Comparing human and machine speech recognition in noise with QuickSIN

Author:

Slaney Malcolm1ORCID,Fitzgerald Matthew B.2ORCID

Affiliation:

1. Center for Computer Research in Music and Acoustics, Stanford University 1 , Stanford, California 94305, USA

2. Department of Otolaryngology—Head and Neck Surgery, Stanford University 2 , Stanford, California 94305, USA malcolm@ieee.org , fitzmb@stanford.edu

Abstract

A test is proposed to characterize the performance of speech recognition systems. The QuickSIN test is used by audiologists to measure the ability of humans to recognize continuous speech in noise. This test yields the signal-to-noise ratio at which individuals can correctly recognize 50% of the keywords in low-context sentences. It is argued that a metric for automatic speech recognizers will ground the performance of automatic speech-in-noise recognizers to human abilities. Here, it is demonstrated that the performance of modern recognizers, built using millions of hours of unsupervised training data, is anywhere from normal to mildly impaired in noise compared to human participants.

Publisher

Acoustical Society of America (ASA)

Reference24 articles.

1. Etymotic Research, Inc. (2001). “ QuickSIN™ Speech-in-Noise Test (product page),” available at https://www.etymotic.com/product/quicksin/ (Last viewed September 2, 2024).

2. QuickSIN™ Speech-in-Noise Test (user manual);Etymotic Research, Inc,2006

3. Preliminary guidelines for replacing word-recognition in quiet with speech in noise assessment in the routine audiologic test battery;Ear Hear.,2023

4. Speech-in-noise assessment in the routine audiologic test battery: Relationship to perceived auditory disability;Ear Hear.,2024

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3