.png){kind=icon}
Return
Quantized Generative Autoencoder for Audio Spectrograms
.png){kind=icon}
PRE
AI
DOI：10.1109/LES.2025.3575372.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This study analyzes techniques for compressing generative autoencoders (AEs) to enable their deployment on resource-constrained devices, addressing the challenges and optimizations required for such environments. As a case study, we present a quantized generative AE optimized for efficiently generating underwater sound spectrograms. The model is evaluated across diverse scenarios, demonstrating its ability to produce low-dimensional spectrograms while adapting to various acoustic conditions. The hardware optimization process focuses on balancing computational efficiency and model accuracy, ensuring performance comparable to its nonquantized counterpart.
Keywords:
Autoencoders
Training
Computational modeling
Spectrogram
Hardware
Computer architecture
Adaptation models
Accuracy
Data models
Quantization (signal)
Fixed-point
generative autoencoder (AE)
hardware
optimization
pruning
quantization
spectrograms
transfer learning (TL)
Journal
IF:
2
Papers:
101
Citations:
696
Organization
Cited Papers
Espectrogramas de registros de Ballenas Barbadas sintetizados a partir de arquitecturas de Autoenconders: CAE, VAE y CAE-LSTM.png)
Elektron
ElektronIF0
PREAI
ShareSaveShareSaveShareSave
ShareSave no more
no more