REVIEW 4 cited by
Hybrid Spectrogram and Waveform Source Separation
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Source separation models either work on the spectrogram or waveform domain. In this work, we show how to perform end-to-end hybrid source separation, letting the model decide which domain is best suited for each source, and even combining both. The proposed hybrid version of the Demucs architecture won the Music Demixing Challenge 2021 organized by Sony. This architecture also comes with additional improvements, such as compressed residual branches, local attention or singular value regularization. Overall, a 1.4 dB improvement of the Signal-To-Distortion (SDR) was observed across all sources as measured on the MusDB HQ dataset, an improvement confirmed by human subjective evaluation, with an overall quality rated at 2.83 out of 5 (2.36 for the non hybrid Demucs), and absence of contamination at 3.04 (against 2.37 for the non hybrid Demucs and 2.44 for the second ranking model submitted at the competition).
Forward citations
Cited by 4 Pith papers
-
Making Separation-First Multi-Stream Audio Watermarking Feasible via Joint Training
Jointly training the watermark embedder/detector with the source separator enables ~1% bit-error-rate recovery of per-stem watermarks after mixing and separation, where independent training yields 15–35%.
-
Improving French Synthetic Speech Quality via SSML Prosody Control
Two fine-tuned LLMs predict SSML prosody tags that raise French TTS naturalness from a 3.20 to 3.87 MOS.
-
Fx-Encoder++: Extracting Instrument-Wise Audio Effects Representations from Mixtures
A contrastive-learning model, Fx-Encoder++, extracts per-instrument audio effects embeddings directly from music mixtures using audio or text queries, outperforming prior effects encoders at the mixture level.
-
Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform
A unified differentiable STFT lets gradient descent tune the window and hop lengths, improving time-frequency readability and slightly boosting a classifier's accuracy on held-out data.
Discussion (0). Continue with ORCID to comment.