Daisuke Saito

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

We present the Voice Conversion Challenge 2018, designed as a follow up to the 2016 edition with the aim of providing a common framework for evaluating and comparing different state-of-the-art...

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

Recent neural networks such as WaveNet and sampleRNN that learn directly from speech waveform samples have achieved very high-quality synthetic speech in terms of both naturalness and speaker...

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

Voice conversion (VC) aims at conversion of speaker characteristic without altering content. Due to training data limitations and modeling imperfections, it is difficult to achieve believable...

How Should We Evaluate Naturalness for Synthetic Speech with a Foreign Accent?

Recent advances in speech synthesis technology have enabled the generation of speech with diverse characteristics. One such characteristic is a foreign accent. In our preliminary experiments, we...

Bandwidth Extension System for Throat Microphone Speech Reconstruction

Cooking State Recognition based on Acoustic Event Detection

Density and Entropy of Spoken Syllables in American English and Japanese English Estimated with Acoustic Word Embeddings

Automatic prediction of intelligibility of English words spoken with Japanese accents - comparative study of features and models used for prediction

Development and Maintenance of Practical and In-service Systems for Recording Shadowing Utterances and Their Assessment

Native Listeners' Shadowing of Non-native Utterances as Spoken Annotation Representing Comprehensibility of the Utterances

Learners' Prosodic Control in the Task of Expressive Storytelling and Predicted Native Listeners' Impressions of the Learners' Speech

New Features and Effectiveness of Suzuki-kun, the First and Only Prosodic Reading Tutor of Tokyo Japanese

Development of a prosodic reading tutor of Japanese - effective use of TTS and F0 contour modeling techniques for CALL

Minecraft-based preparatory training for software development project

Analysis of Transient Signal Due to Person Movement in Gate System Using Intra-Body Communication

Analog In-memory Computing in FeFET-based 1T1R Array for Edge AI Applications

Prosodically Enhanced Foreign Accent Simulation by Discrete Token-based Resynthesis Only with Native Speech Corpora

Shadowability Annotation with Fine Granularity on L2 Utterances and its Improvement with Native Listeners' Script-Shadowing