| 1 |
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
|
|
|
| 2 |
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
|
|
|
| 3 |
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)
|
|
Abstract:
International audience ; Recent progress in deep learning for audio synthesis opens the way to models that directly produce the waveform, shifting away from the traditional paradigm of relying on vocoders or MIDI synthesizers for speech or music generation. Despite their successes, current state-of-the-art neural audio synthesizers such as WaveNet and SampleRNN suffer from prohibitive training and inference times because they are based on autoregressive models that generate audio samples one at a time at a rate of 16kHz. In this work, we study the more computationally efficient alternative of generating the waveform frame-by-frame with large strides. We present SING, a lightweight neural audio synthesizer for the original task of generating musical notes given desired instrument, pitch and velocity. Our model is trained end-to-end to generate notes from nearly 1000 instruments with a single decoder, thanks to a new loss function that minimizes the distances between the log spectrograms of the generated and target waveforms. On the generalization task of synthesizing notes for pairs of pitch and instrument not seen during training, SING produces audio with significantly improved perceptual quality compared to a state-of-the-art autoencoder based on WaveNet as measured by a Mean Opinion Score (MOS), and is about 32 times faster for training and 2, 500 times faster for inference.
|
|
Keyword:
[INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]; [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG]; [INFO.INFO-SD]Computer Science [cs]/Sound [cs.SD]; [SCCO.LING]Cognitive science/Linguistics; [SCCO]Cognitive science; [STAT.ML]Statistics [stat]/Machine Learning [stat.ML]
|
|
URL: https://hal.archives-ouvertes.fr/hal-01899949/document
https://hal.archives-ouvertes.fr/hal-01899949/file/symbol_to_instrument_neural_generator.pdf
https://hal.archives-ouvertes.fr/hal-01899949
|
|
BASE
|
|
Hide details
|
|
|
| 5 |
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
|
|
|
| 6 |
Multiview self-learning
|
|
|
|
In: ISSN: 0925-2312 ; Neurocomputing ; https://hal.archives-ouvertes.fr/hal-01211216 ; Neurocomputing, Elsevier, 2015, 155, pp.117-127. ⟨10.1016/j.neucom.2014.12.041⟩ ; http://www.sciencedirect.com/science/article/pii/S0925231214017056 (2015)
|
|
BASE
|
|
Show details
|
|
|
| 7 |
Open Question Answering with Weakly Supervised Embedding Models
|
|
|
|
In: European Conference (ECML PKDD 2014) ; https://hal.archives-ouvertes.fr/hal-01344007 ; European Conference (ECML PKDD 2014), Sep 2014, nancy, France. pp.165-180, ⟨10.1007/978-3-662-44848-9_11⟩ (2014)
|
|
BASE
|
|
Show details
|
|
|
| 8 |
Open Question Answering with Weakly Supervised Embedding Models ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 9 |
Multiview Semi-Supervised Learning for Ranking Multilingual Documents
|
|
|
|
In: European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases ; https://hal.archives-ouvertes.fr/hal-01286156 ; European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, Sep 2011, Athens, Greece. pp.443-458, ⟨10.1007/978-3-642-23808-6_29⟩ (2011)
|
|
BASE
|
|
Show details
|
|
|
| 10 |
Combining Coregularization and Consensus-Based Self-Training for Multilingual Text Categorization
|
|
|
|
In: Proceedings of the 33rd Annual ACM SIGIR Conference (SIGIR 2010) ; The 33rd Annual ACM SIGIR Conference (SIGIR 2010) ; https://hal.archives-ouvertes.fr/hal-01291883 ; The 33rd Annual ACM SIGIR Conference (SIGIR 2010), Jul 2010, Geneva, Switzerland. pp.475-482, ⟨10.1145/1835449.1835529⟩ (2010)
|
|
BASE
|
|
Show details
|
|
|
| 11 |
Towards Understanding Situated Natural Language
|
|
|
|
In: 13th International Conference on Artificial Intelligence and Statistics ; https://hal.archives-ouvertes.fr/hal-00750937 ; 13th International Conference on Artificial Intelligence and Statistics, May 2010, Chia Laguna Resort, Sardinia, Italy. pp.65-72 (2010)
|
|
BASE
|
|
Show details
|
|
|
| 12 |
Improving Image Annotation in Imbalanced Classification Problems with Ranking SVM
|
|
|
|
In: Multilingual Information Access Evaluation II. Multimedia Experiments ; CLEF 2009 - 10th Workshop of the Cross-Language Evaluation Forum ; https://hal.archives-ouvertes.fr/hal-00581661 ; CLEF 2009 - 10th Workshop of the Cross-Language Evaluation Forum, Sep 2009, Corfu, Greece. pp.291-294, ⟨10.1007/978-3-642-15751-6_37⟩ (2009)
|
|
BASE
|
|
Show details
|
|
|
| 13 |
Learning from Multiple Partially Observed Views -- an Application to Multilingual Text Categorization
|
|
|
|
In: Advances in Neural Information Processing Systems ; https://hal.archives-ouvertes.fr/hal-01297947 ; Advances in Neural Information Processing Systems, Dec 2009, Vancouver, Canada (2009)
|
|
BASE
|
|
Show details
|
|
|
|
|
