Domain-Incremental Learning for Multi-Channel Replay Speech Detection

• URL: http://arxiv.org/abs/2609.11194v1
• Date: Thu, 10 Sep 2026 08:03:02 GMT
• Title: Domain-Incremental Learning for Multi-Channel Replay Speech Detection
• Abstract summary: We present the first continual learning benchmark for multi-channel replay speech detection.<n>We evaluate a state-of-the-art beamformer-based detector over all 24 environment orderings of the ReMASC corpus with five seeds.<n>We show that the last environment of the sequence dominates final performance.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• MAST: Label-Efficient, Robust, and Generalizable Sound Detection for Biodiversity Monitoring via Masked Audio Pretraining and Self-Training [7.983925207958734]
  Time-frequency annotation of animal vocalizations is expensive, site-specific, and difficult to sustain at scale.<n>We present a label-efficient sound detection framework that combines masked audio pretraining with a lightweight detector on mel spectrograms.<n>We evaluate the performance on two ecologically distinct domains: tropical rainforest soundscapes (Indonesia) and bird vocalizations in Mediterranean habitats (Spain)
  arXiv  Detail & Related papers  (2026-09-14T08:41:23Z)
• Adaptive Perturbation Selection for Contrastive Audio Decoding [17.576102240052503]
  Large audio-language models (LALMs) frequently hallucinate by overriding acoustic evidence with language priors.<n>While contrastive decoding (CD) offers training-free mitigation, existing methods rely on blunt perturbations like masking or noise.<n>We explore this design space by evaluating a diverse library of targeted audio perturbations and adaptively selecting the optimal negative branch for each task.
  arXiv  Detail & Related papers  (2026-06-30T22:55:22Z)
• BEST-RQ-2: Contextualize-Then-Predict, a Two-Step Approach for Self-Supervised Audio Representations [9.030040918514464]
  BEST-RQ-2 is an evolution of BEST-RQ that retains frozen randomprojection-based discrete targets while introducing a two-step contextualize-then-predict pretraining scheme.<n>A ViT context encoder processes only the unmasked spectrogram regions, and a lightweight predictor infers targets for the masked regions.<n>On the X-ARES and XARES-LLM benchmarks, BEST-RQ-2 consistently outperforms one-stage baselines in overall transfer.
  arXiv  Detail & Related papers  (2026-06-29T09:52:43Z)
• ANCHOR: Autoregressive Non-intrusive Chunk-Ordered Refinement for Joint Multi-Resolution Speech Quality Modeling [62.983372215479925]
  Streaming and generative systems require incremental estimation from partial audio.<n>We propose ANCHOR, reformulating incremental assessment as a multi-resolution autore task.<n> Experiments show substantial robustness under partial input, including a 48% PLCMOS error reduction on 2-second prefixes.
  arXiv  Detail & Related papers  (2026-06-08T22:46:30Z)
• EchoPilot: Training-Free Ultrasound Video Segmentation via Scale-Space Semantic Prompting and Reliability-Gated Memory [30.279337577859597]
  EchoPilot is a training-free framework for ultrasound video segmentation under sparse first-frame interaction.<n>It orchestrates a frozen medical vision-language model for semantic localization, a vision foundation model for dense geometric feature extraction, and a promptable video segmentor for mask prediction and propagation.<n>We present the first dynamic fetal placenta ultrasound video segmentation dataset with 671 annotated frames.
  arXiv  Detail & Related papers  (2026-05-25T15:22:05Z)
• PACE: Pretrained Audio Continual Learning [27.605574463021693]
  We present the first systematic benchmark for audio continual learning (CL) with pretrained models (PTMs)<n>In addition, we introduce spectrogram-based boundary-aware perturbations to mitigate representation overlap and improve stability.<n>Experiments on six diverse audio CL benchmarks demonstrate that PACE substantially outperforms state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-02-03T10:28:35Z)
• Learning Robust Spatial Representations from Binaural Audio through Feature Distillation [64.36563387033921]
  We investigate the use of a pretraining stage based on feature distillation to learn a robust spatial representation of speech without the need for data labels.<n>Our experiments demonstrate that the pretrained models show improved performance in noisy and reverberant environments.
  arXiv  Detail & Related papers  (2025-08-28T15:43:15Z)
• High-Fidelity Speech Synthesis with Minimal Supervision: All Using Diffusion Models [56.00939852727501]
  Minimally-supervised speech synthesis decouples TTS by combining two types of discrete speech representations. Non-autoregressive framework enhances controllability, and duration diffusion model enables diversified prosodic expression.
  arXiv  Detail & Related papers  (2023-09-27T09:27:03Z)
• TranSpeech: Speech-to-Speech Translation With Bilateral Perturbation [61.564874831498145]
  TranSpeech is a speech-to-speech translation model with bilateral perturbation. We establish a non-autoregressive S2ST technique, which repeatedly masks and predicts unit choices. TranSpeech shows a significant improvement in inference latency, enabling speedup up to 21.4x than autoregressive technique.
  arXiv  Detail & Related papers  (2022-05-25T06:34:14Z)
• Data Augmentation based Consistency Contrastive Pre-training for Automatic Speech Recognition [18.303072203996347]
  Self-supervised acoustic pre-training has achieved amazing results on the automatic speech recognition (ASR) task. Most of the successful acoustic pre-training methods use contrastive learning to learn the acoustic representations. In this letter, we design a novel consistency contrastive learning (CCL) method by utilizing data augmentation for acoustic pre-training.
  arXiv  Detail & Related papers  (2021-12-23T13:23:17Z)
• Cross-domain Adaptation with Discrepancy Minimization for Text-independent Forensic Speaker Verification [61.54074498090374]
  This study introduces a CRSS-Forensics audio dataset collected in multiple acoustic environments. We pre-train a CNN-based network using the VoxCeleb data, followed by an approach which fine-tunes part of the high-level network layers with clean speech from CRSS-Forensics.
  arXiv  Detail & Related papers  (2020-09-05T02:54:33Z)
• Temporal-Spatial Neural Filter: Direction Informed End-to-End Multi-channel Target Speech Separation [66.46123655365113]
  Target speech separation refers to extracting the target speaker's speech from mixed signals. Two main challenges are the complex acoustic environment and the real-time processing requirement. We propose a temporal-spatial neural filter, which directly estimates the target speech waveform from multi-speaker mixture.
  arXiv  Detail & Related papers  (2020-01-02T11:12:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.