Papers for

audio device manufacturers

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Real-time music source separation runs efficiently on low-power audio DSP

Real-Time Music Source Separation on a Low-Power Audio DSP

Abstract: Real-time music source separation is validated on desktop CPUs and GPUs. Does any published system fit the embedded audio hardware it targets? On a commercial audio DSP (2 MB SRAM, 2.07 GMAC/s measured), none does, and the constraints eliminate different models: memory rules out the 16-51 M parameter TasNet/X-UMX family, per-frame compute rules out RT-STT, needing 5.5x the available MAC rate. Parameter count predicts neither: weight reuse spans 1x to 345x. We then build one that fits. Training on continuous rather than block-padded convolution context proves essential: a model scoring 3.93 dB block-wise otherwise collapses to silence within 2 s frame-by-frame. A gated complex FIR deep filter adds a latency knob, gaining 0.38 dB even when strictly causal. It reaches 4.70 dB cSDR on MUSDB18-HQ and runs in 10.43 ms of an 11.6 ms hop, 0.5-0.7 dB behind systems that do not fit.

Thu 10 SeptSound

The gist

Separating different sounds from a music mix in real time usually needs powerful computers, but the authors show how to do it on a small, low-power audio processor. They found existing methods don’t fit the strict memory and speed limits of typical audio hardware. By changing how the model is trained and adding a new filter that controls delay, they made a system that works quickly and nearly as well as bigger setups. This opens the door for better music processing in small devices.

Open → 2609.12201v1

Speech replay attack detection adapts to changing environments over time

Domain-Incremental Learning for Multi-Channel Replay Speech Detection

Abstract: Replay attacks are the most accessible threat to voice-controlled systems, and the acoustic cues that expose them are strongly modulated by the environment in which the attack is mounted. A detector deployed in the field therefore has to absorb new acoustic conditions over time, ideally without revisiting past recordings, since retaining speech indefinitely is both expensive and legally constrained. We frame this as Domain-Incremental Learning (DIL) over acoustic environments and present the first continual learning benchmark for multi-channel replay speech detection, evaluating a state-of-the-art beamformer-based detector over all 24 environment orderings of the ReMASC corpus with five seeds. Sequential fine-tuning forgets severely, raising the error rate on previously learned environments by 18.8 points. Elastic weight consolidation (EWC) halves forgetting but loses plasticity, gradient projection memory (GPM) is statistically indistinguishable from naive fine-tuning, and the proposed task-specific beamformer (TSB) that keeps one spatial front-end per environment significantly improves final and incremental accuracy. We further show that the last environment of the sequence dominates final performance. Code, results, and analysis are available at https://github.com/michaelneri/replay-speech-continual.

Thu 10 SeptCryptography and SecuritySound

The gist

Replay attacks trick voice-controlled systems by playing back recorded speech, and detecting these attacks is harder because different rooms and places change how the sound is heard. The authors looked at how to make a detector learn to recognize these attacks in many different acoustic settings one after another without needing to keep all old recordings. They found that simply retraining forgets old environments quite badly, but using special methods that keep separate sound filters for each environment helps the detector remember better and perform more accurately. Their work tested this idea across many orders of environments, showing that the last place learned has a big impact on how well the detector works.

Open → 2609.11194v1