Picture for Patrick Lumban Tobing

Patrick Lumban Tobing

Expressive Machine Dubbing Through Phrase-level Cross-lingual Prosody Transfer

Add code
Jun 21, 2023
Viaarxiv icon

Cross-lingual Prosody Transfer for Expressive Machine Dubbing

Add code
Jun 20, 2023
Viaarxiv icon

A Cyclical Approach to Synthetic and Natural Speech Mismatch Refinement of Neural Post-filter for Low-cost Text-to-speech System

Add code
Jul 13, 2022
Figure 1 for A Cyclical Approach to Synthetic and Natural Speech Mismatch Refinement of Neural Post-filter for Low-cost Text-to-speech System
Figure 2 for A Cyclical Approach to Synthetic and Natural Speech Mismatch Refinement of Neural Post-filter for Low-cost Text-to-speech System
Figure 3 for A Cyclical Approach to Synthetic and Natural Speech Mismatch Refinement of Neural Post-filter for Low-cost Text-to-speech System
Figure 4 for A Cyclical Approach to Synthetic and Natural Speech Mismatch Refinement of Neural Post-filter for Low-cost Text-to-speech System
Viaarxiv icon

Direct Noisy Speech Modeling for Noisy-to-Noisy Voice Conversion

Add code
Nov 13, 2021
Figure 1 for Direct Noisy Speech Modeling for Noisy-to-Noisy Voice Conversion
Figure 2 for Direct Noisy Speech Modeling for Noisy-to-Noisy Voice Conversion
Figure 3 for Direct Noisy Speech Modeling for Noisy-to-Noisy Voice Conversion
Figure 4 for Direct Noisy Speech Modeling for Noisy-to-Noisy Voice Conversion
Viaarxiv icon

Noisy-to-Noisy Voice Conversion Framework with Denoising Model

Add code
Sep 22, 2021
Figure 1 for Noisy-to-Noisy Voice Conversion Framework with Denoising Model
Figure 2 for Noisy-to-Noisy Voice Conversion Framework with Denoising Model
Figure 3 for Noisy-to-Noisy Voice Conversion Framework with Denoising Model
Figure 4 for Noisy-to-Noisy Voice Conversion Framework with Denoising Model
Viaarxiv icon

Low-Latency Real-Time Non-Parallel Voice Conversion based on Cyclic Variational Autoencoder and Multiband WaveRNN with Data-Driven Linear Prediction

Add code
May 20, 2021
Figure 1 for Low-Latency Real-Time Non-Parallel Voice Conversion based on Cyclic Variational Autoencoder and Multiband WaveRNN with Data-Driven Linear Prediction
Figure 2 for Low-Latency Real-Time Non-Parallel Voice Conversion based on Cyclic Variational Autoencoder and Multiband WaveRNN with Data-Driven Linear Prediction
Figure 3 for Low-Latency Real-Time Non-Parallel Voice Conversion based on Cyclic Variational Autoencoder and Multiband WaveRNN with Data-Driven Linear Prediction
Figure 4 for Low-Latency Real-Time Non-Parallel Voice Conversion based on Cyclic Variational Autoencoder and Multiband WaveRNN with Data-Driven Linear Prediction
Viaarxiv icon

High-Fidelity and Low-Latency Universal Neural Vocoder based on Multiband WaveRNN with Data-Driven Linear Prediction for Discrete Waveform Modeling

Add code
May 20, 2021
Figure 1 for High-Fidelity and Low-Latency Universal Neural Vocoder based on Multiband WaveRNN with Data-Driven Linear Prediction for Discrete Waveform Modeling
Figure 2 for High-Fidelity and Low-Latency Universal Neural Vocoder based on Multiband WaveRNN with Data-Driven Linear Prediction for Discrete Waveform Modeling
Figure 3 for High-Fidelity and Low-Latency Universal Neural Vocoder based on Multiband WaveRNN with Data-Driven Linear Prediction for Discrete Waveform Modeling
Figure 4 for High-Fidelity and Low-Latency Universal Neural Vocoder based on Multiband WaveRNN with Data-Driven Linear Prediction for Discrete Waveform Modeling
Viaarxiv icon

crank: An Open-Source Software for Nonparallel Voice Conversion Based on Vector-Quantized Variational Autoencoder

Add code
Mar 04, 2021
Figure 1 for crank: An Open-Source Software for Nonparallel Voice Conversion Based on Vector-Quantized Variational Autoencoder
Figure 2 for crank: An Open-Source Software for Nonparallel Voice Conversion Based on Vector-Quantized Variational Autoencoder
Viaarxiv icon

The NU Voice Conversion System for the Voice Conversion Challenge 2020: On the Effectiveness of Sequence-to-sequence Models and Autoregressive Neural Vocoders

Add code
Oct 09, 2020
Figure 1 for The NU Voice Conversion System for the Voice Conversion Challenge 2020: On the Effectiveness of Sequence-to-sequence Models and Autoregressive Neural Vocoders
Figure 2 for The NU Voice Conversion System for the Voice Conversion Challenge 2020: On the Effectiveness of Sequence-to-sequence Models and Autoregressive Neural Vocoders
Figure 3 for The NU Voice Conversion System for the Voice Conversion Challenge 2020: On the Effectiveness of Sequence-to-sequence Models and Autoregressive Neural Vocoders
Figure 4 for The NU Voice Conversion System for the Voice Conversion Challenge 2020: On the Effectiveness of Sequence-to-sequence Models and Autoregressive Neural Vocoders
Viaarxiv icon

Baseline System of Voice Conversion Challenge 2020 with Cyclic Variational Autoencoder and Parallel WaveGAN

Add code
Oct 09, 2020
Figure 1 for Baseline System of Voice Conversion Challenge 2020 with Cyclic Variational Autoencoder and Parallel WaveGAN
Figure 2 for Baseline System of Voice Conversion Challenge 2020 with Cyclic Variational Autoencoder and Parallel WaveGAN
Figure 3 for Baseline System of Voice Conversion Challenge 2020 with Cyclic Variational Autoencoder and Parallel WaveGAN
Figure 4 for Baseline System of Voice Conversion Challenge 2020 with Cyclic Variational Autoencoder and Parallel WaveGAN
Viaarxiv icon