2 |
Speech Synthesis from ECoG using Densely Connected 3D Convolutional Neural Networks
|
|
|
|
In: J Neural Eng (2019)
|
|
Abstract:
OBJECTIVE: Direct synthesis of speech from neural signals could provide a fast and natural way of communication to people with neurological diseases. Invasively-measured brain activity (electrocorticography; ECoG) supplies the necessary temporal and spatial resolution to decode fast and complex processes such as speech production. A number of impressive advances in speech decoding using neural signals have been achieved in recent years, but the complex dynamics are still not fully understood. However, it is unlikely that simple linear models can capture the relation between neural activity and continuous spoken speech. APPROACH: Here we show that deep neural networks can be used to map ECoG from speech production areas onto an intermediate representation of speech (logMel spectrogram). The proposed method uses a densely connected convolutional neural network topology which is well-suited to work with the small amount of data available from each participant. MAIN RESULTS: In a study with six participants, we achieved correlations up to r = 0.69 between the reconstructed and original logMel spectrograms. We transfered our prediction back into an audible waveform by applying a Wavenet vocoder. The vocoder was conditioned on logMel features that harnessed a much larger, pre-existing data corpus to provide the most natural acoustic output. SIGNIFICANCE: To the best of our knowledge, this is the first time that high-quality speech has been reconstructed from neural recordings during speech production using deep neural networks.
|
|
Keyword:
Article
|
|
URL: https://doi.org/10.1088/1741-2552/ab0c59 http://www.ncbi.nlm.nih.gov/pubmed/30831567 http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6822609/
|
|
BASE
|
|
Hide details
|
|
3 |
Generating Natural, Intelligible Speech From Brain Activity in Motor, Premotor, and Inferior Frontal Cortices
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Automatic Speech Recognition from Neural Signals: A Focused Review
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Brain-to-text: decoding spoken phrases from phone representations in the brain
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Multilingual Deep Neural Network based Acoustic Modeling For Rapid Language Adaptation
|
|
|
|
In: http://infoscience.epfl.ch/record/198446 (2014)
|
|
BASE
|
|
Show details
|
|
10 |
Integration of Language Identification into a Recognition System for Spoken Conversations Containing Code-Switches ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Integration of Language Identification into a Recognition System for Spoken Conversations Containing Code-Switches ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
An Investigation on Initialization Schemes for Multilayer Perceptron Training Using Multilingual Data and Their Effect on ASR Performance ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
An Investigation on Initialization Schemes for Multilayer Perceptron Training Using Multilingual Data and Their Effect on ASR Performance ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Multilingual Bottle-Neck Features and its Application for Under-Resourced Languages ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Multilingual Bottle-Neck Features and its Application for Under-Resourced Languages ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Modeling Coarticulation in EMG-based Continuous Speech Recognition
|
|
|
|
In: Speech Communication, 52 (4), 341-353 ; ISSN: 0167-6393 (2012)
|
|
BASE
|
|
Show details
|
|
|
|