11 citations · 20 across the 12 of their papers we have counts for
12 papers
Audio Spotforming via Post-Filtering Using Cross-Array Non-target Estimates
Yuto Ishikawa, Li Li, Shogo Seki +1
Audio spotforming is a technique for extracting target speech from noisy mixtures by utilizing multiple microphone arrays. Conventional methods estimate a shared target speech comp…
Confidence-based Filtering for Speech Dataset Curation with Generative Speech Enhancement Using Discrete Tokens
Kazuki Yamauchi, Masato Murata, Shogo Seki
Generative speech enhancement (GSE) models show great promise in producing high-quality clean speech from noisy inputs, enabling applications such as curating noisy text-to-speech…
The T12 System for AudioMOS Challenge 2025: Audio Aesthetics Score Prediction System Using KAN- and VERSA-based Models
Katsuhiko Yamamoto, Koichi Miyazaki, Shogo Seki
We propose an audio aesthetics score (AES) prediction system by CyberAgent (AESCA) for AudioMOS Challenge 2025 (AMC25) Track 2. The AESCA comprises a Kolmogorov--Arnold Network (KA…
Improving DF-Conformer Using Hydra For High-Fidelity Generative Speech Enhancement on Discrete Codec Token
Shogo Seki, Shaoxiang Dang, Li Li
The Dilated FAVOR Conformer (DF-Conformer) is an efficient variant of the Conformer architecture designed for speech enhancement (SE). It employs fast attention through positive or…
Audio Spotforming Using Nonnegative Tensor Factorization with Attractor-Based Regularization
Shoma Ayano, Li Li, Shogo Seki +1
Spotforming is a target-speaker extraction technique that uses multiple microphone arrays. This method applies beamforming (BF) to each microphone array, and the common components…
Improved Remixing Process for Domain Adaptation-Based Speech Enhancement by Mitigating Data Imbalance in Signal-to-Noise Ratio
Li Li, Shogo Seki
RemixIT and Remixed2Remixed are domain adaptation-based speech enhancement (DASE) methods that use a teacher model trained in full supervision to generate pseudo-paired data by rem…
Remixed2Remixed: Domain adaptation for speech enhancement by Noise2Noise learning with Remixing
Li Li, Shogo Seki
This paper proposes Remixed2Remixed, a domain adaptation method for speech enhancement, which adopts Noise2Noise (N2N) learning to adapt models trained on artificially generated (o…
iSTFTNet2: Faster and More Lightweight iSTFT-Based Neural Vocoder Using 1D-2D CNN
Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka +1
The inverse short-time Fourier transform network (iSTFTNet) has garnered attention owing to its fast, lightweight, and high-fidelity speech synthesis. It obtains these characterist…
Wave-U-Net Discriminator: Fast and Lightweight Discriminator for Generative Adversarial Network-Based Speech Synthesis
Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka +1
In speech synthesis, a generative adversarial network (GAN), training a generator (speech synthesizer) and a discriminator in a min-max game, is widely used to improve speech quali…
iSTFTNet: Fast and Lightweight Mel-Spectrogram Vocoder Incorporating Inverse Short-Time Fourier Transform
Takuhiro Kaneko, Kou Tanaka, Hirokazu Kameoka +1
In recent text-to-speech synthesis and voice conversion systems, a mel-spectrogram is commonly applied as an intermediate representation, and the necessity for a mel-spectrogram vo…
VoiceGrad: Non-Parallel Any-to-Many Voice Conversion with Annealed Langevin Dynamics
Hirokazu Kameoka, Takuhiro Kaneko, Kou Tanaka +2
In this paper, we propose a non-parallel any-to-many voice conversion (VC) method termed VoiceGrad. Inspired by WaveGrad, a recently introduced novel waveform generation method, Vo…
Generalized Multichannel Variational Autoencoder for Underdetermined Source Separation
Shogo Seki, Hirokazu Kameoka, Li Li +2
This paper deals with a multichannel audio source separation problem under underdetermined conditions. Multichannel Non-negative Matrix Factorization (MNMF) is one of powerful appr…