Golden speaker builder–An interactive tool for pronunciation training
The type of voice model used in Computer Assisted Pronunciation Instruction is a crucial
factor in the quality of practice and the amount of uptake by language learners. As an …
factor in the quality of practice and the amount of uptake by language learners. As an …
Accentron: Foreign accent conversion to arbitrary non-native speakers using zero-shot learning
Foreign accent conversion (FAC) aims to create a new voice that has the voice identity of a
given second-language (L2) speaker but with a native (L1) accent. Previous FAC …
given second-language (L2) speaker but with a native (L1) accent. Previous FAC …
Accent conversion using phonetic posteriorgrams
Accent conversion (AC) aims to transform non-native speech to sound as if the speaker had
a native accent. This can be achieved by mapping source spectra from a native speaker into …
a native accent. This can be achieved by mapping source spectra from a native speaker into …
The use of articulatory movement data in speech synthesis applications: An overview—application of articulatory movements using machine learning algorithms—
This paper describes speech processing work in which articulator movements are used in
conjunction with the acoustic speech signal and/or linguistic information. By ''articulator …
conjunction with the acoustic speech signal and/or linguistic information. By ''articulator …
Converting foreign accent speech without a reference
Foreign accent conversion (FAC) is the problem of generating a synthetic voice that has the
voice identity of a second-language (L2) learner and the pronunciation patterns of a native …
voice identity of a second-language (L2) learner and the pronunciation patterns of a native …
Data driven articulatory synthesis with deep neural networks
S Aryal, R Gutierrez-Osuna - Computer Speech & Language, 2016 - Elsevier
The conventional approach for data-driven articulatory synthesis consists of modeling the
joint acoustic-articulatory distribution with a Gaussian mixture model (GMM), followed by a …
joint acoustic-articulatory distribution with a Gaussian mixture model (GMM), followed by a …
Can voice conversion be used to reduce non-native accents?
S Aryal, R Gutierrez-Osuna - 2014 IEEE International …, 2014 - ieeexplore.ieee.org
Voice-conversion (VC) techniques aim to transform utterances from a source speaker to
sound as if a target speaker had produced them. For this reason, VC is generally ill-suited …
sound as if a target speaker had produced them. For this reason, VC is generally ill-suited …
Using phonetic posteriorgram based frame pairing for segmental accent conversion
G Zhao, R Gutierrez-Osuna - IEEE/ACM Transactions on Audio …, 2019 - ieeexplore.ieee.org
Accent conversion (AC) aims to transform non-native utterances to sound as if the speaker
had a native accent. This can be achieved by mapping source speech spectra from a native …
had a native accent. This can be achieved by mapping source speech spectra from a native …
Tts-guided training for accent conversion without parallel data
Accent Conversion (AC) seeks to change the accent of speech from one (source) to another
(target) while preserving the speech content and speaker identity. However, many existing …
(target) while preserving the speech content and speaker identity. However, many existing …
Articulatory Copy Synthesis Based on the Speech Synthesizer VocalTractLab and Convolutional Recurrent Neural Networks
Articulatory copy synthesis (ACS) refers to the synthetic reproduction of natural utterances.
The existing methods of ACS have the limitations of poor generalizability for unknown …
The existing methods of ACS have the limitations of poor generalizability for unknown …