BigVSAN: Enhancing GAN-based Neural Vocoders with Slicing Adversarial Network

ICASSP, 2023
Takashi Shibuya, Yuhta Takida, Yuki Mitsufuji

Generative adversarial network (GAN)-based vocoders have been intensively studied because they can synthesize high-fidelity audio waveforms faster than real-time. However, it has been reported that most GANs fail to obtain the optimal projection for discriminating between re…

Diffusion-Based Speech Enhancement with Joint Generative and Predictive Decoders

ICASSP, 2023
Hao Shi*, Kazuki Shimada, Masato Hirano*, Takashi Shibuya, Yuichiro Koyama*, Zhi Zhong*, Shusuke Takahashi*, Tatsuya Kawahara*, Yuki Mitsufuji

Diffusion-based speech enhancement (SE) has been investigated recently, but its decoding is very time-consuming. One solution is to initialize the decoding process with the enhanced feature estimated by a predictive SE system. However, this two-stage method ignores the compl…

Zero- and Few-shot Sound Event Localization and Detection

ICASSP, 2023
Kazuki Shimada, Kengo Uchida, Yuichiro Koyama*, Takashi Shibuya, Shusuke Takahashi*, Yuki Mitsufuji, Tatsuya Kawahara*

Sound event localization and detection (SELD) systems estimate direction-of-arrival (DOA) and temporal activation for sets of target classes. Neural network (NN)-based SELD systems have performed well in various sets of target classes, but they only output the DOA and tempor…

Extending Audio Masked Autoencoders Toward Audio Restoration

WASPAA, 2023
Zhi Zhong*, Hao Shi*, Masato Hirano*, Kazuki Shimada, Kazuya Tateishi*, Takashi Shibuya, Shusuke Takahashi*, Yuki Mitsufuji

Audio classification and restoration are among major downstream tasks in audio signal processing. However, restoration derives less of a benefit from pretrained models compared to the overwhelming success of pretrained models in classification tasks. Due to such unbalanced b…

Diffiner: A Versatile Diffusion-based Generative Refiner for Speech Enhancement

Interspeech, 2023
Ryosuke Sawata*, Naoki Murata, Yuhta Takida, Toshimitsu Uesaka, Takashi Shibuya, Shusuke Takahashi*, Yuki Mitsufuji

Although deep neural network (DNN)-based speech enhancement (SE) methods outperform the previous non-DNN-based ones, they often degrade the perceptual quality of generated outputs. To tackle this problem, we introduce a DNN-based generative refiner, Diffiner, aiming to impro…

SQ-VAE: Variational Bayes on Discrete Representation with Self-annealed Stochastic Quantization

ICML, 2022
Yuhta Takida, Takashi Shibuya, Wei-Hsiang Liao, Chieh-Hsin Lai, Junki Ohmura*, Toshimitsu Uesaka, Naoki Murata, Shusuke Takahashi*, Toshiyuki Kumakura*, Yuki Mitsufuji

One noted issue of vector-quantized variational autoencoder (VQ-VAE) is that the learned discrete representation uses only a fraction of the full capacity of the codebook, also known as codebook collapse. We hypothesize that the training scheme of VQ-VAE, which involves some…


Shape the Future of AI with Sony AI

We want to hear from those of you who have a strong desire
to shape the future of AI.