arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2301.00652eess.AScs.CL
收藏

基于低位量化的高效语音表示学习

Efficient Speech Representation Learning with Low-Bit Quantization

Meta AI

Ching-Feng Yeh, Wei-Ning Hsu, Paden Tomasello, Abdelrahman Mohamed

摘要:

随着机器学习硬件的发展,更新的模型通常以增加的尺寸和计算复杂性为代价。在努力提高这些模型的效率,我们应用和研究最近的量化技术的语音表示学习模型。在SUPERB基准上对量化技术进行了评估。在ASR任务中,通过积极量化到1位,我们实现了86.32%的存储减少(184.42 -> 25.23),88%的估计运行时间减少(1.00 -> 0.12),同时增加了字错误率(7.06 -> 15.96)。与同样致力于模型压缩的DistillHuBERT相比,2位配置产生了更小的存储(35.84 vs. 46.98),更好的字错误率(12.68 vs. 13.37)和更有效的估计运行时间(0.15 vs. 0.73)。

英文摘要:

With the development of hardware for machine learning, newer models often come at the cost of both increased sizes and computational complexity. In effort to improve the efficiency for these models, we apply and investigate recent quantization techniques on speech representation learning models. The quantization techniques were evaluated on the SUPERB benchmark. On the ASR task, with aggressive quantization to 1 bit, we achieved 86.32% storage reduction (184.42 -> 25.23), 88% estimated runtime reduction (1.00 -> 0.12) with increased word error rate (7.06 -> 15.96). In comparison with DistillHuBERT which also aims for model compression, the 2-bit configuration yielded slightly smaller storage (35.84 vs. 46.98), better word error rate (12.68 vs. 13.37) and more efficient estimated runtime (0.15 vs. 0.73).

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑