Cover Image

Closing the Modality Reasoning Gap for Speech Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Chaoren, Lu, Heng, Zhang, Xueyao, Liu, Shujie, Lu, Yan, Li, Jinyu, Wu, Zhizheng
Format:	Preprint
Published:	2026
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

Advancing Zero-shot Text-to-Speech Intelligibility across Diverse Domains via Preference Alignment
by: Zhang, Xueyao, et al.
Published: (2025)

Boosting Large Language Model for Speech Synthesis: An Empirical Study
by: Hao, Hongkun, et al.
Published: (2023)

SingNet: Towards a Large-Scale, Diverse, and In-the-Wild Singing Voice Dataset
by: Gu, Yicheng, et al.
Published: (2025)

SP-MCQA: Evaluating Intelligibility of TTS Beyond the Word Level
by: Tee, Hitomi Jin Ling, et al.
Published: (2025)

VoxPrivacy: A Benchmark for Evaluating Interactional Privacy of Speech Language Models
by: Wang, Yuxiang, et al.
Published: (2026)

TaDiCodec: Text-aware Diffusion Speech Tokenizer for Speech Language Modeling
by: Wang, Yuancheng, et al.
Published: (2025)

StreamMel: Real-Time Zero-shot Text-to-Speech via Interleaved Continuous Autoregressive Modeling
by: Wang, Hui, et al.
Published: (2025)

Emilia: A Large-Scale, Extensive, Multilingual, and Diverse Dataset for Speech Generation
by: He, Haorui, et al.
Published: (2025)

WavLLM: Towards Robust and Adaptive Speech Large Language Model
by: Hu, Shujie, et al.
Published: (2024)

SingVisio: Visual Analytics of Diffusion Model for Singing Voice Conversion
by: Xue, Liumeng, et al.
Published: (2024)

Neurodyne: Neural Pitch Manipulation with Representation Learning and Cycle-Consistency GAN
by: Gu, Yicheng, et al.
Published: (2025)

VALL-E 2: Neural Codec Language Models are Human Parity Zero-Shot Text to Speech Synthesizers
by: Chen, Sanyuan, et al.
Published: (2024)

Investigating Neural Audio Codecs for Speech Language Model-Based Speech Generation
by: Li, Jiaqi, et al.
Published: (2024)

Autoregressive Speech Synthesis without Vector Quantization
by: Meng, Lingwei, et al.
Published: (2024)

Solla: Towards a Speech-Oriented LLM That Hears Acoustic Context
by: Ao, Junyi, et al.
Published: (2025)

FELLE: Autoregressive Speech Synthesis with Token-Wise Coarse-to-Fine Flow Matching
by: Wang, Hui, et al.
Published: (2025)

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

DualCodec: A Low-Frame-Rate, Semantically-Enhanced Neural Audio Codec for Speech Generation
by: Li, Jiaqi, et al.
Published: (2025)

Enabling Auditory Large Language Models for Automatic Speech Quality Evaluation
by: Wang, Siyin, et al.
Published: (2024)

SEAL: Speech Embedding Alignment Learning for Speech Large Language Model with Retrieval-Augmented Generation
by: Sun, Chunyu, et al.
Published: (2025)

SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models
by: Zhang, Xin, et al.
Published: (2023)

Self-Powered LLM Modality Expansion for Large Speech-Text Models
by: Yu, Tengfei, et al.
Published: (2024)

SpeechLLM-as-Judges: Towards General and Interpretable Speech Quality Evaluation
by: Wang, Hui, et al.
Published: (2025)

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

SpeechX: Neural Codec Language Model as a Versatile Speech Transformer
by: Wang, Xiaofei, et al.
Published: (2023)

Amphion: An Open-Source Audio, Music and Speech Generation Toolkit
by: Zhang, Xueyao, et al.
Published: (2023)

Advanced Long-Content Speech Recognition With Factorized Neural Transducer
by: Gong, Xun, et al.
Published: (2024)

Noro: Noise-Robust One-shot Voice Conversion with Hidden Speaker Representation Learning
by: He, Haorui, et al.
Published: (2024)

VALL-E R: Robust and Efficient Zero-Shot Text-to-Speech Synthesis via Monotonic Alignment
by: Han, Bing, et al.
Published: (2024)

An Investigation of Time-Frequency Representation Discriminators for High-Fidelity Vocoder
by: Gu, Yicheng, et al.
Published: (2024)

Investigating Decoder-only Large Language Models for Speech-to-text Translation
by: Huang, Chao-Wei, et al.
Published: (2024)

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

Large Language Model Can Transcribe Speech in Multi-Talker Scenarios with Versatile Instructions
by: Meng, Lingwei, et al.
Published: (2024)

Aliasing-Free Neural Audio Synthesis
by: Gu, Yicheng, et al.
Published: (2025)

Enhancing Generalization of Speech Large Language Models with Multi-Task Behavior Imitation and Speech-Text Interleaving
by: Xie, Jingran, et al.
Published: (2025)

Soft Language Identification for Language-Agnostic Many-to-One End-to-End Speech Translation
by: Wang, Peidong, et al.
Published: (2024)

BLSP-Emo: Towards Empathetic Large Speech-Language Models
by: Wang, Chen, et al.
Published: (2024)

Improving Audio Codec-based Zero-Shot Text-to-Speech Synthesis with Multi-Modal Context and Large Language Model
by: Xue, Jinlong, et al.
Published: (2024)

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

StreamUni: Achieving Streaming Speech Translation with a Unified Large Speech-Language Model
by: Guo, Shoutao, et al.
Published: (2025)