Private Speech Classification without Collapse: Stabilized DP Training and Offline Distillation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wen, Yadi, Li, Tianxin, Liang, Enji, Du, Rong, Fu, Yue
Format:	Preprint
Published:	2026
Subjects:	Sound Multimedia
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

ZO-ASR: Zeroth-Order Fine-Tuning of Speech Foundation Models without Back-Propagation
by: Peng, Yuezhang, et al.
Published: (2025)

Period-conscious Time-series Reconstruction under Local Differential Privacy
by: Wang, Yaxuan, et al.
Published: (2026)

Efficient Speech Watermarking for Speech Synthesis via Progressive Knowledge Distillation
by: Cui, Yang, et al.
Published: (2025)

HDA-SELD: Hierarchical Cross-Modal Distillation with Multi-Level Data Augmentation for Low-Resource Audio-Visual Sound Event Localization and Detection
by: Wang, Qing, et al.
Published: (2025)

STCTS: Generative Semantic Compression for Ultra-Low Bitrate Speech via Explicit Text-Prosody-Timbre Decomposition
by: Wang, Siyu, et al.
Published: (2025)

Towards Controllable Speech Synthesis in the Era of Large Language Models: A Systematic Survey
by: Xie, Tianxin, et al.
Published: (2024)

Can We Hear from Events? Generating Speech from Event Camera
by: Fang, Jingping, et al.
Published: (2026)

DreamFoley: Scalable VLMs for High-Fidelity Video-to-Audio Generation
by: Li, Fu, et al.
Published: (2025)

Soundscapes in Spectrograms: Pioneering Multilabel Classification for South Asian Sounds
by: Chakrabarty, Sudip, et al.
Published: (2026)

MoLEx: Mixture of LoRA Experts in Speech Self-Supervised Models for Audio Deepfake Detection
by: Pan, Zihan, et al.
Published: (2025)

Improving Speech Enhancement by Integrating Inter-Channel and Band Features with Dual-branch Conformer
by: Li, Jizhen, et al.
Published: (2024)

MoTAS: MoE-Guided Feature Selection from TTS-Augmented Speech for Enhanced Multimodal Alzheimer's Early Screening
by: Shao, Yongqi, et al.
Published: (2025)

Dopamine Audiobook: A Training-free MLLM Agent for Emotional and Immersive Audiobook Generation
by: Rong, Yan, et al.
Published: (2025)

Delayed Commitment for Representation Readiness in Stage-wise Audio-Visual Learning
by: Xu, Xinmeng, et al.
Published: (2026)

Enkidu: Universal Frequential Perturbation for Real-Time Audio Privacy Protection against Voice Deepfakes
by: Feng, Zhou, et al.
Published: (2025)

CEM-Net: Cross-Emotion Memory Network for Emotional Talking Face Generation
by: Wu, Kangyi, et al.
Published: (2025)

S-PRESSO: Ultra Low Bitrate Sound Effect Compression With Diffusion Autoencoders And Offline Quantization
by: Lahrichi, Zineb, et al.
Published: (2026)

Enhancing Automatic Chord Recognition via Pseudo-Labeling and Knowledge Distillation
by: Phan, Nghia, et al.
Published: (2026)

Pianist Transformer: Towards Expressive Piano Performance Rendering via Scalable Self-Supervised Pre-Training
by: You, Hong-Jie, et al.
Published: (2025)

3MDiT: Unified Tri-Modal Diffusion Transformer for Text-Driven Synchronized Audio-Video Generation
by: Li, Yaoru, et al.
Published: (2025)

SLAM-LLM: A Modular, Open-Source Multimodal Large Language Model Framework and Best Practice for Speech, Language, Audio and Music Processing
by: Ma, Ziyang, et al.
Published: (2026)

Low-latency Speech Enhancement via Speech Token Generation
by: Xue, Huaying, et al.
Published: (2023)

SonicGauss: Position-Aware Physical Sound Synthesis for 3D Gaussian Representations
by: Wang, Chunshi, et al.
Published: (2025)

MeMo: Attentional Momentum for Real-time Audio-visual Speaker Extraction under Impaired Visual Conditions
by: Li, Junjie, et al.
Published: (2025)

Uncertainty-Aware 3D Emotional Talking Face Synthesis with Emotion Prior Distillation
by: Shen, Nanhan, et al.
Published: (2026)

A Distribution Matching Approach to Neural Piano Transcription with Optimal Transport
by: Wei, Weixing, et al.
Published: (2026)

Multimodal Emotion Recognition from Raw Audio with Sinc-convolution
by: Zhang, Xiaohui, et al.
Published: (2024)

CLAIP-Emo: Parameter-Efficient Adaptation of Language-supervised models for In-the-Wild Audiovisual Emotion Recognition
by: Chen, Yin, et al.
Published: (2025)

Speech-to-See: End-to-End Speech-Driven Open-Set Object Detection
by: Lu, Wenhuan, et al.
Published: (2025)

MixFake: Benchmarking and Enhancing Audio Deepfake Detection in Diverse Real-world Mixed Audio
by: Li, Qingcao, et al.
Published: (2026)

SpotSound: Enhancing Large Audio-Language Models with Fine-Grained Temporal Grounding
by: Sun, Luoyi, et al.
Published: (2026)

InconVAD: A Two-Stage Dual-Tower Framework for Multimodal Emotion Inconsistency Detection
by: Li, Zongyi, et al.
Published: (2025)

MMED: A Multimodal Micro-Expression Dataset based on Audio-Visual Fusion
by: Wang, Junbo, et al.
Published: (2025)

Preserving Speaker Information in Direct Speech-to-Speech Translation with Non-Autoregressive Generation and Pretraining
by: Zhou, Rui, et al.
Published: (2024)

MTAVG-Bench: A Diagnostic Benchmark for Multi-Talker Dialogue-Centric Audio-Video Generation
by: Zhou, Yang-Hao, et al.
Published: (2026)

Timed text extraction from Taiwanese Kua-á-hì TV series
by: Huang, Tzu-Hung, et al.
Published: (2026)

StyleSpeech: Parameter-efficient Fine Tuning for Pre-trained Controllable Text-to-Speech
by: Lou, Haowei, et al.
Published: (2024)

AV-EMO-Reasoning: Benchmarking Emotional Reasoning Capabilities in Omni-modal LLMS with Audio-visual Cues
by: Zhou, Dingkun, et al.
Published: (2025)

SarcasmMiner: A Dual-Track Post-Training Framework for Robust Audio-Visual Sarcasm Reasoning
by: Li, Zhu, et al.
Published: (2026)

AUREXA-SE: Audio-Visual Unified Representation Exchange Architecture with Cross-Attention and Squeezeformer for Speech Enhancement
by: Sajid, M., et al.
Published: (2025)