Imagen de Portada

Comparative Study on Noise-Augmented Training and its Effect on Adversarial Robustness in ASR Systems

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Pizzi, Karla, Pizarro, Matías, Fischer, Asja
Formato:	Preprint
Publicado:	2024
Materias:	Audio and Speech Processing Machine Learning Sound
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Robustifying automatic speech recognition by extracting slowly varying features
por: Pizarro, Matías, et al.
Publicado: (2021)

DistriBlock: Identifying adversarial audio samples by leveraging characteristics of the output distribution
por: Pizarro, Matías, et al.
Publicado: (2023)

Precision-Varying Prediction (PVP): Robustifying ASR systems against adversarial attacks
por: Pizarro, Matías, et al.
Publicado: (2026)

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

Are Deep Speech Denoising Models Robust to Adversarial Noise?
por: Schwarzer, Will, et al.
Publicado: (2025)

Adversarial Data Augmentation for Robust Speaker Verification
por: Zhou, Zhenyu, et al.
Publicado: (2024)

Wav2code: Restore Clean Speech Representations via Codebook Lookup for Noise-Robust ASR
por: Hu, Yuchen, et al.
Publicado: (2023)

Training Generative Adversarial Network-Based Vocoder with Limited Data Using Augmentation-Conditional Discriminator
por: Kaneko, Takuhiro, et al.
Publicado: (2024)

Adapter-Based Multi-Agent AVSR Extension for Pre-Trained ASR Models
por: Simic, Christopher, et al.
Publicado: (2025)

CJST: CTC Compressor based Joint Speech and Text Training for Decoder-Only ASR
por: Zhou, Wei, et al.
Publicado: (2024)

Speech Diarization and ASR with GMM
por: Sharma, Aayush Kumar, et al.
Publicado: (2023)

OLMoASR: Open Models and Data for Training Robust Speech Recognition Models
por: Ngo, Huong, et al.
Publicado: (2025)

Training Universal Vocoders with Feature Smoothing-Based Augmentation Methods for High-Quality TTS Systems
por: Liu, Jeongmin, et al.
Publicado: (2024)

Exploratory Evaluation of Speech Content Masking
por: Williams, Jennifer, et al.
Publicado: (2024)

Multi-modal Adversarial Training for Zero-Shot Voice Cloning
por: Janiczek, John, et al.
Publicado: (2024)

Improving the Adversarial Robustness for Speaker Verification by Self-Supervised Learning
por: Wu, Haibin, et al.
Publicado: (2021)

Exploring Sentence Type Effects on the Lombard Effect and Intelligibility Enhancement: A Comparative Study of Natural and Grid Sentences
por: Chen, Hongyang, et al.
Publicado: (2023)

Accent Conversion in Text-To-Speech Using Multi-Level VAE and Adversarial Training
por: Melechovsky, Jan, et al.
Publicado: (2024)

A Joint Noise Disentanglement and Adversarial Training Framework for Robust Speaker Verification
por: Xing, Xujiang, et al.
Publicado: (2024)

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

Breaking Down Power Barriers in On-Device Streaming ASR: Insights and Solutions
por: Li, Yang, et al.
Publicado: (2024)

Are Modern Speech Enhancement Systems Vulnerable to Adversarial Attacks?
por: Makarov, Rostislav, et al.
Publicado: (2025)

Enhancing Pre-trained ASR System Fine-tuning for Dysarthric Speech Recognition using Adversarial Data Augmentation
por: Wang, Huimeng, et al.
Publicado: (2024)

RobustSpeechFlow: Learning Robust Text-to-Speech Trajectories via Augmentation-based Contrastive Flow Matching
por: Yang, Jinhyeok, et al.
Publicado: (2026)

When De-noising Hurts: A Systematic Study of Speech Enhancement Effects on Modern Medical ASR Systems
por: Chondhekar, Sujal, et al.
Publicado: (2025)

Edge-ASR: Towards Low-Bit Quantization of Automatic Speech Recognition Models
por: Feng, Chen, et al.
Publicado: (2025)

TRNet: Two-level Refinement Network leveraging Speech Enhancement for Noise Robust Speech Emotion Recognition
por: Chen, Chengxin, et al.
Publicado: (2024)

Adversarial Training of Denoising Diffusion Model Using Dual Discriminators for High-Fidelity Multi-Speaker TTS
por: Ko, Myeongjin, et al.
Publicado: (2023)

Houston we have a Divergence: A Subgroup Performance Analysis of ASR Models
por: Koudounas, Alkis, et al.
Publicado: (2024)

Evaluation of Speech Foundation Models for ASR on Child-Adult Conversations in Autism Diagnostic Sessions
por: Ashvin, Aditya, et al.
Publicado: (2024)

TeLeS: Temporal Lexeme Similarity Score to Estimate Confidence in End-to-End ASR
por: Ravi, Nagarathna, et al.
Publicado: (2024)

Towards Supervised Performance on Speaker Verification with Self-Supervised Learning by Leveraging Large-Scale ASR Models
por: Miara, Victor, et al.
Publicado: (2024)

Continued Pretraining for Low-Resource Swahili ASR: Achieving State-of-the-Art Performance with Minimal Labeled Data
por: Mutisya, Hillary, et al.
Publicado: (2026)

SC-MoE: Switch Conformer Mixture of Experts for Unified Streaming and Non-streaming Code-Switching ASR
por: Ye, Shuaishuai, et al.
Publicado: (2024)

Towards Robust Transcription: Exploring Noise Injection Strategies for Training Data Augmentation
por: Kim, Yonghyun, et al.
Publicado: (2024)

Conformer-1: Robust ASR via Large-Scale Semisupervised Bootstrapping
por: Zhang, Kevin, et al.
Publicado: (2024)

Dysarthria Normalization via Local Lie Group Transformations for Robust ASR
por: Osipov, Mikhail
Publicado: (2025)

Sequence-Level Unsupervised Training in Speech Recognition: A Theoretical Study
por: Yang, Zijian, et al.
Publicado: (2026)

Enhanced ASR Robustness to Packet Loss with a Front-End Adaptation Network
por: Dissen, Yehoshua, et al.
Publicado: (2024)

COVID-19 Detection System: A Comparative Analysis of System Performance Based on Acoustic Features of Cough Audio Signals
por: Shati, Asmaa, et al.
Publicado: (2023)