Copertina

X-OPD: Cross-Modal On-Policy Distillation for Capability Alignment in Speech LLMs

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Cao, Di, Fu, Dongjie, Yu, Hai, Zheng, Siqi, Tan, Xu, Jin, Tao
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Audio and Speech Processing Artificial Intelligence Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

TTA: Transcribe, Translate and Alignment for Cross-lingual Speech Representation
di: Liu, Wei, et al.
Pubblicazione: (2025)

Improving Speech Emotion Recognition Through Cross Modal Attention Alignment and Balanced Stacking Model
di: Ueda, Lucas, et al.
Pubblicazione: (2025)

TASU: Text-Only Alignment for Speech Understanding
di: Peng, Jing, et al.
Pubblicazione: (2025)

Dynamic Frequency-Adaptive Knowledge Distillation for Speech Enhancement
di: Yuan, Xihao, et al.
Pubblicazione: (2025)

UME: Upcycling Mixture-of-Experts for Scalable and Efficient Automatic Speech Recognition
di: Fu, Li, et al.
Pubblicazione: (2024)

Cross-Modal Bottleneck Fusion For Noise Robust Audio-Visual Speech Recognition
di: Ok, Seaone, et al.
Pubblicazione: (2026)

SSR: Alignment-Aware Modality Connector for Speech Language Models
di: Tan, Weiting, et al.
Pubblicazione: (2024)

Dual-Branch Knowledge Distillation for Noise-Robust Synthetic Speech Detection
di: Fan, Cunhang, et al.
Pubblicazione: (2023)

Reducing Linguistic Hallucination in LM-Based Speech Enhancement via Noise-Invariant Acoustic-Semantic Distillation
di: Wang, Zheng, et al.
Pubblicazione: (2026)

ToneUnit: A Speech Discretization Approach for Tonal Language Speech Synthesis
di: Tao, Dehua, et al.
Pubblicazione: (2024)

Accelerating Diffusion-based Text-to-Speech Model Training with Dual Modality Alignment
di: Choi, Jeongsoo, et al.
Pubblicazione: (2025)

Speech-Omni-Lite: Portable Speech Interfaces for Vision-Language Models
di: Tao, Dehua, et al.
Pubblicazione: (2026)

WhisperVC: Decoupled Cross-Domain Alignment and Speech Generation for Low-Resource Whisper-to-Normal Conversion
di: Liu, Dong, et al.
Pubblicazione: (2025)

Complex Recurrent Variational Autoencoder with Application to Speech Enhancement
di: Xie, Yuying, et al.
Pubblicazione: (2022)

ARTT: Augmented Reverberant-Target Training for Unsupervised Monaural Speech Dereverberation
di: Song, Siqi, et al.
Pubblicazione: (2026)

Multi-Distillation from Speech and Music Representation Models
di: Wei, Jui-Chiang, et al.
Pubblicazione: (2025)

Exploring the Capability of Mamba in Speech Applications
di: Miyazaki, Koichi, et al.
Pubblicazione: (2024)

Continuous Speech Tokens Makes LLMs Robust Multi-Modality Learners
di: Yuan, Ze, et al.
Pubblicazione: (2024)

TASU2: Controllable CTC Simulation for Alignment and Low-Resource Adaptation of Speech LLMs
di: Peng, Jing, et al.
Pubblicazione: (2026)

Speech Token Prediction via Compressed-to-fine Language Modeling for Speech Generation
di: Liu, Wenrui, et al.
Pubblicazione: (2025)

FlexSpeech: Towards Stable, Controllable and Expressive Text-to-Speech
di: Ma, Linhan, et al.
Pubblicazione: (2025)

LLMs and Speech: Integration vs. Combination
di: Schmitt, Robin, et al.
Pubblicazione: (2026)

Robust One-step Speech Enhancement via Consistency Distillation
di: Xu, Liang, et al.
Pubblicazione: (2025)

SpeechEditBench: A Bilingual Multi-Attribute Benchmark for Instruction-Guided Speech Editing
di: Zhang, Hanlin, et al.
Pubblicazione: (2026)

Distil-DCCRN: A Small-footprint DCCRN Leveraging Feature-based Knowledge Distillation in Speech Enhancement
di: Han, Runduo, et al.
Pubblicazione: (2024)

Attention-weighted Centered Kernel Alignment for Knowledge Distillation in Large Audio-Language Models Applied to Speech Emotion Recognition
di: Yang, Qingran, et al.
Pubblicazione: (2026)

Group Relative Policy Optimization for Speech Recognition
di: Shivakumar, Prashanth Gurunath, et al.
Pubblicazione: (2025)

AS-Speech: Adaptive Style For Speech Synthesis
di: Li, Zhipeng, et al.
Pubblicazione: (2024)

Exploring Cross-Utterance Speech Contexts for Conformer-Transducer Speech Recognition Systems
di: Cui, Mingyu, et al.
Pubblicazione: (2025)

Text-aware Speech Separation for Multi-talker Keyword Spotting
di: Li, Haoyu, et al.
Pubblicazione: (2024)

DeSTA: Enhancing Speech Language Models through Descriptive Speech-Text Alignment
di: Lu, Ke-Han, et al.
Pubblicazione: (2024)

Adaptive Duration Model for Text Speech Alignment
di: Cao, Junjie
Pubblicazione: (2025)

Synergistic Effects of Knowledge Distillation and Structured Pruning for Self-Supervised Speech Models
di: C, Shiva Kumar, et al.
Pubblicazione: (2025)

Semantic-VAE: Semantic-Alignment Latent Representation for Better Speech Synthesis
di: Niu, Zhikang, et al.
Pubblicazione: (2025)

SiamCTC: Learning Speech Representations through Monotonic Temporal Alignment
di: Eom, SooHwan, et al.
Pubblicazione: (2026)

Validating Computational Markers of Depressive Behavior: Cross-Linguistic Speech-Based Depression Detection with Neurophysiological Validation
di: Tao, Fuxiang, et al.
Pubblicazione: (2026)

AV-CrossNet: an Audiovisual Complex Spectral Mapping Network for Speech Separation By Leveraging Narrow- and Cross-Band Modeling
di: Kalkhorani, Vahid Ahmadi, et al.
Pubblicazione: (2024)

Audio-Image Cross-Modal Retrieval with Onomatopoeic Images
di: Imoto, Keisuke, et al.
Pubblicazione: (2026)

Anatomy of the Modality Gap: Dissecting the Internal States of End-to-End Speech LLMs
di: Hsu, Ming-Hao, et al.
Pubblicazione: (2026)

DISPATCH: Distilling Selective Patches for Speech Enhancement
di: Kim, Dohwan, et al.
Pubblicazione: (2025)