Image de couverture de livre

Effective and Efficient Mixed Precision Quantization of Speech Foundation Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Xu, Haoning, Li, Zhaoqing, Jin, Zengrui, Wang, Huimeng, Chen, Youjun, Li, Guinan, Geng, Mengzhe, Hu, Shujie, Deng, Jiajun, Liu, Xunying
Format:	Preprint
Publié:	2025
Sujets:	Sound Artificial Intelligence Audio and Speech Processing
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates
par: Xu, Haoning, et autres
Publié: (2025)

Enhancing Pre-trained ASR System Fine-tuning for Dysarthric Speech Recognition using Adversarial Data Augmentation
par: Wang, Huimeng, et autres
Publié: (2024)

Phone-purity Guided Discrete Tokens for Dysarthric Speech Recognition
par: Wang, Huimeng, et autres
Publié: (2025)

One-pass Multiple Conformer and Foundation Speech Systems Compression and Quantization Using An All-in-one Neural Model
par: Li, Zhaoqing, et autres
Publié: (2024)

Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision
par: Li, Zhaoqing, et autres
Publié: (2025)

Structured Speaker-Deficiency Adaptation of Foundation Models for Dysarthric and Elderly Speech Recognition
par: Hu, Shujie, et autres
Publié: (2024)

Towards LLM-Empowered Fine-Grained Speech Descriptors for Explainable Emotion Recognition
par: Chen, Youjun, et autres
Publié: (2025)

Joint Speaker Features Learning for Audio-visual Multichannel Speech Separation and Recognition
par: Li, Guinan, et autres
Publié: (2024)

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition
par: HU, Shujie, et autres
Publié: (2025)

Unfolding A Few Structures for The Many: Memory-Efficient Compression of Conformer and Speech Foundation Models
par: Li, Zhaoqing, et autres
Publié: (2025)

Towards Effective and Efficient Non-autoregressive Decoding Using Block-based Attention Mask
par: Wang, Tianzi, et autres
Publié: (2024)

Regularized Federated Learning for Privacy-Preserving Dysarthric and Elderly Speech Recognition
par: Zhong, Tao, et autres
Publié: (2025)

Self-supervised ASR Models and Features For Dysarthric and Elderly Speech Recognition
par: Hu, Shujie, et autres
Publié: (2024)

Personalized Adversarial Data Augmentation for Dysarthric and Elderly Speech Recognition
par: Jin, Zengrui, et autres
Publié: (2022)

Homogeneous Speaker Features for On-the-Fly Dysarthric and Elderly Speaker Adaptation
par: Geng, Mengzhe, et autres
Publié: (2024)

UNISON: A Unified Sound Generation and Editing Framework via Deep LLM Fusion
par: Li, Zhaoqing, et autres
Publié: (2026)

MOPSA: Mixture of Prompt-Experts Based Speaker Adaptation for Elderly Speech Recognition
par: Deng, Chengxi, et autres
Publié: (2025)

Towards Effective and Efficient Non-autoregressive decoders for Conformer and LLM-based ASR using Block-based Attention Mask
par: Wang, Tianzi, et autres
Publié: (2025)

Exploring Cross-Utterance Speech Contexts for Conformer-Transducer Speech Recognition Systems
par: Cui, Mingyu, et autres
Publié: (2025)

Exploring SSL Discrete Speech Features for Zipformer-based Contextual ASR
par: Cui, Mingyu, et autres
Publié: (2024)

SemaVoice: Semantic-Aware Continuous Autoregressive Speech Synthesis
par: Wang, Huimeng, et autres
Publié: (2026)

Multi-Channel Speech Enhancement for Cocktail Party Speech Emotion Recognition
par: Chen, Youjun, et autres
Publié: (2026)

Empowering Whisper as a Joint Multi-Talker and Target-Talker Speech Recognition System
par: Meng, Lingwei, et autres
Publié: (2024)

Large Language Model Can Transcribe Speech in Multi-Talker Scenarios with Versatile Instructions
par: Meng, Lingwei, et autres
Publié: (2024)

Efficient Adapter Tuning for Joint Singing Voice Beat and Downbeat Tracking with Self-supervised Learning Features
par: Deng, Jiajun, et autres
Publié: (2025)

Autoregressive Speech Synthesis without Vector Quantization
par: Meng, Lingwei, et autres
Publié: (2024)

Variational Auto-Encoder Based Variability Encoding for Dysarthric Speech Recognition
par: Xie, Xurong, et autres
Publié: (2022)

Investigation of Deep Neural Network Acoustic Modelling Approaches for Low Resource Accented Mandarin Speech Recognition
par: Xie, Xurong, et autres
Publié: (2022)

ClariCodec: Optimising Neural Speech Codes for 200bps Communication using Reinforcement Learning
par: Wang, Junyi, et autres
Publié: (2026)

Supporting SENCOTEN Language Documentation Efforts with Automatic Speech Recognition
par: Geng, Mengzhe, et autres
Publié: (2025)

Boosting Large Language Model for Speech Synthesis: An Empirical Study
par: Hao, Hongkun, et autres
Publié: (2023)

Exploring SSL Discrete Tokens for Multilingual ASR
par: Cui, Mingyu, et autres
Publié: (2024)

Exploiting Audio-Visual Features with Pretrained AV-HuBERT for Multi-Modal Dysarthric Speech Reconstruction
par: Chen, Xueyuan, et autres
Publié: (2024)

WavLLM: Towards Robust and Adaptive Speech Large Language Model
par: Hu, Shujie, et autres
Publié: (2024)

ESC: Efficient Speech Coding with Cross-Scale Residual Vector Quantized Transformers
par: Gu, Yuzhe, et autres
Publié: (2024)

USM-Lite: Quantization and Sparsity Aware Fine-tuning for Speech Recognition with Universal Speech Models
par: Ding, Shaojin, et autres
Publié: (2023)

Advanced Long-Content Speech Recognition With Factorized Neural Transducer
par: Gong, Xun, et autres
Publié: (2024)

Outlier Reduction with Gated Attention for Improved Post-training Quantization in Large Sequence-to-sequence Speech Foundation Models
par: Wagner, Dominik, et autres
Publié: (2024)

ZipVoice: Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching
par: Zhu, Han, et autres
Publié: (2025)

Resource-Efficient Adaptation of Speech Foundation Models for Multi-Speaker ASR
par: Wang, Weiqing, et autres
Publié: (2024)