Performance and Efficiency Evaluation of ASR Inference on the Edge

Electronics (MDPI) Journal


Automatic speech recognition, a process of converting speech signals to text, has improved a great deal in the past decade thanks to the deep learning based systems. With the latest transformer based models, the recognition accuracy measured as word-error-rate (WER), is even below the human annotator error (4%). However, most of these advanced models run on big servers with large amounts of memory, CPU/GPU resources and have huge carbon footprint. This server based architecture of ASR is not viable in the long run given the inherent lack of privacy for user data, reliability and latency issues of the network connection. On the other hand, on-device ASR (meaning, speech to text conversion on the edge device itself) solutions will fix deep-rooted privacy issues while at same time being more reliable and performant by avoiding network connectivity to the backend server. On-device ASR can also lead to a more sustainable solution by considering the energy vs. accuracy trade-off and choosing right model for specific use cases/applications of the product. Hence, in this paper we evaluate energy-accuracy trade-off of ASR with a typical transformer based speech recognition model on an edge device. We have run evaluations on Raspberry Pi with an off-the-shelf USB meter for measuring energy consumption. We conclude that, in the case of CPU based ASR inference, the energy consumption grows exponentially as the word error rate improves linearly. Additionally, based on our experiment we deduce that, with PyTorch mobile optimization and quantization, the typical transformer based ASR on edge performs reasonably well in terms of accuracy and latency and comes close to the accuracy of server based inference.

Related Publications

All Publications

Electronics (MDPI) Journal - November 4, 2021

Performance Evaluation of Offline Speech Recognition on Edge Devices

Santosh Gondi, Vineel Pratap

EMNLP Conference on Machine Translation (WMT) - October 1, 2020

BERGAMOT-LATTE Submissions for the WMT20 Quality Estimation Shared Task

Marina Fomicheva, Shuo Sun, Lisa Yankovskaya, Frédéric Blain, Vishrav Chaudhary, Mark Fishel, Francisco Guzmán, Lucia Specia

WMT - November 8, 2021

Findings of the WMT 2021 Shared Task on Large-Scale Multilingual Machine Translation

Guillaume Wenzek, Vishrav Chaudhary, Angela Fan, Sahir Gomez, Naman Goyal, Somya Jain, Douwe Kiela, Tristan Thrush, Francisco Guzmán

Natural Language Processing for Indigenous Languages of the Americas (AmericasNLP) at NAACL - July 1, 2021

Findings of the AmericasNLP 2021 Shared Task on Open Machine Translation for Indigenous Languages of the Americas

Manuel Mager, Arturo Oncevay, Abteen Ebrahimi, John Ortega, Annette Rios, Angela Fan, Ximena Gutierrez-Vasques, Luis Chiruzzo, Gustavo A. Giménez-Lugo, Ricardo Ramos, Ivan Vladimir Meza Ruiz, Rolando Coto-Solano, Alexis Palmer, Elisabeth Mager, Vishrav Chaudhary, Graham Neubig, Ngoc Thang Vu, Katharina Kann

To help personalize content, tailor and measure ads, and provide a safer experience, we use cookies. By clicking or navigating the site, you agree to allow our collection of information on and off Facebook through cookies. Learn more, including about available controls: Cookie Policy