Cover Image

Delayed-KD: Delayed Knowledge Distillation based CTC for Low-Latency Streaming ASR

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Longhao, Li, Yangze, Xue, Hongfei, Liu, Jie, Fang, Shuai, Wang, Kai, Xie, Lei
Format:	Preprint
Published:	2025
Subjects:	Sound Audio and Speech Processing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Unveiling the Potential of LLM-Based ASR on Chinese Open-Source Datasets
by: Geng, Xuelong, et al.
Published: (2024)

FastTurn: Unifying Acoustic and Streaming Semantic Cues for Low-Latency and Robust Turn Detection
by: Wang, Chengyou, et al.
Published: (2026)

kNN-CTC: Enhancing ASR via Retrieval of CTC Pseudo Labels
by: Zhou, Jiaming, et al.
Published: (2023)

Selective Invocation for Multilingual ASR: A Cost-effective Approach Adapting to Speech Recognition Difficulty
by: Xue, Hongfei, et al.
Published: (2025)

Ideal-LLM: Integrating Dual Encoders and Language-Adapted LLM for Multilingual Speech-to-Text
by: Xue, Hongfei, et al.
Published: (2024)

SynthVC: Leveraging Synthetic Data for End-to-End Low Latency Streaming Voice Conversion
by: Guo, Zhao, et al.
Published: (2025)

A Transcription Prompt-based Efficient Audio Large Language Model for Robust Speech Recognition
by: Li, Yangze, et al.
Published: (2024)

CUSIDE-T: Chunking, Simulating Future and Decoding for Transducer based Streaming ASR
by: Zhao, Wenbo, et al.
Published: (2024)

Fast Streaming Transducer ASR Prototyping via Knowledge Distillation with Whisper
by: Thorbecke, Iuliia, et al.
Published: (2024)

Unimodal Aggregation for CTC-based Speech Recognition
by: Fang, Ying, et al.
Published: (2023)

NTC-KWS: Noise-aware CTC for Robust Keyword Spotting
by: Xi, Yu, et al.
Published: (2024)

Analyzing the Importance of Blank for CTC-Based Knowledge Distillation
by: Hilmes, Benedikt, et al.
Published: (2025)

Mamba for Streaming ASR Combined with Unimodal Aggregation
by: Fang, Ying, et al.
Published: (2024)

Efficient Scaling for LLM-based ASR
by: Mu, Bingshen, et al.
Published: (2025)

CTC Blank Triggered Dynamic Layer-Skipping for Efficient CTC-based Speech Recognition
by: Hou, Junfeng, et al.
Published: (2024)

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

A Language-Agnostic Hierarchical LoRA-MoE Architecture for CTC-based Multilingual ASR
by: Zheng, Yuang, et al.
Published: (2026)

Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM
by: Wang, Xiong, et al.
Published: (2024)

Streaming Endpointer for Spoken Dialogue using Neural Audio Codecs and Label-Delayed Training
by: Udupa, Sathvik, et al.
Published: (2025)

CJST: CTC Compressor based Joint Speech and Text Training for Decoder-Only ASR
by: Zhou, Wei, et al.
Published: (2024)

Weakly Supervised Data Refinement and Flexible Sequence Compression for Efficient Thai LLM-based ASR
by: Shao, Mingchen, et al.
Published: (2025)

StreamVC: Real-Time Low-Latency Voice Conversion
by: Yang, Yang, et al.
Published: (2024)

SQ-Whisper: Speaker-Querying based Whisper Model for Target-Speaker ASR
by: Guo, Pengcheng, et al.
Published: (2024)

MMGER: Multi-modal and Multi-granularity Generative Error Correction with LLM for Joint Accent and Speech Recognition
by: Mu, Bingshen, et al.
Published: (2024)

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

DualVC 2: Dynamic Masked Convolution for Unified Streaming and Non-Streaming Voice Conversion
by: Ning, Ziqian, et al.
Published: (2023)

Scaling Multi-Talker ASR with Speaker-Agnostic Activity Streams
by: He, Xiluo, et al.
Published: (2025)

Boosting CTC-Based ASR Using LLM-Based Intermediate Loss Regularization
by: Altinok, Duygu
Published: (2025)

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

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

Llasa+: Free Lunch for Accelerated and Streaming Llama-Based Speech Synthesis
by: Tian, Wenjie, et al.
Published: (2025)

Integrated Multi-Level Knowledge Distillation for Enhanced Speaker Verification
by: Yang, Wenhao, et al.
Published: (2024)

Comparative Analysis of Fast and High-Fidelity Neural Vocoders for Low-Latency Streaming Synthesis in Resource-Constrained Environments
by: Yoneyama, Reo, et al.
Published: (2025)

Lightweight Target-Speaker-Based Overlap Transcription for Practical Streaming ASR
by: Pražák, Aleš, et al.
Published: (2025)

Enhancing Non-Core Language Instruction-Following in Speech LLMs via Semi-Implicit Cross-Lingual CoT Reasoning
by: Xue, Hongfei, et al.
Published: (2025)

BLSP-KD: Bootstrapping Language-Speech Pre-training via Knowledge Distillation
by: Wang, Chen, et al.
Published: (2024)

LL-SDR: Low-Latency Speech enhancement through Discrete Representations
by: Li, Jingyi, et al.
Published: (2026)

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

HDMoLE: Mixture of LoRA Experts with Hierarchical Routing and Dynamic Thresholds for Fine-Tuning LLM-based ASR Models
by: Mu, Bingshen, et al.
Published: (2024)

WCTC-Biasing: Retraining-free Contextual Biasing ASR with Wildcard CTC-based Keyword Spotting and Inter-layer Biasing
by: Nakagome, Yu, et al.
Published: (2025)