End-to-end Phoneme Sequence Recognition using Convolutional Neural Networks
By Dimitri Palaz, Ronan Collobert, Mathew Magimai-Doss. 2013
43 citations recorded by the source corpus.
Note: Accepted at NIPS Deep learning Workshop Reference EPFL-REPORT-192559 Record created on 2013-12-19, modified on 2017-05-10
Subfields: Artificial Intelligence, Speech & Audio, Signal Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Gabriel Synnaeve
- Emmanuel Dupoux
- Ronan Collobert
- Satoshi Nakamura
- Andros Tjandra
- Sakriani Watiasri Sakti
- Yoshua Bengio
- Neil Zeghidour
In Speech & Audio
- Gabriel Synnaeve
- Emmanuel Dupoux
- Ronan Collobert
- Andros Tjandra
- Neil Zeghidour
- Sakriani Watiasri Sakti
- Satoshi Nakamura
- Thomas Schatz
In Signal Processing
- Gabriel Synnaeve
- Emmanuel Dupoux
- Ronan Collobert
- Neil Zeghidour
- Andros Tjandra
- Sakriani Watiasri Sakti
- Satoshi Nakamura
- Thomas Schatz
Citations in the corpus
- Learning Filterbanks from Raw Speech for Phone Recognition (2017, methodology): “Dev PER Test PER Hybrid HMM/Hierarchical CNN + Maxout + Dropout [10] MFSC + energy + ∆ + ∆∆ 13.3 16.5 CNN + CRF on raw speech [13] wav - 29.2 CNN-Conv2D-10L-Maxout [ [10] are trained in an end-to-end fashion.”
- Analysis of CNN-based speech recognition system using raw speech as input (2015, methodology): “Using temporal raw speech directly as input has been proposed in the context of DNNs [14] and in the context of end-to-end sequence-discriminative training of CNNs [15].”
- Attention-based Wav2Text with feature transfer learning (2017, background): “Deep learning is well known for its ability to learn directly from low-level feature representation such as raw speech [2, 4].”