Download Fast Signal Reconstruction from Magnitude Spectrogram of Continuous Wavelet Transform Based on Spectrogram Consistency The continuous wavelet transform (CWT) can be seen as a filterbank having logarithmic frequency subbands spacing similar to the human auditory system. Thus, to make computers imitate the significant functions of the human auditory system, one promising approach would be to model, analyze and process magnitude spectrograms given by the CWT. To realize this approach, we must be able to convert a processed or modified magnitude CWT spectrogram, which contains no information about the phase, into a time domain signal specifically for those applications in which the aim is to generate audio signals. To this end, this paper proposes a fast algorithm for estimating the phase from a given magnitude CWT spectrogram to reconstruct an audio signal. The experimental results revealed that the proposed algorithm was around 100 times faster than a conventional algorithm, while the reconstructed signals obtained with the proposed algorithm had almost the same audio quality as those obtained with the previous study.
Download Hyperbolic Embeddings for Order-Aware Classification of Audio Effect Chains Audio effects (AFXs) are essential tools in music production, frequently applied in chains to shape timbre and dynamics. The order of AFXs in a chain plays a crucial role in determining the final sound, particularly when non-linear (e.g., distortion) or timevariant (e.g., chorus) processors are involved. Despite its importance, most AFX-related studies have primarily focused on estimating effect types and their parameters from a wet signal. To
address this gap, we formulate AFX chain recognition as the task
of jointly estimating AFX types and their order from a wet signal.
We propose a neural-network-based method that embeds wet signals into a hyperbolic space and classifies their AFX chains. Hyperbolic space can represent tree-structured data more efficiently
than Euclidean space due to its exponential expansion property.
Since AFX chains can be represented as trees, with AFXs as nodes
and edges encoding effect order, hyperbolic space is well-suited
for modeling the exponentially growing and non-commutative nature of ordered AFX combinations, where changes in effect order can result in different final sounds. Experiments using guitar
sounds demonstrate that, with an appropriate curvature, the proposed method outperforms its Euclidean counterpart. Further analysis based on AFX type and chain length highlights the effectiveness of the proposed method in capturing AFX order.