Picture for Daisuke Saito

Daisuke Saito

A Pilot Study of Applying Sequence-to-Sequence Voice Conversion to Evaluate the Intelligibility of L2 Speech Using a Native Speaker's Shadowings

Add code
Oct 03, 2024
Viaarxiv icon

Simulating Native Speaker Shadowing for Nonnative Speech Assessment with Latent Speech Representations

Add code
Sep 19, 2024
Figure 1 for Simulating Native Speaker Shadowing for Nonnative Speech Assessment with Latent Speech Representations
Figure 2 for Simulating Native Speaker Shadowing for Nonnative Speech Assessment with Latent Speech Representations
Figure 3 for Simulating Native Speaker Shadowing for Nonnative Speech Assessment with Latent Speech Representations
Figure 4 for Simulating Native Speaker Shadowing for Nonnative Speech Assessment with Latent Speech Representations
Viaarxiv icon

A Pilot Study of GSLM-based Simulation of Foreign Accentuation Only Using Native Speech Corpora

Add code
Jul 16, 2024
Viaarxiv icon

Do learned speech symbols follow Zipf's law?

Add code
Sep 18, 2023
Viaarxiv icon

Preliminary Systematic Literature Review of Machine Learning System Development Process

Add code
Oct 12, 2019
Figure 1 for Preliminary Systematic Literature Review of Machine Learning System Development Process
Figure 2 for Preliminary Systematic Literature Review of Machine Learning System Development Process
Viaarxiv icon

A Spoofing Benchmark for the 2018 Voice Conversion Challenge: Leveraging from Spoofing Countermeasures for Speech Artifact Assessment

Add code
Sep 04, 2018
Figure 1 for A Spoofing Benchmark for the 2018 Voice Conversion Challenge: Leveraging from Spoofing Countermeasures for Speech Artifact Assessment
Figure 2 for A Spoofing Benchmark for the 2018 Voice Conversion Challenge: Leveraging from Spoofing Countermeasures for Speech Artifact Assessment
Figure 3 for A Spoofing Benchmark for the 2018 Voice Conversion Challenge: Leveraging from Spoofing Countermeasures for Speech Artifact Assessment
Figure 4 for A Spoofing Benchmark for the 2018 Voice Conversion Challenge: Leveraging from Spoofing Countermeasures for Speech Artifact Assessment
Viaarxiv icon

Wasserstein GAN and Waveform Loss-based Acoustic Model Training for Multi-speaker Text-to-Speech Synthesis Systems Using a WaveNet Vocoder

Add code
Jul 31, 2018
Figure 1 for Wasserstein GAN and Waveform Loss-based Acoustic Model Training for Multi-speaker Text-to-Speech Synthesis Systems Using a WaveNet Vocoder
Figure 2 for Wasserstein GAN and Waveform Loss-based Acoustic Model Training for Multi-speaker Text-to-Speech Synthesis Systems Using a WaveNet Vocoder
Figure 3 for Wasserstein GAN and Waveform Loss-based Acoustic Model Training for Multi-speaker Text-to-Speech Synthesis Systems Using a WaveNet Vocoder
Figure 4 for Wasserstein GAN and Waveform Loss-based Acoustic Model Training for Multi-speaker Text-to-Speech Synthesis Systems Using a WaveNet Vocoder
Viaarxiv icon

The Voice Conversion Challenge 2018: Promoting Development of Parallel and Nonparallel Methods

Add code
Apr 12, 2018
Figure 1 for The Voice Conversion Challenge 2018: Promoting Development of Parallel and Nonparallel Methods
Figure 2 for The Voice Conversion Challenge 2018: Promoting Development of Parallel and Nonparallel Methods
Figure 3 for The Voice Conversion Challenge 2018: Promoting Development of Parallel and Nonparallel Methods
Figure 4 for The Voice Conversion Challenge 2018: Promoting Development of Parallel and Nonparallel Methods
Viaarxiv icon