Copertina

Efficiently Train ASR Models that Memorize Less and Perform Better with Per-core Clipping

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wang, Lun, Thakkar, Om, Meng, Zhong, Rafidi, Nicole, Prabhavalkar, Rohit, Narayanan, Arun
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Cryptography and Security Computation and Language Sound Audio and Speech Processing
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Training Large ASR Encoders with Differential Privacy
di: Chauhan, Geeticka, et al.
Pubblicazione: (2024)

Multi-speaker Text-to-speech Training with Speaker Anonymized Data
di: Huang, Wen-Chin, et al.
Pubblicazione: (2024)

DIN-CTS: Low-Complexity Depthwise-Inception Neural Network with Contrastive Training Strategy for Deepfake Speech Detection
di: Pham, Lam, et al.
Pubblicazione: (2025)

Improving Membership Inference in ASR Model Auditing with Perturbed Loss Features
di: Teixeira, Francisco, et al.
Pubblicazione: (2024)

SuperEar: Eavesdropping on Mobile Voice Calls via Stealthy Acoustic Metamaterials
di: Ning, Zhiyuan, et al.
Pubblicazione: (2025)

Your Microphone Array Retains Your Identity: A Robust Voice Liveness Detection System for Smart Speakers
di: Meng, Yan, et al.
Pubblicazione: (2025)

Attacker's Noise Can Manipulate Your Audio-based LLM in the Real World
di: Sadasivan, Vinu Sankar, et al.
Pubblicazione: (2025)

WaLi: Can Pressure Sensors in HVAC Systems Capture Human Speech?
di: Tamiti, Tarikul Islam, et al.
Pubblicazione: (2025)

Hybrid Audio Detection Using Fine-Tuned Audio Spectrogram Transformers: A Dataset-Driven Evaluation of Mixed AI-Human Speech
di: Huang, Kunyang, et al.
Pubblicazione: (2025)

LENS-DF: Deepfake Detection and Temporal Localization for Long-Form Noisy Speech
di: Liu, Xuechen, et al.
Pubblicazione: (2025)

Cross-Technology Generalization in Synthesized Speech Detection: Evaluating AST Models with Modern Voice Generators
di: Ustinov, Andrew, et al.
Pubblicazione: (2025)

Benchmarking Fake Voice Detection in the Fake Voice Generation Arms Race
di: Mao, Xutao, et al.
Pubblicazione: (2025)

Why Speech Deepfake Detectors Won't Generalize: The Limits of Detection in an Open World
di: Berisha, Visar, et al.
Pubblicazione: (2025)

Spoofing attack augmentation: can differently-trained attack models improve generalisation?
di: Ge, Wanying, et al.
Pubblicazione: (2023)

Sok: Comprehensive Security Overview, Challenges, and Future Directions of Voice-Controlled Systems
di: Xu, Haozhe, et al.
Pubblicazione: (2024)

Zero-Query Adversarial Attack on Black-box Automatic Speech Recognition Systems
di: Fang, Zheng, et al.
Pubblicazione: (2024)

Pitch Imperfect: Detecting Audio Deepfakes Through Acoustic Prosodic Analysis
di: Warren, Kevin, et al.
Pubblicazione: (2025)

Robust AI-Synthesized Speech Detection Using Feature Decomposition Learning and Synthesizer Feature Augmentation
di: Zhang, Kuiyuan, et al.
Pubblicazione: (2024)

Evaluating Synthetic Command Attacks on Smart Voice Assistants
di: He, Zhengxian, et al.
Pubblicazione: (2024)

SpeechVerifier: Robust Acoustic Fingerprint against Tampering Attacks via Watermarking
di: Yao, Lingfeng, et al.
Pubblicazione: (2025)

Privacy in Speech Technology
di: Bäckström, Tom
Pubblicazione: (2023)

Making Acoustic Side-Channel Attacks on Noisy Keyboards Viable with LLM-Assisted Spectrograms' "Typo" Correction
di: Ayati, Seyyed Ali, et al.
Pubblicazione: (2025)

Lightweight Protection for Privacy in Offloaded Speech Understanding
di: Cai, Dongqi
Pubblicazione: (2024)

An RFP dataset for Real, Fake, and Partially fake audio detection
di: AlAli, Abdulazeez, et al.
Pubblicazione: (2024)

A Preliminary Case Study on Long-Form In-the-Wild Audio Spoofing Detection
di: Liu, Xuechen, et al.
Pubblicazione: (2024)

Two Views, One Truth: Spectral and Self-Supervised Features Fusion for Robust Speech Deepfake Detection
di: Kheir, Yassine El, et al.
Pubblicazione: (2025)

MerkleSpeech: Public-Key Verifiable, Chunk-Localised Speech Provenance via Perceptual Fingerprints and Merkle Commitments
di: Ono, Tatsunori
Pubblicazione: (2026)

One-Class Learning with Adaptive Centroid Shift for Audio Deepfake Detection
di: Kim, Hyun Myung, et al.
Pubblicazione: (2024)

Quantized Approximate Signal Processing (QASP): Towards Homomorphic Encryption for audio
di: Nguyen, Tu Duyen, et al.
Pubblicazione: (2025)

Yours or Mine? Overwriting Attacks Against Neural Audio Watermarking
di: Yao, Lingfeng, et al.
Pubblicazione: (2025)

Quantifying Source Speaker Leakage in One-to-One Voice Conversion
di: Wellington, Scott, et al.
Pubblicazione: (2025)

Phoneme-Based Proactive Anti-Eavesdropping with Controlled Recording Privilege
di: Huang, Peng, et al.
Pubblicazione: (2024)

An Effective Energy Mask-based Adversarial Evasion Attacks against Misclassification in Speaker Recognition Systems
di: Park, Chanwoo, et al.
Pubblicazione: (2026)

Interpretable Temporal Class Activation Representation for Audio Spoofing Detection
di: Li, Menglu, et al.
Pubblicazione: (2024)

Frame-level Temporal Difference Learning for Partial Deepfake Speech Detection
di: Li, Menglu, et al.
Pubblicazione: (2025)

A Practical Survey on Emerging Threats from AI-driven Voice Attacks: How Vulnerable are Commercial Voice Control Systems?
di: Wang, Yuanda, et al.
Pubblicazione: (2023)

Inference Attacks for X-Vector Speaker Anonymization
di: Bauer, Luke, et al.
Pubblicazione: (2025)

Gumbel Rao Monte Carlo based Bi-Modal Neural Architecture Search for Audio-Visual Deepfake Detection
di: PN, Aravinda Reddy, et al.
Pubblicazione: (2024)

The Man Behind the Sound: Demystifying Audio Private Attribute Profiling via Multimodal Large Language Model Agents
di: Wang, Lixu, et al.
Pubblicazione: (2025)

PITCH: AI-assisted Tagging of Deepfake Audio Calls using Challenge-Response
di: Mittal, Govind, et al.
Pubblicazione: (2024)