14.4 A scalable speech recognizer with deep-neural-network acoustic models and voice-activated power gating

2017 IEEE International Solid-State Circuits Conference (ISSCC) Pub Date : 2017-02-01 DOI:10.1109/ISSCC.2017.7870352

Michael Price, James R. Glass, A. Chandrakasan

引用次数: 68

Abstract

The applications of speech interfaces, commonly used for search and personal assistants, are diversifying to include wearables, appliances, and robots. Hardware-accelerated automatic speech recognition (ASR) is needed for scenarios that are constrained by power, system complexity, or latency. Furthermore, a wakeup mechanism, such as voice activity detection (VAD), is needed to power gate the ASR and downstream system. This paper describes IC designs for ASR and VAD that improve on the accuracy, programmability, and scalability of previous work.

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

14.4具有深度神经网络声学模型和声控功率门控的可扩展语音识别器

通常用于搜索和个人助理的语音界面的应用正在多样化，包括可穿戴设备、家电和机器人。对于受功率、系统复杂性或延迟限制的场景，需要硬件加速的自动语音识别(ASR)。此外，需要一个唤醒机制，如语音活动检测(VAD)，为ASR和下游系统供电。本文介绍了ASR和VAD的IC设计，这些设计提高了以前工作的准确性、可编程性和可扩展性。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊

2017 IEEE International Solid-State Circuits Conference (ISSCC)

自引率

0.00%

发文量

期刊最新文献

20.7 A 13.8µW binaural dual-microphone digital ANSI S1.11 filter bank for hearing aids with zero-short-circuit-current logic in 65nm CMOS 21.6 A 12nW always-on acoustic sensing and object recognition microsystem using frequency-domain feature extraction and SVM classification 7.4 A 915MHz asymmetric radio using Q-enhanced amplifier for a fully integrated 3×3×3mm3 wireless sensor node with 20m non-line-of-sight communication 13.5 A 0.35-to-2.6GHz multilevel outphasing transmitter with a digital interpolating phase modulator enabling up to 400MHz instantaneous bandwidth 5.1 A 5×80W 0.004% THD+N automotive multiphase Class-D audio amplifier with integrated low-latency ΔΣ ADCs for digitized feedback after the output filter