CAN WE TRUST EXPLAINABLE AI METHODS ON ASR? AN EVALUATION ON PHONEME RECOGNITION

Xiaoliang Wu, Peter Bell, Ajitha Rajan

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

Explainable AI (XAI) techniques have been widely used to help explain and understand the output of deep learning models in fields such as image classification and Natural Language Processing. Interest in using XAI techniques to explain deep learning-based Automatic Speech Recognition (ASR) is emerging. But there is not enough evidence on whether these explanations can be trusted. To address this, we adapt a state-of-the-art XAI technique from the image classification domain, Local Interpretable Model-Agnostic Explanations (LIME), to a model trained for a TIMIT-based phoneme recognition task. This simple task provides a controlled setting for evaluation while also providing expert annotated ground truth to assess the quality of explanations. We find a variant of LIME based on time partitioned audio segments, that we propose in this paper, produces the most reliable explanations, containing the ground truth 96% of the time in its top three audio segments.
Original languageEnglish
Title of host publicationICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
PublisherIEEE
Pages10296-10300
Number of pages5
ISBN (Electronic)979-8-3503-4485-1
ISBN (Print)979-8-3503-4486-8
DOIs
Publication statusPublished - 18 Mar 2024
Event2024 IEEE International Conference on Acoustics, Speech and Signal Processing - Seoul, Korea, Republic of
Duration: 14 Apr 202419 Apr 2024
https://2024.ieeeicassp.org/

Publication series

NameInternational Conference on Acoustics, Speech, and Signal Processing (ICASSP)
PublisherIEEE
ISSN (Print)1520-6149
ISSN (Electronic)2379-190X

Conference

Conference2024 IEEE International Conference on Acoustics, Speech and Signal Processing
Abbreviated titleICASSP 2024
Country/TerritoryKorea, Republic of
CitySeoul
Period14/04/2419/04/24
Internet address

Keywords / Materials (for Non-textual outputs)

  • Explanation
  • Phoneme Recognition

Fingerprint

Dive into the research topics of 'CAN WE TRUST EXPLAINABLE AI METHODS ON ASR? AN EVALUATION ON PHONEME RECOGNITION'. Together they form a unique fingerprint.

Cite this