[논문]Counterfactually Fair Automatic Speech Recognition

Sarı, Leda; Hasegawa-Johnson, Mark; Yoo, Chang D.

doi:10.1109/taslp.2021.3126949

[해외논문] Counterfactually Fair Automatic Speech Recognition 원문보기

IEEE/ACM transactions on audio, speech, and language processing, v.29, 2021년, pp.3515 - 3525

Sarı, Leda (University of Illinois at Urbana-Champaign, Department of Electrical and Computer Engineering, Urbana, IL, USA) , Hasegawa-Johnson, Mark (KAIST, Daejeon, Korea) , Yoo, Chang D.

Abstract ▼ AI-Helper

Widelyused automatic speech recognition (ASR) systems have been empirically demonstrated in various studies to be unfair, having higher error rates for some groups of users than others. One way to define fairness in ASR is to require that changing the demographic group affiliation of any individual (e.g., changing their gender, age, education or race) should not change the probability distribution across possible speech-to-text transcriptions. In the paradigm of counterfactual fairness, all variables independent of group affiliation (e.g., the text being read by the speaker) remain unchanged, while variables dependent on group affiliation (e.g., the speaker’s voice) are counterfactually modified. Hence, we approach the fairness of ASR by training the ASR to minimize change in its outcome probabilities despite a counterfactual change in the individual’s demographic attributes. Starting from the individualized counterfactual equal odds criterion, we provide relaxations to it and compare their performances for connectionist temporal classification (CTC) based end-to-end ASR systems. We perform our experiments on the Corpus of Regional African American Language (CORAAL) and the LibriSpeech dataset to accommodate for differences due to gender, age, education, and race. We show that with counterfactual training, we can reduce average character error rates while achieving lower performance gap between demographic groups, and lower error standard deviation among individuals.

참고문헌 (42)

10.1109/ICASSP.2015.7178964
10.21437/Interspeech.2020-1290
The Corpus of Regional African American Language Version 2020 05 kendall 2020
Proc Adv Neural Inf Process Syst Causal effect inference with deep latent-variable models louizos 0 6446
Proc 6th Int Conf Learn Representations ICLR CausalGAN: Learning causal implicit generative models with adversarial training kocaoglu 2018
Pearl, Judea. Causal Diagrams for Empirical Research. Biometrika, vol.82, no.4, 669-688.

상세보기
NIST SCTK Toolkit fiscus 2018
Proc 32nd Int Conf Mach Learn ser Proc Mach Learn Res Unsupervised domain adaptation by backpropagation ganin 2015 37 1180
Proc Adv Neural Inf Process Syst PyTorch: An imperative style, high-performance deep learning library paszke 2019 8026
Proc Int Conf Mach Learn Deep speech 2: End-to-end speech recognition in English and Mandarin amodei 0 173
10.1145/3422841.3423533
Morgan, Marcyliena H.. Indirectness and interpretation in African American women’s discourse. Pragmatics : quarterly publication of the International Pragmatics Association, vol.1, no.4, 421-451.

상세보기
Proc Int Conf Learn Representations Learning the difference that makes a difference with counterfactually-augmented data kaushik 0 1
10.18653/v1/2020.findings-emnlp.7
Proc 1st ACL Workshop Ethics Natural Lang Process Gender and dialect bias in youtube’s automatic captions tatman 0 53
Koenecke, Allison, Nam, Andrew, Lake, Emily, Nudell, Joe, Quartey, Minnie, Mengesha, Zion, Toups, Connor, Rickford, John R., Jurafsky, Dan, Goel, Sharad. Racial disparities in automated speech recognition. Proceedings of the National Academy of Sciences of the United States of America, vol.117, no.14, 7684-7689.

상세보기
10.21437/Interspeech.2006-349
10.1109/ASRU.2013.6707705
10.1109/ICASSP.2016.7472692
10.1145/3347449.3357480
Proc Mach Learn Healthcare Conf Counterfactual reasoning for fair clinical risk prediction pfohl 0 325
10.1145/3287560.3287564
Bickel, P. J., Hammel, E. A., O'Connell, J. W.. Sex Bias in Graduate Admissions: Data from Berkeley. Science, vol.187, no.4175, 398-404.

상세보기
10.1145/3194770.3194776
Workshop on Fairness Accountability and Transparency in Machine Learning (FAT/ML) Fairer and more accurate, but for whom? chouldechova 2017
10.1017/CBO9780511803161.008
Proc Adv Neural Inf Process Syst Equality of opportunity in supervised learning hardt 0 3315
Proc ACM SIGKDD Int Conf Knowl Discov Data Mining Mathematical notions vs. human perception of fairness: A descriptive approach to fairness for machine learning m 0 2459
Proc Adv Neural Inf Process Syst Counterfactual fairness kusner 0 4066
Friedler, Sorelle A., Scheidegger, Carlos, Venkatasubramanian, Suresh. The (Im)possibility of fairness : different value systems require different mechanisms for fair decision making. Communications of the ACM, vol.64, no.4, 136-143.

상세보기
Chouldechova, Alexandra. Fair Prediction with Disparate Impact: A Study of Bias in Recidivism Prediction Instruments. Big data, vol.5, no.2, 153-163.

상세보기
Evaluating and mitigating bias in image classifiers: A causal perspective using counterfactuals dash 2021
10.1145/2090236.2090255
10.1145/1143844.1143891
ICML Representation Learning Worksop Sequence transduction with recurrent neural networks graves 2012
10.1109/ICASSP.2013.6638947
10.21437/Interspeech.2019-2680
10.21437/Interspeech.2017-1296
10.1145/3351095.3372864
10.1109/ICASSP.2016.7472621
Chouldechova, Alexandra, Roth, Aaron. A snapshot of the frontiers of fairness in machine learning. Communications of the ACM, vol.63, no.5, 82-89.

상세보기
10.21437/Interspeech.2017-1566

LOADING...

활용도 분석정보

상세보기

다운로드

내보내기

활용도 Top5 논문

해당 논문의 주제분야에서 활용도가 높은 상위 5개 콘텐츠를 보여줍니다.
더보기 버튼을 클릭하시면 더 많은 관련자료를 살펴볼 수 있습니다.

원문 보기

AccessON 원문보기

원문 URL 링크

DOI : 10.1109/TASLP.2021.3126949
IEEE : 저널 > 논문
Association for Computing Machinery : 저널
AccessON : 저널

*원문 PDF 파일 및 링크정보가 존재하지 않을 경우 KISTI DDS 시스템에서 제공하는 원문복사서비스를 사용할 수 있습니다.

오픈액세스(OA) 유형

GOLD(Hybrid)

저자가 APC(Article Processing Charge)를 지불한 논문에 한하여 자유로운 이용이 가능한, hybrid 저널에 출판된 논문

저작권 관리 안내

내보내기 메뉴

내보내기 구분

파일저장
인쇄
메일전송

구성항목

기본정보
상세정보

관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관

저장형식

Text(ASCII format)
Excel format
RefWorks Direct Export
RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley

메일정보

받는사람 (필수): @
보내는사람 (선택): @
제목
내용: KISTI 검색결과 이메일 서비스

안내

총 건의 자료가 검색되었습니다.

다운받으실 자료의 인덱스를 입력하세요. (1-10,000)

검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다.

데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요)

다운로드 파일은 UTF-8 형태로 저장됩니다.
파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오.

Text(ASCII format)
Excel format

표제어: PCR

동의어: Packet Collision Rate

용어 설명 출처 목록 (6)

용어 설명: PCR은 세균 특이성이 있는 primer를 이용하여 적은 수의 세균이 있을지라도 쉽게 검출할 수 있는 유용한 방법이며, 이를 이용하여 구강 내 치면세균막이나 타액에서 직접 세균을 검출할 수 있게 되었다[8].

AI-Helper ※ AI-Helper는 을 사용합니다.

AI-Helper

안녕하세요, AI-Helper입니다. 좌측 "선택된 텍스트"에서 텍스트를 선택하여 요약, 번역, 용어설명을 실행하세요.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.

연합인증