Picture for Lester Phillip Violeta

Lester Phillip Violeta

A Preliminary Investigation on Flexible Singing Voice Synthesis Through Decomposed Framework with Inferrable Features

Add code
Jul 12, 2024
Viaarxiv icon

Quantifying the effect of speech pathology on automatic and human speaker verification

Add code
Jun 10, 2024
Viaarxiv icon

A Comparative Study of Voice Conversion Models with Large-Scale Speech and Singing Data: The T13 Systems for the Singing Voice Conversion Challenge 2023

Add code
Oct 08, 2023
Figure 1 for A Comparative Study of Voice Conversion Models with Large-Scale Speech and Singing Data: The T13 Systems for the Singing Voice Conversion Challenge 2023
Figure 2 for A Comparative Study of Voice Conversion Models with Large-Scale Speech and Singing Data: The T13 Systems for the Singing Voice Conversion Challenge 2023
Figure 3 for A Comparative Study of Voice Conversion Models with Large-Scale Speech and Singing Data: The T13 Systems for the Singing Voice Conversion Challenge 2023
Figure 4 for A Comparative Study of Voice Conversion Models with Large-Scale Speech and Singing Data: The T13 Systems for the Singing Voice Conversion Challenge 2023
Viaarxiv icon

Improving severity preservation of healthy-to-pathological voice conversion with global style tokens

Add code
Oct 04, 2023
Viaarxiv icon

Electrolaryngeal Speech Intelligibility Enhancement Through Robust Linguistic Encoders

Add code
Sep 18, 2023
Viaarxiv icon

The Singing Voice Conversion Challenge 2023

Add code
Jul 06, 2023
Viaarxiv icon

An Analysis of Personalized Speech Recognition System Development for the Deaf and Hard-of-Hearing

Add code
Jun 24, 2023
Viaarxiv icon

Intermediate Fine-Tuning Using Imperfect Synthetic Speech for Improving Electrolaryngeal Speech Recognition

Add code
Nov 02, 2022
Viaarxiv icon

Two-stage training method for Japanese electrolaryngeal speech enhancement based on sequence-to-sequence voice conversion

Add code
Oct 19, 2022
Figure 1 for Two-stage training method for Japanese electrolaryngeal speech enhancement based on sequence-to-sequence voice conversion
Figure 2 for Two-stage training method for Japanese electrolaryngeal speech enhancement based on sequence-to-sequence voice conversion
Figure 3 for Two-stage training method for Japanese electrolaryngeal speech enhancement based on sequence-to-sequence voice conversion
Figure 4 for Two-stage training method for Japanese electrolaryngeal speech enhancement based on sequence-to-sequence voice conversion
Viaarxiv icon

Investigating Self-supervised Pretraining Frameworks for Pathological Speech Recognition

Add code
Mar 30, 2022
Figure 1 for Investigating Self-supervised Pretraining Frameworks for Pathological Speech Recognition
Figure 2 for Investigating Self-supervised Pretraining Frameworks for Pathological Speech Recognition
Figure 3 for Investigating Self-supervised Pretraining Frameworks for Pathological Speech Recognition
Figure 4 for Investigating Self-supervised Pretraining Frameworks for Pathological Speech Recognition
Viaarxiv icon