Cover Image

Joint decoding method for controllable contextual speech recognition based on Speech LLM

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Fang, Yangui, Peng, Jing, Xi, Yu, Li, Xu, Li, Haoyu, Zhang, Chengwei, Zhong, Guohui, Yu, Kai
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

Low-Resource Domain Adaptation for Speech LLMs via Text-Only Fine-Tuning
by: Fang, Yangui, et al.
Published: (2025)

Fewer Hallucinations, More Verification: A Three-Stage LLM-Based Framework for ASR Error Correction
by: Fang, Yangui, et al.
Published: (2025)

MOSA: Mixtures of Simple Adapters Outperform Monolithic Approaches in LLM-based Multilingual ASR
by: Li, Junjie, et al.
Published: (2025)

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

TC-BiMamba: Trans-Chunk bidirectionally within BiMamba for unified streaming and non-streaming ASR
by: She, Qingshun, et al.
Published: (2026)

A Survey on Speech Large Language Models for Understanding
by: Peng, Jing, et al.
Published: (2024)

An efficient text augmentation approach for contextualized Mandarin speech recognition
by: Zheng, Naijun, et al.
Published: (2024)

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

Voxtlm: unified decoder-only models for consolidating speech recognition/synthesis and speech/text continuation tasks
by: Maiti, Soumi, et al.
Published: (2023)

Graph-based multi-Feature fusion method for speech emotion recognition
by: Liu, Xueyu, et al.
Published: (2024)

Neural Directed Speech Enhancement with Dual Microphone Array in High Noise Scenario
by: Wen, Wen, et al.
Published: (2024)

Advancing LLM-based phoneme-to-grapheme for multilingual speech recognition
by: Dong, Lukuang, et al.
Published: (2026)

Exploring the limits of decoder-only models trained on public speech recognition corpora
by: Gupta, Ankit, et al.
Published: (2024)

XCB: an effective contextual biasing approach to bias cross-lingual phrases in speech recognition
by: Wan, Xucheng, et al.
Published: (2024)

Comparison of linear and nonlinear methods for decoding selective attention to speech from ear-EEG recordings
by: Thornton, Mike, et al.
Published: (2024)

Language model integration based on memory control for sequence to sequence speech recognition
by: Cho, Jaejin, et al.
Published: (2018)

LLM-based phoneme-to-grapheme for phoneme-based speech recognition
by: Ma, Te, et al.
Published: (2025)

Phoneme-based speech recognition driven by large language models and sampling marginalization
by: Ma, Te, et al.
Published: (2025)

TDT-KWS: Fast And Accurate Keyword Spotting Using Token-and-duration Transducer
by: Xi, Yu, et al.
Published: (2024)

Masked Self-distilled Transducer-based Keyword Spotting with Semi-autoregressive Decoding
by: Xi, Yu, et al.
Published: (2025)

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

Self-supervised speech representation and contextual text embedding for match-mismatch classification with EEG recording
by: Wang, Bo, et al.
Published: (2024)

MFA-KWS: Effective Keyword Spotting with Multi-head Frame-asynchronous Decoding
by: Xi, Yu, et al.
Published: (2025)

MELA-TTS: Joint transformer-diffusion model with representation alignment for speech synthesis
by: An, Keyu, et al.
Published: (2025)

Contrastive Learning With Audio Discrimination For Customizable Keyword Spotting In Continuous Speech
by: Xi, Yu, et al.
Published: (2024)

Prominence-aware automatic speech recognition for conversational speech
by: Linke, Julian, et al.
Published: (2025)

Streaming Keyword Spotting Boosted by Cross-layer Discrimination Consistency
by: Xi, Yu, et al.
Published: (2024)

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

Enhancing CTC-based speech recognition with diverse modeling units
by: Han, Shiyi, et al.
Published: (2024)

Detect, Attend and Extract: Keyword Guided Target Speaker Extraction
by: Li, Haoyu, et al.
Published: (2026)

Paraformer-v2: An improved non-autoregressive transformer for noise-robust speech recognition
by: An, Keyu, et al.
Published: (2024)

Towards Effective and Efficient Non-autoregressive decoders for Conformer and LLM-based ASR using Block-based Attention Mask
by: Wang, Tianzi, et al.
Published: (2025)

Robust fine-tuning of speech recognition models via model merging: application to disordered speech
by: Ducorroy, Alexandre, et al.
Published: (2025)

Teaching the Teachers: Boosting unsupervised domain adaptation in speech recognition by ensemble update
by: Ahmad, Rehan, et al.
Published: (2026)

AS-70: A Mandarin stuttered speech dataset for automatic speech recognition and stuttering event detection
by: Gong, Rong, et al.
Published: (2024)

SpecASR: Accelerating LLM-based Automatic Speech Recognition via Speculative Decoding
by: Wei, Linye, et al.
Published: (2025)

BabAR: from phoneme recognition to developmental measures of young children's speech production
by: Lavechin, Marvin, et al.
Published: (2026)

Improving child speech recognition with augmented child-like speech
by: Zhang, Yuanyuan, et al.
Published: (2024)

PROCTER: PROnunciation-aware ConTextual adaptER for personalized speech recognition in neural transducers
by: Pandey, Rahul, et al.
Published: (2023)

Balancing Speech Understanding and Generation Using Continual Pre-training for Codec-based Speech LLM
by: Shi, Jiatong, et al.
Published: (2025)