Running LSTM neural networks on an Imagination NNA
January 8, 2021
Speech recognition has become more relevant in recent years: it enables computers to translate spoken language into text. It can be found in different types of applications, such as translators or closed captioning. An example of this technology is Mozilla’s DeepSpeech, an open-source speech-to-text engine, which uses a model trained by machine learning techniques based on Baidu’s Deep Speech research paper. We are going to provide an overview of how we are running version 0.5.1 of this model, by accelerating a static LSTM network on the Imagination neural network accelerator (NNA), with the goal of creating a prototype of a voice assistant for an automotive use case.
To read the full article, click here
Related Blogs
- Why the PowerVR 2NX NNA is the future of neural net acceleration
- Self-Compressing Neural Networks
- ChiPy®: Bridge Neural Networks and C++ on Silicon — Full Inference Pipelines with Zero CPU Round-Trips
- Efficient inference on IMG Series4 NNAs
Latest Blogs
- Embedded Security explained: Advanced Encryption Standard (AES)
- Cadence Demonstrates PCIe 8.0 PHY at PCI-SIG DevCon 2026
- Cadence Achieves Successful Silicon Validation of 1st IP Test Chips on Intel 18A
- From Classical CAN and CAN FD to CAN XL: Functional Safety and Security for Next-Generation In-Vehicle Communication
- Accelerating Embedded Memory Performance with 16-bit xSPI PSRAM IP