| 1 |
Learning representations of speech from the raw waveform ; Apprentissage de représentations de la parole à partir du signal brut
|
|
|
|
In: https://tel.archives-ouvertes.fr/tel-02278616 ; Machine Learning [cs.LG]. Université Paris sciences et lettres, 2019. English. ⟨NNT : 2019PSLEE004⟩ (2019)
|
|
BASE
|
|
Show details
|
|
|
| 2 |
Learning to detect dysarthria from raw speech
|
|
|
|
In: ICASSP ; ICASSP-2019 - IEEE International Conference on Acoustics, Speech and Signal Processing ; https://hal.archives-ouvertes.fr/hal-02274504 ; ICASSP-2019 - IEEE International Conference on Acoustics, Speech and Signal Processing, May 2019, Brighton, United Kingdom (2019)
|
|
Abstract:
International audience ; Speech classifiers of paralinguistic traits traditionally learn from diverse hand-crafted low-level features, by selecting the relevant information for the task at hand. We explore an alternative to this selection, by learning jointly the classifier, and the feature extraction. Recent work on speech recognition has shown improved performance over speech features by learning from the waveform. We extend this approach to paralinguistic classification and propose a neural network that can learn a filterbank, a normalization factor and a compression power from the raw speech, jointly with the rest of the architecture. We apply this model to dysarthria detection from sentence-level audio recordings. Starting from a strong attention-based baseline on which mel-filterbanks outperform standard low-level descriptors, we show that learning the filters or the normalization and compression improves over fixed features by 10% absolute accuracy. We also observe a gain over OpenSmile features by learning jointly the feature extraction, the normalization, and the compression factor with the architecture. This constitutes a first attempt at learning jointly all these operations from raw audio for a speech classification task.
|
|
Keyword:
[INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]; [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]
|
|
URL: https://hal.archives-ouvertes.fr/hal-02274504
|
|
BASE
|
|
Hide details
|
|
|
| 3 |
Learning Filterbanks from Raw Speech for Phoneme Recognition
|
|
|
|
In: ICASSP 2018 - IEEE International Conference on Acoustics, Speech and Signal Processing ; https://hal.archives-ouvertes.fr/hal-01888737 ; ICASSP 2018 - IEEE International Conference on Acoustics, Speech and Signal Processing, Apr 2018, Calgary, Alberta, Canada (2018)
|
|
BASE
|
|
Show details
|
|
|
| 4 |
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
|
|
|
| 5 |
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
|
|
|
| 6 |
SING: Symbol-to-Instrument Neural Generator
|
|
|
|
In: Conference on Neural Information Processing Systems (NIPS) ; https://hal.archives-ouvertes.fr/hal-01899949 ; Conference on Neural Information Processing Systems (NIPS), Dec 2018, Montréal, Canada (2018)
|
|
BASE
|
|
Show details
|
|
|
| 8 |
Fader Networks: Manipulating Images by Sliding Attributes
|
|
|
|
In: 31st Conference on Neural Information Processing Systems (NIPS 2017) ; https://hal.archives-ouvertes.fr/hal-02275215 ; 31st Conference on Neural Information Processing Systems (NIPS 2017), Dec 2017, Long Beach, CA, United States. pp.5969-5978 (2017)
|
|
BASE
|
|
Show details
|
|
|
| 9 |
Learning Weakly Supervised Multimodal Phoneme Embeddings
|
|
|
|
In: Interspeech 2017 ; https://hal.inria.fr/hal-01687415 ; Interspeech 2017, 2017, Stockholm, Sweden. ⟨10.21437/Interspeech.2017-1689⟩ (2017)
|
|
BASE
|
|
Show details
|
|
|
| 10 |
Learning weakly supervised multimodal phoneme embeddings ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|
|
