Cover Image

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xu, Haoning, Li, Zhaoqing, Chen, Youjun, Wang, Huimeng, Li, Guinan, Geng, Mengzhe, Deng, Chengxi, Liu, Xunying
Format:	Preprint
Published:	2025
Subjects:	Sound Artificial Intelligence Audio and Speech Processing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

Two-pass Endpoint Detection for Speech Recognition
by: Raju, Anirudh, 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)

USM-Lite: Quantization and Sparsity Aware Fine-tuning for Speech Recognition with Universal Speech Models
by: Ding, Shaojin, et al.
Published: (2023)

Efficient Adapter Tuning for Joint Singing Voice Beat and Downbeat Tracking with Self-supervised Learning Features
by: Deng, Jiajun, et al.
Published: (2025)

Supporting SENCOTEN Language Documentation Efforts with Automatic Speech Recognition
by: Geng, Mengzhe, et al.
Published: (2025)

Rate-Aware Learned Speech Compression
by: Xu, Jun, et al.
Published: (2025)

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

Exploiting Audio-Visual Features with Pretrained AV-HuBERT for Multi-Modal Dysarthric Speech Reconstruction
by: Chen, Xueyuan, et al.
Published: (2024)

Outlier Reduction with Gated Attention for Improved Post-training Quantization in Large Sequence-to-sequence Speech Foundation Models
by: Wagner, Dominik, et al.
Published: (2024)

Self-Supervised Speech Quality Assessment (S3QA): Leveraging Speech Foundation Models for a Scalable Speech Quality Metric
by: Ogg, Mattson, et al.
Published: (2025)

ZipVoice: Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching
by: Zhu, Han, et al.
Published: (2025)

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

Analysis of Self-Supervised Speech Models on Children's Speech and Infant Vocalizations
by: Li, Jialu, et al.
Published: (2024)

Statistical Beamformer Exploiting Non-stationarity and Sparsity with Spatially Constrained ICA for Robust Speech Recognition
by: Shin, Ui-Hyeop, et al.
Published: (2023)

Simulating Native Speaker Shadowing for Nonnative Speech Assessment with Latent Speech Representations
by: Geng, Haopeng, et al.
Published: (2024)

Beyond Acoustic Sparsity and Linguistic Bias: A Prompt-Free Paradigm for Mispronunciation Detection and Diagnosis
by: Geng, Haopeng, et al.
Published: (2026)

MeanFlowSE: One-Step Generative Speech Enhancement via MeanFlow
by: Zhu, Yike, et al.
Published: (2025)