9 papers
Prox-Friendly Log-Magnitude Prior on Complex-Valued Signal
Kazuki Matsumoto, Keidai Arai, Kohei Yatabe
The logarithmic transform is essential in audio signal processing since human auditory perception is approximately logarithmic with respect to magnitude. However, directly incorpor…
LipSSM: Structurally Lipschitz-Bounded Cascaded State-Space Model via Metric Transfer between Consecutive SSM Layers
Natsuki Yoshino, Ren Uchida, Kazuki Matsumoto +1
Lipschitz continuity is a fundamental principle in the design of certifiably robust deep neural networks (DNNs), wherein adjusting the Lipschitz constant, which quantifies network…
LipsAM: Lipschitz-continuous Neural Networks for Convergent Plug-and-Play Audio Signal Recovery
Kazuki Matsumoto, Ren Uchida, Natsuki Yoshino +1
The Lipschitz continuity of deep neural networks (DNNs) is essential for establishing theoretical guarantees regarding their behavior. From both theoretical and practical perspecti…
PolarBM: Complex-valued Boltzmann Machine for Modeling Audio Signals in Polar and Log-polar Coordinates
Toru Nakashika, Kohei Yatabe
Although vast amounts of data, such as audio signal spectra, are naturally represented using complex numbers, conventional machine learning methods often simplify complex-domain pr…
LipsAM: Lipschitz-Continuous Amplitude Modifier for Audio Signal Processing and its Application to Plug-and-Play Dereverberation
Kazuki Matsumoto, Ren Uchida, Kohei Yatabe
The robustness of deep neural networks (DNNs) can be certified through their Lipschitz continuity, which has made the construction of Lipschitz-continuous DNNs an active research f…
Learn and Verify: A Framework for Rigorous Verification of Physics-Informed Neural Networks
Kazuaki Tanaka, Kohei Yatabe
The numerical solution of differential equations using neural networks has become a central topic in scientific computing, with Physics-Informed Neural Networks (PINNs) emerging as…
Dissecting Performance Degradation in Audio Source Separation under Sampling Frequency Mismatch
Kanami Imamura, Tomohiko Nakamura, Kohei Yatabe +1
Audio processing methods based on deep neural networks are typically trained at a single sampling frequency (SF). To handle untrained SFs, signal resampling is commonly employed, b…
Local Equivariance Error-Based Metrics for Evaluating Sampling-Frequency-Independent Property of Neural Network
Kanami Imamura, Tomohiko Nakamura, Norihiro Takamune +2
Audio signal processing methods based on deep neural networks (DNNs) are typically trained only at a single sampling frequency (SF) and therefore require signal resampling to handl…
Subband Splitting: Simple, Efficient and Effective Technique for Solving Block Permutation Problem in Determined Blind Source Separation
Kazuki Matsumoto, Kohei Yatabe
Solving the permutation problem is essential for determined blind source separation (BSS). Existing methods, such as independent vector analysis (IVA) and independent low-rank matr…