Cover Image

Towards Fine-Grained Multi-Dimensional Speech Understanding: Data Pipeline, Benchmark, and Model

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Guojian, Zhao, Zhixian, Lin, Zhennan, Hu, Jingbin, Zhan, Qirui, Cao, Yuang, Xie, Pengyuan, Xie, Chuan, Liu, Jie, Zhang, Qiang, Fu, Zhonghua, Xie, Lei
Format:	Preprint
Published:	2026
Subjects:	Audio and Speech Processing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

MINT-Bench: A Comprehensive Multilingual Benchmark for Instruction-Following Text-to-Speech
by: Chen, Huakang, et al.
Published: (2026)

OmniCodec: Low Frame Rate Universal Audio Codec with Semantic-Acoustic Disentanglement
by: Hu, Jingbin, et al.
Published: (2026)

Speaker-Reasoner: Scaling Interaction Turns and Reasoning Patterns for Timestamped Speaker-Attributed ASR
by: Lin, Zhennan, et al.
Published: (2026)

Serial-Parallel Dual-Path Architecture for Speaking Style Recognition
by: Li, Guojian, et al.
Published: (2025)

EmoOmni: Bridging Emotional Understanding and Expression in Omni-Modal LLMs
by: Tian, Wenjie, et al.
Published: (2026)

Towards Building Speech Large Language Models for Multitask Understanding in Low-Resource Languages
by: Shao, Mingchen, et al.
Published: (2025)

FleSpeech: Flexibly Controllable Speech Generation with Various Prompts
by: Li, Hanzhao, et al.
Published: (2025)

VoiceSculptor: Your Voice, Designed By You
by: Hu, Jingbin, et al.
Published: (2026)

OSUM: Advancing Open Speech Understanding Models with Limited Resources in Academia
by: Geng, Xuelong, et al.
Published: (2025)

Towards Fine-Grained and Multi-Granular Contrastive Language-Speech Pre-training
by: Yang, Yifan, et al.
Published: (2026)

UrduSpeech: A 156-Hour Urdu Speech Corpus with 12-Dimension Paralinguistic Annotations
by: Haq, Attia Nafees ul, et al.
Published: (2026)

MSU-Bench: Towards Understanding the Conversational Multi-talker Scenarios
by: Wang, Shuai, et al.
Published: (2025)

Seeing the Context: Rich Visual Context-Aware Speech Recognition via Multimodal Reasoning
by: Tian, Wenjie, et al.
Published: (2026)

Full-Duplex Interaction in Spoken Dialogue Systems: A Comprehensive Study from the ICASSP 2026 HumDial Challenge
by: Wang, Chengyou, et al.
Published: (2026)

dLLM-ASR: A Faster Diffusion LLM-based Framework for Speech Recognition
by: Tian, Wenjie, et al.
Published: (2026)

EchoFree: Towards Ultra Lightweight and Efficient Neural Acoustic Echo Cancellation
by: Li, Xingchen, et al.
Published: (2025)

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

CAMEL: Cross-Attention Enhanced Mixture-of-Experts and Language Bias for Code-Switching Speech Recognition
by: Wang, He, et al.
Published: (2024)

Contextualized Automatic Speech Recognition with Dynamic Vocabulary Prediction and Activation
by: Lin, Zhennan, et al.
Published: (2025)

WenetSpeech-Wu: Datasets, Benchmarks, and Models for a Unified Chinese Wu Dialect Speech Processing Ecosystem
by: Wang, Chengyou, et al.
Published: (2026)

Towards LLM-Empowered Fine-Grained Speech Descriptors for Explainable Emotion Recognition
by: Chen, Youjun, et al.
Published: (2025)

TTS-PRISM: A Perceptual Reasoning and Interpretable Speech Model for Fine-Grained Diagnosis
by: Wang, Xi, et al.
Published: (2026)

SoulX-Transcriber: A Robust End-to-End Framework for Multi-Speaker Speech Transcription
by: Dai, Yuhang, et al.
Published: (2026)

FireRedTTS-2: Towards Long Conversational Speech Generation for Podcast and Chatbot
by: Xie, Kun, et al.
Published: (2025)

XEmoRAG: Cross-Lingual Emotion Transfer with Controllable Intensity Using Retrieval-Augmented Generation
by: Zuo, Tianlun, et al.
Published: (2025)

Listening with Time: Precise Temporal Awareness for Long-Form Audio Understanding
by: Shao, Mingchen, et al.
Published: (2026)

Position: Towards Responsible Evaluation for Text-to-Speech
by: Yang, Yifan, et al.
Published: (2025)

Toward Natural Emotional Text-To-Speech System with Fine-Grained Non-Verbal Expression Control
by: Zhou, Wangzixi, et al.
Published: (2026)

UltraVoice: Scaling Fine-Grained Style-Controlled Speech Conversations for Spoken Dialogue Models
by: Tu, Wenming, et al.
Published: (2025)

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

HumDial-EIBench: A Human-Recorded Multi-Turn Emotional Intelligence Benchmark for Audio Language Models
by: Wang, Shuiyuan, et al.
Published: (2026)

SenSE: Semantic-Aware High-Fidelity Universal Speech Enhancement
by: Li, Xingchen, et al.
Published: (2025)

Fine-Grained and Interpretable Neural Speech Editing
by: Morrison, Max, et al.
Published: (2024)

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

Fine-grained Preference Optimization Improves Zero-shot Text-to-Speech
by: Yao, Jixun, et al.
Published: (2025)

Steering Language Model to Stable Speech Emotion Recognition via Contextual Perception and Chain of Thought
by: Zhao, Zhixian, et al.
Published: (2025)

Speaking from Coarse to Fine: Improving Neural Codec Language Model via Multi-Scale Speech Coding and Generation
by: Guo, Haohan, et al.
Published: (2024)

WenetSpeech4TTS: A 12,800-hour Mandarin TTS Corpus for Large Speech Generation Model Benchmark
by: Ma, Linhan, et al.
Published: (2024)

A Scalable Pipeline for Enabling Non-Verbal Speech Generation and Understanding
by: Ye, Runchuan, et al.
Published: (2025)

Fine-Grained Quantitative Emotion Editing for Speech Generation
by: Inoue, Sho, et al.
Published: (2024)