Buchumschlag

ASPIRin: Action Space Projection for Interactivity-Optimized Reinforcement Learning in Full-Duplex Speech Language Models

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Hsiao, Chi-Yuan, Lu, Ke-Han, Fu, Yu-Kuan, Lin, Guan-Ting, Hung, Hsiao-Tsung, Lee, Hung-yi
Format:	Preprint
Veröffentlicht:	2026
Schlagworte:	Computation and Language Artificial Intelligence Sound Audio and Speech Processing
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

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

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

Phoenix-VAD: Streaming Semantic Endpoint Detection for Full-Duplex Speech Interaction
von: Wu, Weijie, et al.
Veröffentlicht: (2025)

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

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

Full-Duplex-Bench v1.5: Evaluating Overlap Handling for Full-Duplex Speech Models
von: Lin, Guan-Ting, et al.
Veröffentlicht: (2025)

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

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

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

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

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

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

ConSep: a Noise- and Reverberation-Robust Speech Separation Framework by Magnitude Conditioning
von: Ho, Kuan-Hsun, et al.
Veröffentlicht: (2024)

Dynamic-SUPERB: Towards A Dynamic, Collaborative, and Comprehensive Instruction-Tuning Benchmark for Speech
von: Huang, Chien-yu, et al.
Veröffentlicht: (2023)

What do neural networks listen to? Exploring the crucial bands in Speech Enhancement using Sinc-convolution
von: Ho, Kuan-Hsun, et al.
Veröffentlicht: (2024)

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

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

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

Full-Duplex-Bench-v3: Benchmarking Tool Use for Full-Duplex Voice Agents Under Real-World Disfluency
von: Lin, Guan-Ting, et al.
Veröffentlicht: (2026)

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

Do Prompts Really Prompt? Exploring the Prompt Understanding Capability of Whisper
von: Yang, Chih-Kai, et al.
Veröffentlicht: (2024)

UAF: A Unified Audio Front-end LLM for Full-Duplex Speech Interaction
von: Li, Yadong, et al.
Veröffentlicht: (2026)

Leveraging Mamba with Full-Face Vision for Audio-Visual Speech Enhancement
von: Chao, Rong, et al.
Veröffentlicht: (2025)

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

A Small-footprint Acoustic Echo Cancellation Solution for Mobile Full-Duplex Speech Interactions
von: Jiang, Yiheng, et al.
Veröffentlicht: (2025)

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

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

SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model
von: Hu, Ke, et al.
Veröffentlicht: (2025)

Adaptive vector steering: A training-free, layer-wise intervention for hallucination mitigation in large audio and multimodal models
von: Lin, Tsung-En, et al.
Veröffentlicht: (2025)

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

Full-Duplex-Bench-v2: A Multi-Turn Evaluation Framework for Duplex Dialogue Systems with an Automated Examiner
von: Lin, Guan-Ting, et al.
Veröffentlicht: (2025)

SpeechCaps: Advancing Instruction-Based Universal Speech Models with Multi-Talker Speaking Style Captioning
von: Huang, Chien-yu, et al.
Veröffentlicht: (2024)

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

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

Investigating Zero-Shot Generalizability on Mandarin-English Code-Switched ASR and Speech-to-text Translation of Recent Foundation Models with Self-Supervision and Weak Supervision
von: Yang, Chih-Kai, et al.
Veröffentlicht: (2023)

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

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

A Study on Synthesizing Expressive Violin Performances: Approaches and Comparisons
von: Hung, Tzu-Yun, et al.
Veröffentlicht: (2024)

Identifying Speaker Information in Feed-Forward Layers of Self-Supervised Speech Transformers
von: Lin, Tzu-Quan, et al.
Veröffentlicht: (2025)

TurnGuide: Enhancing Meaningful Full Duplex Spoken Interactions via Dynamic Turn-Level Text-Speech Interleaving
von: Cui, Wenqian, et al.
Veröffentlicht: (2025)