arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.05784cs.SDeess.AS
收藏

用于智能设备的极低占用空间端到端ASR系统

Extremely Low Footprint End-to-End ASR System for Smart Device

Alibaba Group(阿里巴巴集团);Singapore Institute of Technology(新加坡理工大学)

Zhifu Gao, Yiwu Yao, Shiliang Zhang, Jun Yang, Ming Lei, Ian McLoughlin

摘要:

最近,端到端(E2 E)语音识别已经变得流行,因为它可以将声学、发音和语言模型集成到单个神经网络中,该单个神经网络优于传统模型。在E2 E方法中,基于注意力的模型(例如,Transformer)已经显现为优越的。这些模型为在智能设备上部署ASR打开了大门,但是它们仍然需要大量的模型参数。我们提出了一种适用于智能设备的极低占用空间的E2 E ASR系统,以实现在不牺牲识别准确性的情况下满足资源限制的目标。我们设计了跨层权重共享以提高参数效率,并进一步利用包括稀疏化和量化在内的模型压缩方法,以减少内存存储并提高解码效率。我们在公共AISHELL-1和AISHELL-2基准上评估我们的方法。在AISHELL-2任务上,所提出的方法实现了超过10倍的压缩(模型大小从248 MB减少到24 MB),代价是只有很小的性能损失(CER从6.49%减少到6.92%)。

英文摘要:

Recently, end-to-end (E2E) speech recognition has become popular, since it can integrate the acoustic, pronunciation and language models into a single neural network, which outperforms conventional models. Among E2E approaches, attention-based models, e.g. Transformer, have emerged as being superior. Such models have opened the door to deployment of ASR on smart devices, however they still suffer from requiring a large number of model parameters. We propose an extremely low footprint E2E ASR system for smart devices, to achieve the goal of satisfying resource constraints without sacrificing recognition accuracy. We design cross-layer weight sharing to improve parameter efficiency and further exploit model compression methods including sparsification and quantization, to reduce memory storage and boost decoding efficiency. We evaluate our approaches on the public AISHELL-1 and AISHELL-2 benchmarks. On the AISHELL-2 task, the proposed method achieves more than 10x compression (model size reduces from 248 to 24MB), at the cost of only minor performance loss (CER reduces from 6.49% to 6.92%).

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。

↑