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 …
The Nós Project: Opening routes for the Galician language in the field of language technologies
The development of language technologies (LTs) such as machine translation, text
analytics, and dialogue systems is essential in the current digital society, culture and …
analytics, and dialogue systems is essential in the current digital society, culture and …
Using current biometrics technologies for authentication in e-learning assessment
This paper introduces current biometric technologies that can be easily used for advanced
authentication methods for remote assessment in e-learning solutions. The focus is on …
authentication methods for remote assessment in e-learning solutions. The focus is on …
Unsupervised learning for expressive speech synthesis
I Jauk - 2017 - upcommons.upc.edu
Nowadays, especially with the upswing of neural networks, speech synthesis is almost
totally data driven. The goal of this thesis is to provide methods for automatic and …
totally data driven. The goal of this thesis is to provide methods for automatic and …
Web-based automation speech-to-text application using audio recording for meeting speech
M Yasir, MNK Nababan, Y Laia… - Journal of physics …, 2019 - iopscience.iop.org
The use of technology is very important nowadays. Most of everyday activities are
documented and stored in digital form. One of those activity is recording. Activity of an …
documented and stored in digital form. One of those activity is recording. Activity of an …
A Spanish multispeaker database of esophageal speech
LS García, S Raman, IH Rioja, EN Cordón… - Computer Speech & …, 2021 - Elsevier
A laryngectomee is a person whose larynx has been removed by surgery, usually due to
laryngeal cancer. After surgery, most laryngectomees are able to speak again, using …
laryngeal cancer. After surgery, most laryngectomees are able to speak again, using …
[PDF][PDF] Listening to Laryngectomees: A study of Intelligibility and Self-reportedListening Effort of Spanish Oesophageal Speech
Oesophageal speakers face a multitude of challenges, such as difficulty in basic everyday
communication and inability to interact with digital voice assistants. We aim to quantify the …
communication and inability to interact with digital voice assistants. We aim to quantify the …
Intelligibility and listening effort of Spanish oesophageal speech
Communication is a huge challenge for oesophageal speakers, be it for interactions with
fellow humans or with digital voice assistants. We aim to quantify these communication …
fellow humans or with digital voice assistants. We aim to quantify these communication …
Designing high-coverage multi-level text corpus for non-professional-voice conservation
M Jůzová, D Tihelka, J Matoušek - International Conference on Speech …, 2016 - Springer
The paper focuses on building a text corpus suitable for the conservation of the voices of
non-professional speakers, who are loosing their voices due to serious healthy problems …
non-professional speakers, who are loosing their voices due to serious healthy problems …
Development of the Slovak HMM-based tts system and evaluation of voices in respect to the used vocoding techniques
M Sulír, J Juhár, M Rusko - Computing and Informatics, 2016 - cai.sk
This paper describes the development of a Slovak text-to-speech system which applies a
technique wherein speech is directly synthesized from hidden Markov models. Statistical …
technique wherein speech is directly synthesized from hidden Markov models. Statistical …