Silent speech interfaces for speech restoration: A review
JA Gonzalez-Lopez, A Gomez-Alanis… - IEEE …, 2020 - ieeexplore.ieee.org
This review summarises the status of silent speech interface (SSI) research. SSIs rely on non-
acoustic biosignals generated by the human body during speech production to enable …
acoustic biosignals generated by the human body during speech production to enable …
Operator-valued kernels for learning from functional response data
In this paper we consider the problems of supervised classification and regression in the
case where attributes and labels are functions: a data is represented by a set of functions …
case where attributes and labels are functions: a data is represented by a set of functions …
A silent speech system based on permanent magnet articulography and direct synthesis
JA Gonzalez, LA Cheah, JM Gilbert, J Bai, SR Ell… - Computer Speech & …, 2016 - Elsevier
In this paper we present a silent speech interface (SSI) system aimed at restoring speech
communication for individuals who have lost their voice due to laryngectomy or diseases …
communication for individuals who have lost their voice due to laryngectomy or diseases …
Acoustic-to-articulatory mapping with joint optimization of deep speech enhancement and articulatory inversion models
AS Shahrebabaki, G Salvi, T Svendsen… - … on Audio, Speech …, 2021 - ieeexplore.ieee.org
We investigate the problem of speaker independent acoustic-to-articulatory inversion (AAI)
in noisy conditions within the deep neural network (DNN) framework. In contrast with recent …
in noisy conditions within the deep neural network (DNN) framework. In contrast with recent …
Retrieving tract variables from acoustics: a comparison of different machine learning strategies
Many different studies have claimed that articulatory information can be used to improve the
performance of automatic speech recognition systems. Unfortunately, such articulatory …
performance of automatic speech recognition systems. Unfortunately, such articulatory …
Speaker-adaptive acoustic-articulatory inversion using cascaded gaussian mixture regression
This paper addresses the adaptation of an acoustic-articulatory model of a reference
speaker to the voice of another speaker, using a limited amount of audio-only data. In the …
speaker to the voice of another speaker, using a limited amount of audio-only data. In the …
Recognizing articulatory gestures from speech for robust speech recognition
Studies have shown that supplementary articulatory information can help to improve the
recognition rate of automatic speech recognition systems. Unfortunately, articulatory …
recognition rate of automatic speech recognition systems. Unfortunately, articulatory …
Articulatory and spectrum information fusion based on deep recurrent neural networks
Many studies have shown that articulatory features can significantly improve the
performance of automatic speech recognition systems. Unfortunately, such features are not …
performance of automatic speech recognition systems. Unfortunately, such features are not …
[PDF][PDF] Cross-speaker Acoustic-to-Articulatory Inversion using Phone-based Trajectory HMM for Pronunciation Training.
The article presents a statistical mapping approach for crossspeaker acoustic-to-articulatory
inversion. The goal is to estimate the most likely articulatory trajectories for a reference …
inversion. The goal is to estimate the most likely articulatory trajectories for a reference …
[PDF][PDF] Raw Speech-to-Articulatory Inversion by Temporal Filtering and Decimation.
AS Shahrebabaki, SM Siniscalchi, T Svendsen - Interspeech, 2021 - iris.unipa.it
We propose a novel sequence-to-sequence acoustic-toarticulatory inversion (AAI) neural
architecture in the temporal waveform domain. In contrast to traditional AAI approaches that …
architecture in the temporal waveform domain. In contrast to traditional AAI approaches that …