PulseAugur
EN
LIVE 11:11:39

Speech models compressed using parameter clustering

By PulseAugur Editorial · [2 sources] ·

Researchers have developed a new method for compressing speech foundation models without requiring additional data or retraining. This approach utilizes channelwise clustering with k-means to achieve parameter compression, exploring mixed sparsity pruning by varying the number of clusters per layer. Experiments on LibriSpeech demonstrated significant word error rate (WER) reductions compared to magnitude-based pruning on models like HuBERT-large and Whisper-large-v3, even with substantial sparsity levels. AI

IMPACT This compression technique could enable more efficient deployment of large speech models on resource-constrained devices.

RANK_REASON The cluster contains an academic paper detailing a new research method for model compression.

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

COVERAGE [2]

  1. arXiv cs.AI TIER_1 English(EN) · Haoning Xu, Zhaoqing Li, Huimeng Wang, Youjun Chen, Chengxi Deng, Mengzhe Geng, Xunying Liu ·

    Towards Data-free and Training-free Compression for Speech Foundation Models Using Parameter Clustering

    arXiv:2606.11836v1 Announce Type: cross Abstract: This paper presents a novel data-free and training-free compression approach for speech foundation models using channelwise clustering via k-means. More fine-grained, mixed sparsity pruning by layer-level varying number of paramet…

  2. arXiv cs.AI TIER_1 English(EN) · Xunying Liu ·

    Towards Data-free and Training-free Compression for Speech Foundation Models Using Parameter Clustering

    This paper presents a novel data-free and training-free compression approach for speech foundation models using channelwise clustering via k-means. More fine-grained, mixed sparsity pruning by layer-level varying number of parameter clusters is also explored. Experiments conducte…

RELATED ENTITIES

RELATED TOPICS