Mixed-Precision Information Bottlenecks for On-Device Trait-State Disentanglement in Bipolar Agitation Detection

• URL: http://arxiv.org/abs/2605.03039v1
• Date: Mon, 04 May 2026 18:06:17 GMT
• Title: Mixed-Precision Information Bottlenecks for On-Device Trait-State Disentanglement in Bipolar Agitation Detection
• Abstract summary: MP-IB is the first framework to treat mixed-precision quantization as an information bottleneck for clinical trait-state separation.<n>On Bridge2AI-Voice (N=833, 4 sessions/participant, strict speaker-independent CV), MPIB rho = 0.117 (95% CI: [0.089, 0.145 vs. chance], p3 vs. chance)<n>End-to-end latency is 23.4 ms with a 617 KB footprint, enabling real-time monitoring on sub 20 dollar devices.
• Score: 3.252472808549431
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Continuous monitoring of bipolar disorder agitation via voice biomarkers requires disentangling stable speaker traits from volatile affective states on resource-constrained edge devices. We introduce MP-IB, the first framework to treat mixed-precision quantization as an information bottleneck for clinical trait-state separation. The core insight is that numerical precision itself controls capacity: an FP16 trait head (1,024 bits) encodes speaker identity, while an INT4 state head (128 bits) captures agitation, yielding 8x information asymmetry without adversarial training. We augment this with Dynamic Precision Scheduling and Multi-Scale Temporal Fusion. On Bridge2AI-Voice (N=833, 4 sessions/participant, strict speaker-independent CV), MP-IB achieves rho = 0.117 (95\% CI: [0.089, 0.145], p=0.003 vs. chance), outperforming 94M-parameter WavLM-Adapter with in-domain SSL continuation (rho = -0.042), beta VAE disentanglement (rho = 0.089), and hand-crafted prosody (rho = 0.031) by 2.8--15.9 points absolute. Zero-shot transfer to CREMA-D achieves AUC=0.817. Identity leakage is suppressed to near-random (EER=0.42, MIA-AUC=0.52). End-to-end latency is 23.4 ms with a 617 KB footprint, enabling real-time monitoring on sub 20 dollar devices.

Related papers

• Low-Power, Neuromorphic, Acoustic Anomaly Detection for Persistent Machine Monitoring [0.5586300501966862]
  We demonstrate autoencoder-based acoustic anomaly detection on an Intel Loihi 2 processor under clean and noisy conditions.<n>Results support both neuromorphic acoustic anomaly detection as a practical candidate for low-power, sample orders machine monitoring.
  arXiv  Detail & Related papers  (2026-08-18T21:46:11Z)
• Omni2LoRA: Coherence-Preserving Parametric Memory for Efficient Omni Language Models [65.49950267695267]
  We introduce Omni2LoRA, a framework for efficient parametric memory compression via coherence-preserving context distillation.<n>By converting multimodal memory into a fixed-budget, reusable parameter state, our method drives answer-time multimodal-token load to zero.
  arXiv  Detail & Related papers  (2026-08-10T07:49:10Z)
• VibeVoice-ASR-BitNet Technical Report [86.93881874028209]
  VibeVoice-ASR-BitNet is a compressed variant of VibeVoice-ASR optimized for real-time inference on edge CPUs.<n>We implement a progressive quantization-aware training strategy to preserve accuracy under aggressive compression.<n> VibeVoice-ASR-BitNet is 1.6-2.3x faster than Whisper at comparable model sizes.
  arXiv  Detail & Related papers  (2026-07-23T09:08:04Z)
• Intrinsic-Noise Consolidation: A Doob-Barrier-Conditioned Diffusion Turns Analog Device Noise into a Continual-Learning Resource [0.0]
  On analog neuromorphic hardware, intrinsic device noise is normally an accuracy tax.<n>On single-head Split-MNIST (8 seeds) rule lifts retention 10.9 points at an optimum interior.<n>We measure the intrinsic noise on real BrainScaleS-2 (additive, trial-to-trial independent, tunable via on-chip averaging) and run the rule on chip with its noise in the training loop.
  arXiv  Detail & Related papers  (2026-07-08T02:38:02Z)
• Acquisition state behaves as a structured, measurable variable governing lung-nodule AI: kernel-driven measurement instability and noise-driven detection fragility, invisible to DICOM metadata [0.0]
  The 2026 ACR-SIIM Practice recommends local acceptance testing and ongoing drift monitoring.<n>We argue that a necessary, currently unmonitored layer sits beneath output metrics: whether incoming studies remain within the acquisition envelope a model was validated on.
  arXiv  Detail & Related papers  (2026-06-11T02:38:37Z)
• Asymmetric Phase Coding Audio Watermarking [7.627186551029829]
  Deepfake audio challenges voice-based authentication systems.<n>We propose Asymmetric Phase Coding, a training-free cryptographic signing layer for audio.<n>We achieve cryptographic verification rates between 97.5% and 98.3% on every condition at meanQ.02 and tens-of-milliseconds latency.
  arXiv  Detail & Related papers  (2026-05-08T04:54:59Z)
• CAWN: Continuous Acoustic Wave Networks for Autoregressive Language Modeling [46.16066322190728]
  We introduce the Continuous Acoustic Wave Network (CAWN), a fully continuous sequence-mixing architecture.<n>Instead of discrete matrix-based attention, CAWN projects hidden states into multi-headed complex-domain phasors.<n>To prevent signal degradation over ultra-long contexts, we introduce a dual-gated Selective Phase Resonance mechanism.
  arXiv  Detail & Related papers  (2026-04-05T20:13:22Z)
• From Black Box to Glass Box: Cross-Model ASR Disagreement to Prioto Review in Ambient AI Scribe Documentation [43.148402136307716]
  Cross-model disagreement among heterogeneous ASR systems can act as a reference-free uncertainty signal.<n>We transcribed 50 publicly available medical audio clips with eight ASR systems spanning commercial APIs and open-source engines.<n>Low-agreement regions were enriched for content disagreements, with the content fraction increasing from 53.9% to 73.9% across quintiles of high-risk mass.
  arXiv  Detail & Related papers  (2026-03-02T13:02:13Z)
• Reliable Audio Deepfake Detection in Variable Conditions via Quantum-Kernel SVMs [0.0]
  We show that using a quantum kernel in audio deepfake detection reduces falsepositive rates without increasing model size.<n>We compare quantum-kernel SVMs with classical SVMs using identical mel-spectrogram preprocessing.<n> QSVMs achieve consistently lower equalerror rates (EER): 0.183 vs. 0.299 on ASVspoof 5 (2024), 0.081 vs. 0.188 on ADD23, and 0.346 vs. 0.399 on ASVspoof 2019, and 0.355 vs. 0.413 In-the-Wild.
  arXiv  Detail & Related papers  (2025-12-21T16:31:05Z)
• Uncertainty Makes It Stable: Curiosity-Driven Quantized Mixture-of-Experts [6.221156050218661]
  We present a curiosity-driven quantized Mixture-of-Experts framework for deep neural networks on resource-constrained devices.<n>Our 4-bit quantization maintains 99.9 percent of 16-bit accuracy (0.858 vs 0.859 F1) with 4x compression and 41 percent energy savings.<n>Our information-theoretic routing demonstrates that adaptive quantization yields accurate (0.858 F1, 1.2M params), energy-efficient (3.87 F1/mJ), and predictable edge models.
  arXiv  Detail & Related papers  (2025-11-13T15:32:41Z)
• Enhancing Kerr-Cat Qubit Coherence with Controlled Dissipation [64.05054054401175]
  Kerr-cat qubit (KCQ) is a bosonic quantum processor.<n>KCQs are experimentally compatible with on-chip architectures and high-fidelity operations.<n>We present direct evidence that the bit-flip time in a KCQ is limited by leakage out of the qubit manifold.
  arXiv  Detail & Related papers  (2025-11-02T17:58:36Z)
• U-Mamba2-SSL for Semi-Supervised Tooth and Pulp Segmentation in CBCT [44.3806898357896]
  We propose U-Mamba2-SSL, a novel semi-supervised learning framework that builds on the U-Mamba2 model and employs a multi-stage training strategy.<n>U-Mamba2-SSL achieved an average score of 0.789 and a DSC of 0.917 on the hidden test set, achieving first place in Task 1 of the STSR 2025 challenge.
  arXiv  Detail & Related papers  (2025-09-24T14:19:33Z)
• Cross-Attention with Confidence Weighting for Multi-Channel Audio Alignment [5.380078543698624]
  Multi-channel audio alignment is a key requirement in bioacoustic monitoring, spatial audio systems, and acoustic localization.<n>We introduce a method that combines cross-attention mechanisms with confidence-weighted scoring to improve multi-channel audio synchronization.<n>Our method achieved first place in the BioDCASE 2025 Task 1 challenge with 0.30 MSE average across test datasets, compared to 0.58 for the deep learning baseline.
  arXiv  Detail & Related papers  (2025-09-21T05:14:06Z)
• Quantum-Inspired Audio Unlearning: Towards Privacy-Preserving Voice Biometrics [44.60499998155848]
  QPAudioEraser is a quantum-inspired audio unlearning framework.<n>It consistently surpasses conventional baselines across single-class, multi-class, sequential, and accent-level erasure scenarios.
  arXiv  Detail & Related papers  (2025-07-29T20:12:24Z)
• Raw Waveform Encoder with Multi-Scale Globally Attentive Locally Recurrent Networks for End-to-End Speech Recognition [45.858039215825656]
  We propose a new encoder that adopts globally attentive locally recurrent (GALR) networks and directly takes raw waveform as input. Experiments are conducted on a benchmark dataset AISHELL-2 and two large-scale Mandarin speech corpus of 5,000 hours and 21,000 hours.
  arXiv  Detail & Related papers  (2021-06-08T12:12:33Z)
• Near-degenerate quadrature-squeezed vacuum generation on a silicon-nitride chip [54.87128096861778]
  In this Letter, we demonstrate the generation of quadrature-phase squeezed states in the radio-frequency carrier sideband using a small-footprint silicon-nitride microresonator with a dual-pumped four-wave-mixing process. It is critical to account for the nonlinear behavior of the pump fields to properly predict the squeezing that can be generated in this system.
  arXiv  Detail & Related papers  (2020-02-04T01:41:41Z)

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.