Picture for Adriana Stan

Adriana Stan

Efficient training strategies for natural sounding speech synthesis and speaker adaptation based on FastPitch

Add code
Oct 09, 2024
Viaarxiv icon

TBDM-Net: Bidirectional Dense Networks with Gender Information for Speech Emotion Recognition

Add code
Sep 16, 2024
Viaarxiv icon

WavLM model ensemble for audio deepfake detection

Add code
Aug 14, 2024
Viaarxiv icon

An analysis of large speech models-based representations for speech emotion recognition

Add code
Nov 01, 2023
Viaarxiv icon

Towards generalisable and calibrated synthetic speech detection with self-supervised representations

Add code
Sep 11, 2023
Viaarxiv icon

An analysis on the effects of speaker embedding choice in non auto-regressive TTS

Add code
Jul 19, 2023
Viaarxiv icon

Residual Information in Deep Speaker Embedding Architectures

Add code
Feb 06, 2023
Viaarxiv icon

The ZevoMOS entry to VoiceMOS Challenge 2022

Add code
Jun 15, 2022
Figure 1 for The ZevoMOS entry to VoiceMOS Challenge 2022
Figure 2 for The ZevoMOS entry to VoiceMOS Challenge 2022
Figure 3 for The ZevoMOS entry to VoiceMOS Challenge 2022
Viaarxiv icon

FlexLip: A Controllable Text-to-Lip System

Add code
Jun 07, 2022
Figure 1 for FlexLip: A Controllable Text-to-Lip System
Figure 2 for FlexLip: A Controllable Text-to-Lip System
Figure 3 for FlexLip: A Controllable Text-to-Lip System
Figure 4 for FlexLip: A Controllable Text-to-Lip System
Viaarxiv icon

An objective evaluation of the effects of recording conditions and speaker characteristics in multi-speaker deep neural speech synthesis

Add code
Jun 03, 2021
Figure 1 for An objective evaluation of the effects of recording conditions and speaker characteristics in multi-speaker deep neural speech synthesis
Figure 2 for An objective evaluation of the effects of recording conditions and speaker characteristics in multi-speaker deep neural speech synthesis
Figure 3 for An objective evaluation of the effects of recording conditions and speaker characteristics in multi-speaker deep neural speech synthesis
Figure 4 for An objective evaluation of the effects of recording conditions and speaker characteristics in multi-speaker deep neural speech synthesis
Viaarxiv icon