of modern systems on numerous spoken language understanding (SLU) related tasks. Since most of current researc
Publikováno v:
Artificial Intelligence Review. 53:2957-2982
Quaternion neural networks have recently received an increasing interest due to noticeable improvements over real-valued neural networks on real world tasks such as image, speech and signal processing. The extension of quaternion numbers to neural ar
Publikováno v:
SN Computer Science
SN Computer Science, Springer, 2021, 2, pp.37. ⟨10.1007/s42979-020-00413-7⟩
SN Computer Science, Springer, 2021, 2, pp.37. ⟨10.1007/s42979-020-00413-7⟩
International audience; Abusive behaviors are common on online social networks. The increasing frequency of antisocial behaviors forces the hosts of online platforms to find new solutions to address this problem. Automating the moderation process has
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b1e7f1c83d38f6cb4358333bd028a487
Publikováno v:
ICASSP
ICASSP, May 2020, Barcelone, Spain
ICASSP, May 2020, Barcelone, Spain
International audience; Modern end-to-end (E2E) Automatic Speech Recognition (ASR) systems rely on Deep Neural Networks (DNN) that are mostly trained on handcrafted and pre-computed acoustic features such as Mel-filter-banks or Mel-frequency cepstral
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8e957f6a18292a6115cc4a37e79d0411
https://hal.archives-ouvertes.fr/hal-02484600
https://hal.archives-ouvertes.fr/hal-02484600
Publikováno v:
IEEE/ACM Transactions on Audio, Speech and Language Processing
IEEE/ACM Transactions on Audio, Speech and Language Processing, Institute of Electrical and Electronics Engineers, 2017, 25 (9), pp.1809-1820. ⟨10.1109/TASLP.2017.2718843⟩
IEEE/ACM Transactions on Audio, Speech and Language Processing, Institute of Electrical and Electronics Engineers, 2017, 25 (9), pp.1809-1820. ⟨10.1109/TASLP.2017.2718843⟩
Automatic transcription of spoken documents is affected by automatic transcription errors that are especially frequent when speech is acquired in severe noisy conditions. Automatic speech recognition errors induce errors in the linguistic features us
Publikováno v:
INTERSPEECH
INTERSPEECH 2019
INTERSPEECH 2019, Sep 2019, Gratz, Austria
INTERSPEECH 2019
INTERSPEECH 2019, Sep 2019, Gratz, Austria
Deep learning is at the core of recent spoken language understanding (SLU) related tasks. More precisely, deep neural networks (DNNs) drastically increased the performances of SLU systems, and numerous architectures have been proposed. In the real-li
Publikováno v:
INTERSPEECH 2019
INTERSPEECH 2019, Jun 2019, Graz, Austria
INTERSPEECH
INTERSPEECH 2019, Jun 2019, Graz, Austria
INTERSPEECH
Deep neural networks (DNNs) and more precisely recurrent neural networks (RNNs) are at the core of modern automatic speech recognition systems, due to their efficiency to process input sequences. Recently, it has been shown that different input repre
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5b861c082624b8ed15e3fdc9eba6f156
https://hal.archives-ouvertes.fr/hal-02158201/file/INTERSPEECH_2019___Projection_QLSTM-3.pdf
https://hal.archives-ouvertes.fr/hal-02158201/file/INTERSPEECH_2019___Projection_QLSTM-3.pdf
Publikováno v:
ICASSP
Recurrent neural networks (RNN) are at the core of modern automatic speech recognition (ASR) systems. In particular, long-short term memory (LSTM) recurrent neural networks have achieved state-of-the-art results in many speech recognition tasks, due