Cover Image

Train Short, Infer Long: Speech-LLM Enables Zero-Shot Streamable Joint ASR and Diarization on Long Audio

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Shi, Mohan, Xiao, Xiong, Fan, Ruchao, Ling, Shaoshi, Li, Jinyu
Format:	Preprint
Published:	2025
Subjects:	Audio and Speech Processing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

AlignFormer: Modality Matching Can Achieve Better Zero-shot Instruction-Following Speech-LLM
by: Fan, Ruchao, et al.
Published: (2024)

Efficient Long-Form Speech Recognition for General Speech In-Context Learning
by: Yen, Hao, et al.
Published: (2024)

SOA: Reducing Domain Mismatch in SSL Pipeline by Speech Only Adaptation for Low Resource ASR
by: Shankar, Natarajan Balaji, et al.
Published: (2024)

RLBR: Reinforcement Learning with Biasing Rewards for Contextual Speech Large Language Models
by: Ren, Bo, et al.
Published: (2026)

Benchmarking Children's ASR with Supervised and Self-supervised Speech Foundation Models
by: Fan, Ruchao, et al.
Published: (2024)

Speech Diarization and ASR with GMM
by: Sharma, Aayush Kumar, et al.
Published: (2023)

UniEnc-CASSNAT: An Encoder-only Non-autoregressive ASR for Speech SSL Models
by: Fan, Ruchao, et al.
Published: (2024)

Bengali-Loop: Community Benchmarks for Long-Form Bangla ASR and Speaker Diarization
by: Tabib, H. M. Shadman, et al.
Published: (2026)

A High-Quality and Low-Complexity Streamable Neural Speech Codec with Knowledge Distillation
by: Zhang, En-Wei, et al.
Published: (2025)

Joint Training of Speaker Embedding Extractor, Speech and Overlap Detection for Diarization
by: Pálka, Petr, et al.
Published: (2024)

Prompting Whisper for Joint Speech Transcription and Diarization
by: Zamyrova, Mariia, et al.
Published: (2026)

Advancing Speech Summarization in Multi-modal LLMs with Reinforcement Learning
by: Ling, Shaoshi, et al.
Published: (2025)

End-to-End Joint ASR and Speaker Role Diarization with Child-Adult Interactions
by: Xu, Anfeng, et al.
Published: (2026)

A Toolkit for Joint Speaker Diarization and Identification with Application to Speaker-Attributed ASR
by: Morrone, Giovanni, et al.
Published: (2024)

PixIT: Joint Training of Speaker Diarization and Speech Separation from Real-world Multi-speaker Recordings
by: Kalda, Joonas, et al.
Published: (2024)

DM-ASR: Diarization-aware Multi-speaker ASR with Large Language Models
by: Li, Li, et al.
Published: (2026)

Towards Efficient Speech-Text Jointly Decoding within One Speech Language Model
by: Wu, Haibin, et al.
Published: (2025)

LibriheavyMix: A 20,000-Hour Dataset for Single-Channel Reverberant Multi-Talker Speech Separation, ASR and Speaker Diarization
by: Jin, Zengrui, et al.
Published: (2024)

LCB-net: Long-Context Biasing for Audio-Visual Speech Recognition
by: Yu, Fan, et al.
Published: (2024)

Customizing Speech Recognition Model with Large Language Model Feedback
by: Ling, Shaoshi, et al.
Published: (2025)

SwanVoice: Expressive Long-Form Zero-Shot Speech Synthesis for Both Monologue and Dialogue
by: Li, Ruiqi, et al.
Published: (2026)

StreamVoice: Streamable Context-Aware Language Modeling for Real-time Zero-Shot Voice Conversion
by: Wang, Zhichao, et al.
Published: (2024)

CHSER: A Dataset and Case Study on Generative Speech Error Correction for Child ASR
by: Shankar, Natarajan Balaji, et al.
Published: (2025)

Comparing Unsupervised and Supervised Semantic Speech Tokens: A Case Study of Child ASR
by: Shi, Mohan, et al.
Published: (2025)

FairASR: Fair Audio Contrastive Learning for Automatic Speech Recognition
by: Kim, Jongsuk, et al.
Published: (2025)

Prompt Amplification and Zero-Shot Late Fusion in Audio-Language Models for Speech Emotion Recognition
by: Kataria, Saurabh, et al.
Published: (2026)

TagSpeech: End-to-End Multi-Speaker ASR and Diarization with Fine-Grained Temporal Grounding
by: Huo, Mingyue, et al.
Published: (2026)

Diffusion-based Generative Modeling with Discriminative Guidance for Streamable Speech Enhancement
by: Li, Chenda, et al.
Published: (2024)

LLM-ForcedAligner: A Non-Autoregressive and Accurate LLM-Based Forced Aligner for Multilingual and Long-Form Speech
by: Mu, Bingshen, et al.
Published: (2026)

DiariST: Streaming Speech Translation with Speaker Diarization
by: Yang, Mu, et al.
Published: (2023)

Doctor or Patient? Synergizing Diarization and ASR for Code-Switched Hinglish Medical Conditions Extraction
by: Baroudi, Séverin, et al.
Published: (2026)

Mind the Gap: Impact of Synthetic Conversational Data on Multi-Talker ASR and Speaker Diarization
by: Polok, Alexander, et al.
Published: (2026)

SLM-S2ST: A multimodal language model for direct speech-to-speech translation
by: Hu, Yuxuan, et al.
Published: (2025)

CTC-GMM: CTC guided modality matching for fast and accurate streaming speech translation
by: Zhao, Rui, et al.
Published: (2024)

Incremental Disentanglement for Environment-Aware Zero-Shot Text-to-Speech Synthesis
by: Lu, Ye-Xin, et al.
Published: (2024)

FireRedTTS-1S: An Upgraded Streamable Foundation Text-to-Speech System
by: Guo, Hao-Han, et al.
Published: (2025)

HALL-E: Hierarchical Neural Codec Language Model for Minute-Long Zero-Shot Text-to-Speech Synthesis
by: Nishimura, Yuto, et al.
Published: (2024)

Target Speech Diarization with Multimodal Prompts
by: Jiang, Yidi, et al.
Published: (2024)

ASR-Synchronized Speaker-Role Diarization
by: Ghosh, Arindam, et al.
Published: (2025)

LSTMSE-Net: Long Short Term Speech Enhancement Network for Audio-visual Speech Enhancement
by: Jain, Arnav, et al.
Published: (2024)