DeepFilterNet: Perceptually Motivated Real-Time Speech Enhancement

2023/05/14 by Hendrik Schröter, Tobias Rosenkranz, Schröter, Hendrik +5 · 8 citations
Computer Science · Engineering · Health Professions · #Advanced Adaptive Filtering Techniques #Audio and Speech Processing (eess.AS) #Computation and Language (cs.CL) #FOS: Computer and information sciences #FOS: Electrical engineering #Infant Health and Development #Sound (cs.SD) #Speech and Audio Processing #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2305.08227

openalex publication_date 2023/05/14 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Multi-frame algorithms for single-channel speech enhancement are able to take advantage from short-time correlations within the speech signal. Deep Filtering (DF) was proposed to directly estimate a complex filter in frequency domain to take advantage of these correlations. In this work, we present a real-time speech enhancement demo using DeepFilterNet. DeepFilterNet's efficiency is enabled by exploiting domain knowledge of speech production and psychoacoustic perception. Our model is able to match state-of-the-art speech enhancement benchmarks while achieving a real-time-factor of 0.19 on a single threaded notebook CPU. The framework as well as pretrained weights have been published under an open source license.

Cited by

• Real-Time Streamable Generative Speech Restoration with Flow Matching
• DPDFNet: Boosting DeepFilterNet2 via Dual-Path RNN
• The CCF AATC 2025 Speech Restoration Challenge: A Retrospective
• Lightweight DNN for Full-Band Speech Denoising on Mobile Devices: Exploiting Long and Short Temporal Patterns
• Lightweight speech enhancement guided target speech extraction in noisy multi-speaker scenarios
• A Framework for Robust Speaker Verification in Highly Noisy Environments Leveraging Both Noisy and Enhanced Audio
• A Data-Centric Framework for Addressing Phonetic and Prosodic Challenges in Russian Speech Generative Models
• MB-RIRs: a Synthetic Room Impulse Response Dataset with Frequency-Dependent Absorption Coefficients

Related

• DeepFilterNet2: Towards Real-Time Speech Enhancement on Embedded Devices for Full-Band Audio
• DeepFilterNet: A Low Complexity Speech Enhancement Framework for Full-Band Audio based on Deep Filtering
• A Two-Stage Hierarchical Deep Filtering Framework for Real-Time Speech Enhancement
• DPDFNet: Boosting DeepFilterNet2 via Dual-Path RNN
• A Perceptually-Motivated Approach for Low-Complexity, Real-Time\n Enhancement of Fullband Speech