Accentize DeRoom vs DPDFNet

Accentize DeRoom is a machine-learning audio plugin for reducing reverb and room resonances in recordings. It is intended to improve speech quality and intelligibility when reflections and echoes affect a recording. Its neural network distinguishes direct sound from reflections, detects reverb tails and echoes, and suppresses them. DeRoom estimates room timing constants automatically; the user chooses the reduction amount. The standard license includes reverb removal and room resonance suppression. DeRoom Pro adds spectral focus, attack and release controls, reverb-only monitoring, separate left and right processing, and spectrogram and gain visualization. Both versions support mono and stereo audio in VST3, AU, and AAX formats, with listed hosts including Pro Tools, Cubase, Nuendo, Reaper, Ableton Live, Logic Pro, Adobe Premiere, Final Cut, and DaVinci Resolve. DeRoom runs locally, and its serial-key license works offline. Pro uses iLok and requires a free iLok account. The software runs on macOS and Windows. DeRoom costs €49, paid once; DeRoom Pro costs €249, paid once. A seven-day free trial is offered.

DPDFNet is a free, open-source model for reducing noise in single-channel speech from recordings, live streams, and edge-device applications. It supports offline processing and streaming, and extends DeepFilterNet2 with dual-path encoder blocks and an always-on fine-tuning approach intended to reduce over-attenuation. Pretrained variants support 8, 16, and 48 kHz audio. The repository includes PyTorch code and ONNX and TFLite inference models, with command-line, Python, and stateful streaming interfaces. Streaming buffers about 20 ms before the first enhanced output, then adds about 10 ms of delay for later blocks. A hosted Gradio demo and audio examples are linked from the project page. Listed community integrations include sherpa-onnx, OBS Studio, VST3 and LADSPA plugins, Core ML ports, and WebAssembly. The project page reports real-time DPDFNet-4 deployment on Ceva-NeuPro-Nano edge NPUs in a benchmark setup using int8 weights and int16 activations. The software is under Apache License 2.0. Model files are not bundled in the source repository; it provides commands to download checkpoints and ONNX or TFLite models from Hugging Face.