Cover Image

Style Amnesia: Investigating Speaking Style Degradation and Mitigation in Multi-Turn Spoken Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lin, Yu-Xiang, Chiang, Cheng-Han, Lee, Hung-yi
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Sound
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Advancing Large Language Models to Capture Varied Speaking Styles and Respond Properly in Spoken Conversations
by: Lin, Guan-Ting, et al.
Published: (2024)

TASTE-Streaming: Towards Streamable Text-Aligned Speech Tokenization and Embedding for Spoken Language Modeling
by: Tseng, Liang-Hsuan, et al.
Published: (2026)

Investigating the Effects of Large-Scale Pseudo-Stereo Data and Different Speech Foundation Model on Dialogue Generative Spoken Language Model
by: Fu, Yu-Kuan, et al.
Published: (2024)

When Silence Matters: The Impact of Irrelevant Audio on Text Reasoning in Large Audio-Language Models
by: Li, Chen-An, et al.
Published: (2025)

Hearing the Order: Investigating Position Bias in Large Audio-Language Models
by: Lin, Yu-Xiang, et al.
Published: (2025)

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

TASTE: Text-Aligned Speech Tokenization and Embedding for Spoken Language Modeling
by: Tseng, Liang-Hsuan, et al.
Published: (2025)

Factor-Conditioned Speaking-Style Captioning
by: Ando, Atsushi, et al.
Published: (2024)

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models
by: Hsiao, Chi-Yuan, et al.
Published: (2025)

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

Expressive Speech Retrieval using Natural Language Descriptions of Speaking Style
by: Kang, Wonjune, et al.
Published: (2025)

VStyle: A Benchmark for Voice Style Adaptation with Spoken Instructions
by: Zhan, Jun, et al.
Published: (2025)

On the Evaluation of Speech Foundation Models for Spoken Language Understanding
by: Arora, Siddhant, et al.
Published: (2024)

Zero Resource Code-switched Speech Benchmark Using Speech Utterance Pairs For Multiple Spoken Languages
by: Huang, Kuan-Po, et al.
Published: (2023)

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)

MI-Fuse: Label Fusion for Unsupervised Domain Adaptation with Closed-Source Large-Audio Language Model
by: Huang, Hsiao-Ying, et al.
Published: (2025)

Causal Tracing of Audio-Text Fusion in Large Audio Language Models
by: Chen, Wei-Chih, et al.
Published: (2026)

Audio-Aware Large Language Models as Judges for Speaking Styles
by: Chiang, Cheng-Han, et al.
Published: (2025)

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

Building a Taiwanese Mandarin Spoken Language Model: A First Attempt
by: Yang, Chih-Kai, et al.
Published: (2024)

SpeechDPR: End-to-End Spoken Passage Retrieval for Open-Domain Spoken Question Answering
by: Lin, Chyi-Jiunn, et al.
Published: (2024)

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

From Turn-Taking to Synchronous Dialogue: A Survey of Full-Duplex Spoken Language Models
by: Chen, Yuxuan, et al.
Published: (2025)

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)

Voice Conversion for Lombard Speaking Style with Implicit and Explicit Acoustic Feature Conditioning
by: Woszczyk, Dominika, et al.
Published: (2025)

LibriTTS-P: A Corpus with Speaking Style and Speaker Identity Prompts for Text-to-Speech and Style Captioning
by: Kawamura, Masaya, et al.
Published: (2024)

TCSinger: Zero-Shot Singing Voice Synthesis with Style Transfer and Multi-Level Style Control
by: Zhang, Yu, et al.
Published: (2024)

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

SPAR-K: Scheduled Periodic Alternating Early Exit for Spoken Language Models
by: Huang, Hsiao-Ying, et al.
Published: (2026)

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)

Reflecting Twice before Speaking with Empathy: Self-Reflective Alternating Inference for Empathy-Aware End-to-End Spoken Dialogue
by: Jia, Yuhang, et al.
Published: (2026)

How Auditory Knowledge in LLM Backbones Shapes Audio Language Models: A Holistic Evaluation
by: Lu, Ke-Han, et al.
Published: (2026)

DeSTA2: Developing Instruction-Following Speech Language Model Without Speech Instruction-Tuning Data
by: Lu, Ke-Han, et al.
Published: (2024)

StyleSinger: Style Transfer for Out-of-Domain Singing Voice Synthesis
by: Zhang, Yu, et al.
Published: (2023)

On The Landscape of Spoken Language Models: A Comprehensive Survey
by: Arora, Siddhant, et al.
Published: (2025)

SUTA-LM: Bridging Test-Time Adaptation and Language Model Rescoring for Robust ASR
by: Huang, Wei-Ping, et al.
Published: (2025)

Audio MultiChallenge: A Multi-Turn Evaluation of Spoken Dialogue Systems on Natural Human Interaction
by: Gosai, Advait, et al.
Published: (2025)

REBORN: Reinforcement-Learned Boundary Segmentation with Iterative Training for Unsupervised ASR
by: Tseng, Liang-Hsuan, et al.
Published: (2024)

DeepDialogue: A Multi-Turn Emotionally-Rich Spoken Dialogue Dataset
by: Koudounas, Alkis, et al.
Published: (2025)

Spoken Language Identification with Pre-trained Models and Margin Loss
by: Fang, Zhihua, et al.
Published: (2026)