Identifying Speaker Information in Feed-Forward Layers of Self-Supervised Speech Transformers

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lin, Tzu-Quan, Cheng, Hsi-Chun, Lee, Hung-yi, Tang, Hao
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Sound Audio and Speech Processing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Property Neurons in Self-Supervised Speech Transformers
by: Lin, Tzu-Quan, et al.
Published: (2024)

DAISY: Data Adaptive Self-Supervised Early Exit for Speech Representation Models
by: Lin, Tzu-Quan, et al.
Published: (2024)

Is Smaller Always Faster? Tradeoffs in Compressing Self-Supervised Speech Transformers
by: Lin, Tzu-Quan, et al.
Published: (2022)

MelHuBERT: A simplified HuBERT on Mel spectrograms
by: Lin, Tzu-Quan, et al.
Published: (2022)

Improving Speech Emotion Recognition in Under-Resourced Languages via Speech-to-Speech Translation with Bootstrapping Data Selection
by: Lin, Hsi-Che, et al.
Published: (2024)

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

Continual Test-time Adaptation for End-to-end Speech Recognition on Noisy Speech
by: Lin, Guan-Ting, et al.
Published: (2024)

How Contrastive Decoding Enhances Large Audio Language Models?
by: Lin, Tzu-Quan, et al.
Published: (2026)

SMILE: Speech Meta In-Context Learning for Low-Resource Language Automatic Speech Recognition
by: Hsu, Ming-Hao, et al.
Published: (2024)

Spectral-Aware Low-Rank Adaptation for Speaker Verification
by: Li, Zhe, et al.
Published: (2025)

A Large-Scale Probing Analysis of Speaker-Specific Attributes in Self-Supervised Speech Representations
by: Chiu, Aemon Yat Fei, et al.
Published: (2025)

CodecFake: Enhancing Anti-Spoofing Models Against Deepfake Audios from Codec-Based Speech Synthesis Systems
by: Wu, Haibin, et al.
Published: (2024)

Toward Fair Speech Technologies: A Comprehensive Survey of Bias and Fairness in Speech AI
by: Lin, Yi-Cheng, et al.
Published: (2026)

Fusion of Discrete Representations and Self-Augmented Representations for Multilingual Automatic Speech Recognition
by: Wang, Shih-heng, et al.
Published: (2024)

Neural Codec-based Adversarial Sample Detection for Speaker Verification
by: Chen, Xuanjun, et al.
Published: (2024)

Efficient Training of Self-Supervised Speech Foundation Models on a Compute Budget
by: Liu, Andy T., et al.
Published: (2024)

Can you Remove the Downstream Model for Speaker Recognition with Self-Supervised Speech Features?
by: Aldeneh, Zakaria, et al.
Published: (2024)

Mitigating Subgroup Disparities in Multi-Label Speech Emotion Recognition: A Pseudo-Labeling and Unsupervised Learning Approach
by: Lin, Yi-Cheng, et al.
Published: (2025)

Stimulus Modality Matters: Impact of Perceptual Evaluations from Different Modalities on Speech Emotion Recognition System Performance
by: Chou, Huang-Cheng, et al.
Published: (2024)

Parallel Synthesis for Autoregressive Speech Generation
by: Hsu, Po-chun, et al.
Published: (2022)

Leveraging Self-Supervised Learning for Speaker Diarization
by: Han, Jiangyu, et al.
Published: (2024)

Multichannel Long-Term Streaming Neural Speech Enhancement for Static and Moving Speakers
by: Quan, Changsheng, et al.
Published: (2024)

Low-Resource Self-Supervised Learning with SSL-Enhanced TTS
by: Hsu, Po-chun, et al.
Published: (2023)

PEFT for Speech: Unveiling Optimal Placement, Merging Strategies, and Ensemble Techniques
by: Lin, Tzu-Han, et al.
Published: (2024)

Self-Distillation Prototypes Network: Learning Robust Speaker Representations without Supervision
by: Chen, Yafeng, et al.
Published: (2024)

Self-Distillation Prototypes Network: Learning Robust Speaker Representations without Supervision
by: Chen, Yafeng, et al.
Published: (2023)

NanoVoice: Efficient Speaker-Adaptive Text-to-Speech for Multiple Speakers
by: Park, Nohil, et al.
Published: (2024)

Can Large Audio-Language Models Truly Hear? Tackling Hallucinations with Multi-Task Assessment and Stepwise Audio Reasoning
by: Kuan, Chun-Yi, et al.
Published: (2024)

Teaching Audio-Aware Large Language Models What Does Not Hear: Mitigating Hallucinations through Synthesized Negative Samples
by: Kuan, Chun-Yi, et al.
Published: (2025)

The DKU System for Multi-Speaker Automatic Speech Recognition in MLC-SLM Challenge
by: Lin, Yuke, et al.
Published: (2025)

VIBE: Voice-Induced open-ended Bias Evaluation for Large Audio-Language Models via Real-World Speech
by: Lin, Yi-Cheng, et al.
Published: (2026)

Xi+: Uncertainty Supervision for Robust Speaker Embedding
by: Li, Junjie, et al.
Published: (2025)

EMO-Codec: An In-Depth Look at Emotion Preservation capacity of Legacy and Neural Codec Models With Subjective and Objective Evaluations
by: Ren, Wenze, et al.
Published: (2024)

SAKURA: On the Multi-hop Reasoning of Large Audio-Language Models Based on Speech and Audio Information
by: Yang, Chih-Kai, et al.
Published: (2025)

Analysis of Self-Supervised Speech Models on Children's Speech and Infant Vocalizations
by: Li, Jialu, et al.
Published: (2024)

Speaker Anonymisation for Speech-based Suicide Risk Detection
by: Cui, Ziyun, et al.
Published: (2025)

Speech-Copilot: Leveraging Large Language Models for Speech Processing via Task Decomposition, Modularization, and Program Generation
by: Kuan, Chun-Yi, et al.
Published: (2024)

Vox-Profile: A Speech Foundation Model Benchmark for Characterizing Diverse Speaker and Speech Traits
by: Feng, Tiantian, et al.
Published: (2025)

Speaker Embeddings With Weakly Supervised Voice Activity Detection For Efficient Speaker Diarization
by: Thienpondt, Jenthe, et al.
Published: (2024)

Dataset-Distillation Generative Model for Speech Emotion Recognition
by: Ritter-Gutierrez, Fabian, et al.
Published: (2024)