针对语音模型低比特量化中的激活范围大问题，提出进化策略校准方法。
Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models
- 用进化策略将激活缩放建模为优化问题，分两步求解。
- 实现全INT8量化无性能损失，全INT4量化接近无损。
- 适合追求高精度低比特语音模型部署的研究者。
量化已成为语音处理系统高效部署的关键技术。尽管研究广泛，但多数现有方法针对视觉和自然语言处理架构设计，忽视了音频信号的特殊挑战。我们发现，音频激活值可能具有极大动态范围，导致标准校准技术造成显著信息丢失。为此，提出基于进化策略的校准方法ESC，将激活缩放建模为优化问题，并采用由进化策略驱动的两阶段局部-全局求解方案。ESC在全INT8量化下保持性能不变，是首个在多个语音任务中实现全INT4量化近似无损的校准方法。结合训练后量化（PTQ）方法进一步降低性能损失，在AST模型上仅产生1%相对准确率下降。
原文摘要 · Abstract (English)
Quantization has become essential for the efficient deployment of speech processing systems. Although widely studied, most existing quantization methods were developed for vision and NLP architectures, while the specific challenges of audio signals remain largely overlooked. In particular, we show that audio activations can exhibit large calibration ranges, leading to significant information loss when standard calibration techniques are applied. To address this, we propose ESC, an Evolution Strategy-based Calibration method that formulates activation scaling as an optimization problem and solves it using a two-step local-global scheme driven by an evolution strategy. ESC enables unaltered performance under full INT8 quantization and is the first calibration method to achieve near-lossless performance for full INT4 quantization across multiple speech tasks. Integrating ESC with PTQ methods further reduces performance loss, achieving a 1% relative accuracy degradation on the AST model.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。