Copertina

Towards Effective and Efficient Non-autoregressive decoders for Conformer and LLM-based ASR using Block-based Attention Mask

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wang, Tianzi, Xie, Xurong, Jin, Zengrui, Geng, Mengzhe, Deng, Jiajun, Li, Zhaoqing, Hu, Shoukang, Hu, Shujie, Li, Guinan, Cui, Mingyu, Meng, Helen, Liu, Xunying
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Audio and Speech Processing
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Towards Effective and Efficient Non-autoregressive Decoding Using Block-based Attention Mask
di: Wang, Tianzi, et al.
Pubblicazione: (2024)

Self-supervised ASR Models and Features For Dysarthric and Elderly Speech Recognition
di: Hu, Shujie, et al.
Pubblicazione: (2024)

One-pass Multiple Conformer and Foundation Speech Systems Compression and Quantization Using An All-in-one Neural Model
di: Li, Zhaoqing, et al.
Pubblicazione: (2024)

Structured Speaker-Deficiency Adaptation of Foundation Models for Dysarthric and Elderly Speech Recognition
di: Hu, Shujie, et al.
Pubblicazione: (2024)

Homogeneous Speaker Features for On-the-Fly Dysarthric and Elderly Speaker Adaptation
di: Geng, Mengzhe, et al.
Pubblicazione: (2024)

Personalized Adversarial Data Augmentation for Dysarthric and Elderly Speech Recognition
di: Jin, Zengrui, et al.
Pubblicazione: (2022)

Enhancing Pre-trained ASR System Fine-tuning for Dysarthric Speech Recognition using Adversarial Data Augmentation
di: Wang, Huimeng, et al.
Pubblicazione: (2024)

Exploring Cross-Utterance Speech Contexts for Conformer-Transducer Speech Recognition Systems
di: Cui, Mingyu, et al.
Pubblicazione: (2025)

Joint Speaker Features Learning for Audio-visual Multichannel Speech Separation and Recognition
di: Li, Guinan, et al.
Pubblicazione: (2024)

Effective and Efficient Mixed Precision Quantization of Speech Foundation Models
di: Xu, Haoning, et al.
Pubblicazione: (2025)

Unfolding A Few Structures for The Many: Memory-Efficient Compression of Conformer and Speech Foundation Models
di: Li, Zhaoqing, et al.
Pubblicazione: (2025)

Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision
di: Li, Zhaoqing, et al.
Pubblicazione: (2025)

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition
di: HU, Shujie, et al.
Pubblicazione: (2025)

Exploring SSL Discrete Speech Features for Zipformer-based Contextual ASR
di: Cui, Mingyu, et al.
Pubblicazione: (2024)

Regularized Federated Learning for Privacy-Preserving Dysarthric and Elderly Speech Recognition
di: Zhong, Tao, et al.
Pubblicazione: (2025)

Phone-purity Guided Discrete Tokens for Dysarthric Speech Recognition
di: Wang, Huimeng, et al.
Pubblicazione: (2025)

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

MOPSA: Mixture of Prompt-Experts Based Speaker Adaptation for Elderly Speech Recognition
di: Deng, Chengxi, et al.
Pubblicazione: (2025)

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates
di: Xu, Haoning, et al.
Pubblicazione: (2025)

UNISON: A Unified Sound Generation and Editing Framework via Deep LLM Fusion
di: Li, Zhaoqing, et al.
Pubblicazione: (2026)

Multi-Channel Speech Enhancement for Cocktail Party Speech Emotion Recognition
di: Chen, Youjun, et al.
Pubblicazione: (2026)

NLE: Non-autoregressive LLM-based ASR by Transcript Editing
di: Dekel, Avihu, et al.
Pubblicazione: (2026)

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

Investigation of Deep Neural Network Acoustic Modelling Approaches for Low Resource Accented Mandarin Speech Recognition
di: Xie, Xurong, et al.
Pubblicazione: (2022)

Variational Auto-Encoder Based Variability Encoding for Dysarthric Speech Recognition
di: Xie, Xurong, et al.
Pubblicazione: (2022)

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

Bayesian Learning for Deep Neural Network Adaptation
di: Xie, Xurong, et al.
Pubblicazione: (2020)

Exploring SSL Discrete Tokens for Multilingual ASR
di: Cui, Mingyu, et al.
Pubblicazione: (2024)

Empowering Whisper as a Joint Multi-Talker and Target-Talker Speech Recognition System
di: Meng, Lingwei, et al.
Pubblicazione: (2024)

LV-CTC: Non-autoregressive ASR with CTC and latent variable models
di: Fujita, Yuya, et al.
Pubblicazione: (2024)

SemaVoice: Semantic-Aware Continuous Autoregressive Speech Synthesis
di: Wang, Huimeng, et al.
Pubblicazione: (2026)

Perceiver-Prompt: Flexible Speaker Adaptation in Whisper for Chinese Disordered Speech Recognition
di: Jiang, Yicong, et al.
Pubblicazione: (2024)

Align-Consistency: Improving Non-autoregressive and Semi-supervised ASR with Consistency Regularization
di: Huang, Wanting, et al.
Pubblicazione: (2026)

A Comprehensive Study on the Effectiveness of ASR Representations for Noise-Robust Speech Emotion Recognition
di: Shi, Xiaohan, et al.
Pubblicazione: (2023)

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis
di: Wu, Chun Yat, et al.
Pubblicazione: (2025)

Leveraging ASR Pretrained Conformers for Speaker Verification through Transfer Learning and Knowledge Distillation
di: Cai, Danwei, et al.
Pubblicazione: (2023)

Loss Masking Is Not Needed in Decoder-only Transformer for Discrete-token-based ASR
di: Chen, Qian, et al.
Pubblicazione: (2023)

Joint decoding method for controllable contextual speech recognition based on Speech LLM
di: Fang, Yangui, et al.
Pubblicazione: (2025)

Audio-Conditioned Diffusion LLMs for ASR and Deliberation Processing
di: Wang, Mengqi, et al.
Pubblicazione: (2025)

Hybrid Attention-based Encoder-decoder Model for Efficient Language Model Adaptation
di: Ling, Shaoshi, et al.
Pubblicazione: (2023)