{"ID":2880266,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.14709","arxiv_id":"2508.14709","title":"Improving Resource-Efficient Speech Enhancement via Neural Differentiable DSP Vocoder Refinement","abstract":"Deploying speech enhancement (SE) systems in wearable devices, such as smart glasses, is challenging due to the limited computational resources on the device. Although deep learning methods have achieved high-quality results, their computational cost limits their feasibility on embedded platforms. This work presents an efficient end-to-end SE framework that leverages a Differentiable Digital Signal Processing (DDSP) vocoder for high-quality speech synthesis. First, a compact neural network predicts enhanced acoustic features from noisy speech: spectral envelope, fundamental frequency (F0), and periodicity. These features are fed into the DDSP vocoder to synthesize the enhanced waveform. The system is trained end-to-end with STFT and adversarial losses, enabling direct optimization at the feature and waveform levels. Experimental results show that our method improves intelligibility and quality by 4% (STOI) and 19% (DNSMOS) over strong baselines without significantly increasing computation, making it well-suited for real-time applications.","short_abstract":"Deploying speech enhancement (SE) systems in wearable devices, such as smart glasses, is challenging due to the limited computational resources on the device. Although deep learning methods have achieved high-quality results, their computational cost limits their feasibility on embedded platforms. This work presents an...","url_abs":"https://arxiv.org/abs/2508.14709","url_pdf":"https://arxiv.org/pdf/2508.14709v1","authors":"[\"Heitor R. Guimarães\",\"Ke Tan\",\"Juan Azcarreta\",\"Jesus Alvarez\",\"Prabhav Agrawal\",\"Ashutosh Pandey\",\"Buye Xu\"]","published":"2025-08-20T13:36:28Z","proceeding":"eess.AS","tasks":"[\"eess.AS\",\"cs.SD\"]","methods":"[]","has_code":false}