Go to ACL ARR 2025 July homepageCIS-BWE: Chaos-Informed Speech Bandwidth Extension
Abstract: Recovery of high-frequency components lost due to bandwidth constraints is critical for Text-To-Speech and Automatic Speech Recognition applications. We design CIS-BWE, a novel adversarial Bandwidth Extension (BWE) framework that introduces two chaos-informed discriminators - Multi-Resolution Lyapunov Discriminator (MRLD) and Multi-Scale Detrended Fractal Analysis Discriminator (MSDFA) - for capturing the deterministic chaos from speech. MRLD exploits Lyapunov exponents to capture nonlinear chaotic fluctuations. MSDFA exploits detrended fluctuation analysis to quantify fractal-like, long-range temporal chaotic correlations. To the best of our knowledge, MRLD and MSDFA are included here for the first time with a complex-valued adversarial network to explore the chaotic study of speech reconstruction. We also introduce a novel complex-valued and
dual-stream generator, which uses our newly proposed ConformerNeXt as a core block with Lattice interactions, acting as a gating mechanism by enabling controlled mixing of information across streams. We extensively optimize our design across five resolutions and use depth-wise separable convolutions to make our model lightweight yet powerful. Our CIS-BWE requires a 40x reduction in discriminator size, overall 0.5x fewer parameters, and results in better performance across a total of eight subjective and objective evaluation metrics, establishing a new baseline in the BWE task.
Paper Type: Long
Research Area: Speech Recognition, Text-to-Speech and Spoken Language Understanding
Research Area Keywords: speech technologies, spoken language understanding
Contribution Types: NLP engineering experiment, Approaches to low-resource settings
Languages Studied: English
Submission Number: 877
Loading