Buchumschlag

Activation Steering for Accent Adaptation in Speech Foundation Models

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Sun, Jinuo, Xiao, Yang, Chung, Sung Kyun, Hu, Qiuchi, Huang, Gongping, Holden, Eun-Jung, Dang, Ting
Format:	Preprint
Veröffentlicht:	2026
Schlagworte:	Audio and Speech Processing
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Adapting Where It Matters: Depth-Aware Adaptation for Efficient Multilingual Speech Recognition in Low-Resource Languages
von: Xiao, Yang, et al.
Veröffentlicht: (2026)

Rethinking Continual Learning for Speech and Audio: A Representation-Centric Taxonomy and Open Problems
von: Xiao, Yang, et al.
Veröffentlicht: (2026)

Activation Steering for Accent-Neutralized Zero-Shot Text-To-Speech
von: Yang, Mu, et al.
Veröffentlicht: (2026)

Continual Adaptation for Pacific Indigenous Speech Recognition
von: Xiao, Yang, et al.
Veröffentlicht: (2026)

Adaptive Federated Fine-Tuning of Self-Supervised Speech Representations
von: Guo, Xin, et al.
Veröffentlicht: (2026)

Why Can't They Remember? Uncovering Representation and Retrieval Bottlenecks in Multi-Turn Acoustic Memory
von: Xiao, Yang, et al.
Veröffentlicht: (2026)

ImKWS: Test-Time Adaptation for Keyword Spotting with Class Imbalance
von: Ding, Hanyu, et al.
Veröffentlicht: (2026)

CodecMOS-Accent: A MOS Benchmark of Resynthesized and TTS Speech from Neural Codecs Across English Accents
von: Huang, Wen-Chin, et al.
Veröffentlicht: (2026)

SALSA: Speech Aware LLM Adaptation via Learned Steering Activation Vectors
von: Yegorova, Yekaterina, et al.
Veröffentlicht: (2026)

MacST: Multi-Accent Speech Synthesis via Text Transliteration for Accent Conversion
von: Inoue, Sho, et al.
Veröffentlicht: (2024)

RawTFNet: A Lightweight CNN Architecture for Speech Anti-spoofing
von: Xiao, Yang, et al.
Veröffentlicht: (2025)

Multi-Scale Accent Modeling and Disentangling for Multi-Speaker Multi-Accent Text-to-Speech Synthesis
von: Zhou, Xuehao, et al.
Veröffentlicht: (2024)

Spatial-Filter-Bank-Based Neural Method for Multichannel Speech Enhancement
von: Zheng, Tianqin, et al.
Veröffentlicht: (2025)

Unsupervised Accent Adaptation Through Masked Language Model Correction Of Discrete Self-Supervised Speech Units
von: Poncelet, Jakob, et al.
Veröffentlicht: (2023)

Test-Time Adaptation for Speech Emotion Recognition
von: Dong, Jiaheng, et al.
Veröffentlicht: (2026)

Analyzing the Impact of Accent on English Speech: Acoustic and Articulatory Perspectives
von: Premananth, Gowtham, et al.
Veröffentlicht: (2025)

E-BATS: Efficient Backpropagation-Free Test-Time Adaptation for Speech Foundation Models
von: Dong, Jiaheng, et al.
Veröffentlicht: (2025)

Forward Convolutive Prediction for Frame Online Monaural Speech Dereverberation Based on Kronecker Product Decomposition
von: Zhu, Yujie, et al.
Veröffentlicht: (2025)

Token-Level Logits Matter: A Closer Look at Speech Foundation Models for Ambiguous Emotion Recognition
von: Halim, Jule Valendo, et al.
Veröffentlicht: (2025)

Zero Shot Text to Speech Augmentation for Automatic Speech Recognition on Low-Resource Accented Speech Corpora
von: Nespoli, Francesco, et al.
Veröffentlicht: (2024)

AccentFold: A Journey through African Accents for Zero-Shot ASR Adaptation to Target Accents
von: Owodunni, Abraham Toluwase, et al.
Veröffentlicht: (2024)

Advances in Microphone Array Processing and Multichannel Speech Enhancement
von: Huang, Gongping, et al.
Veröffentlicht: (2025)

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

Empowering Communication: Speech Technology for Indian and Western Accents through AI-powered Speech Synthesis
von: R, Vinotha, et al.
Veröffentlicht: (2024)

Scalable Controllable Accented TTS
von: Xinyuan, Henry Li, et al.
Veröffentlicht: (2025)

Accent Conversion with Articulatory Representations
von: Siriwardena, Yashish M., et al.
Veröffentlicht: (2024)

LID Models are Actually Accent Classifiers: Implications and Solutions for LID on Accented Speech
von: Bafna, Niyati, et al.
Veröffentlicht: (2025)

DITTO: Data-efficient and Fair Targeted Subset Selection for ASR Accent Adaptation
von: Kothawade, Suraj, et al.
Veröffentlicht: (2021)

Resource-Efficient Adaptation of Speech Foundation Models for Multi-Speaker ASR
von: Wang, Weiqing, et al.
Veröffentlicht: (2024)

Generative Speech Foundation Model Pretraining for High-Quality Speech Extraction and Restoration
von: Ku, Pin-Jui, et al.
Veröffentlicht: (2024)

SpeechAccentLLM: A Unified Framework for Foreign Accent Conversion and Text to Speech
von: Cheng, Zhuangfei, et al.
Veröffentlicht: (2025)

GLOBE: A High-quality English Corpus with Global Accents for Zero-shot Speaker Adaptive Text-to-Speech
von: Wang, Wenbin, et al.
Veröffentlicht: (2024)

Structured Speaker-Deficiency Adaptation of Foundation Models for Dysarthric and Elderly Speech Recognition
von: Hu, Shujie, et al.
Veröffentlicht: (2024)

Clustering and Mining Accented Speech for Inclusive and Fair Speech Recognition
von: Kim, Jaeyoung, et al.
Veröffentlicht: (2024)

Pairwise Evaluation of Accent Similarity in Speech Synthesis
von: Zhong, Jinzuomu, et al.
Veröffentlicht: (2025)

Speech Emotion Recognition Via CNN-Transformer and Multidimensional Attention Mechanism
von: Tang, Xiaoyu, et al.
Veröffentlicht: (2024)

Characterization of Speech Similarity Between Australian Aboriginal and High-Resource Languages: A Case Study on Dharawal
von: Dang, Ting, et al.
Veröffentlicht: (2025)

LMFCA-Net: A Lightweight Model for Multi-Channel Speech Enhancement with Efficient Narrow-Band and Cross-Band Attention
von: Zhang, Yaokai, et al.
Veröffentlicht: (2025)

EmoSteer-TTS: Fine-Grained and Training-Free Emotion-Controllable Text-to-Speech via Activation Steering
von: Xie, Tianxin, et al.
Veröffentlicht: (2025)

A Unified Neural Codec Language Model for Selective Editable Text to Speech Generation
von: Pei, Hanchen, et al.
Veröffentlicht: (2026)