# An 8.93 TOPS/W LSTM Recurrent Neural Network Accelerator Featuring Hierarchical Coarse-Grain Sparsity for On-Device Speech Recognition

> Research article (IEEE Journal of Solid-State Circuits, 2020) · cited 60× · AI/ML

**Wikidata**: [openalex:W3027324516](https://www.wikidata.org/wiki/openalex:W3027324516)  
**Source**: https://4ort.xyz/entity/an-8-93-tops-w-lstm-recurrent-neural-network-accelerator-featuring-hierarchical-coarse-grain-sparsity-for-on-device-spee