解释深度学习模型以理解语言障碍中语言可理解性的丧失:语音特征出现的贡献

Sondes Abderrazek, C. Fredouille, A. Ghio, M. Lalain, Christine Meunier, V. Woisard
{"title":"解释深度学习模型以理解语言障碍中语言可理解性的丧失:语音特征出现的贡献","authors":"Sondes Abderrazek, C. Fredouille, A. Ghio, M. Lalain, Christine Meunier, V. Woisard","doi":"10.1109/icassp43922.2022.9746198","DOIUrl":null,"url":null,"abstract":"Apart from the impressive performance it has achieved in several tasks, one of the most important factors remaining for the continuous progress of deep learning is the increased work related to interpretability, especially in a medical context. In a recent work, we presented competitive performance achieved with a CNN-based model trained on normal speech for the French phone classification and how it correlates well with different perceptual measures when exposed to disordered speech. This paper extends that work by focusing on interpretability. Here, the goal is to get insights into the way in which neural representations shape the final task of phone classification so that it can be used further to explain the loss of intelligibility in disordered speech. In this way, an original framework is proposed, relying firstly on the neural activity and a novel representation per neuron, here considering the phone classification, and, secondly, permitting to identify a set of neurons devoted to the detection of specific phonetic traits on normal speech. Faced to disordered speech, a degradation of that set of neurons is observed, demonstrating a loss of specific phonetic traits in some patients involved, and the potentiality of the proposed approaches to inform about speech alteration.","PeriodicalId":272439,"journal":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":"{\"title\":\"Towards Interpreting Deep Learning Models to Understand Loss of Speech Intelligibility in Speech Disorders Step 2: Contribution of the Emergence of Phonetic Traits\",\"authors\":\"Sondes Abderrazek, C. Fredouille, A. Ghio, M. Lalain, Christine Meunier, V. Woisard\",\"doi\":\"10.1109/icassp43922.2022.9746198\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Apart from the impressive performance it has achieved in several tasks, one of the most important factors remaining for the continuous progress of deep learning is the increased work related to interpretability, especially in a medical context. In a recent work, we presented competitive performance achieved with a CNN-based model trained on normal speech for the French phone classification and how it correlates well with different perceptual measures when exposed to disordered speech. This paper extends that work by focusing on interpretability. Here, the goal is to get insights into the way in which neural representations shape the final task of phone classification so that it can be used further to explain the loss of intelligibility in disordered speech. In this way, an original framework is proposed, relying firstly on the neural activity and a novel representation per neuron, here considering the phone classification, and, secondly, permitting to identify a set of neurons devoted to the detection of specific phonetic traits on normal speech. Faced to disordered speech, a degradation of that set of neurons is observed, demonstrating a loss of specific phonetic traits in some patients involved, and the potentiality of the proposed approaches to inform about speech alteration.\",\"PeriodicalId\":272439,\"journal\":{\"name\":\"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)\",\"volume\":\"76 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-05-23\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"4\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/icassp43922.2022.9746198\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/icassp43922.2022.9746198","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 4

摘要

除了在一些任务中取得的令人印象深刻的表现外,深度学习持续发展的最重要因素之一是与可解释性相关的工作增加,特别是在医学背景下。在最近的一项工作中,我们展示了一个基于cnn的模型在正常语音上训练的法语电话分类的竞争性表现,以及当暴露于无序语音时,它如何与不同的感知测量相关联。本文通过关注可解释性来扩展这项工作。在这里,我们的目标是深入了解神经表征如何塑造电话分类的最终任务,以便它可以进一步用于解释无序语音的可理解性丧失。通过这种方式,提出了一个原始框架,首先依赖于神经活动和每个神经元的新表示,在这里考虑电话分类,其次,允许识别一组致力于检测正常语音的特定语音特征的神经元。面对言语障碍,这组神经元的退化被观察到,在一些患者中表现出特定语音特征的丧失,以及所提出的方法通知语言改变的潜力。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Towards Interpreting Deep Learning Models to Understand Loss of Speech Intelligibility in Speech Disorders Step 2: Contribution of the Emergence of Phonetic Traits
Apart from the impressive performance it has achieved in several tasks, one of the most important factors remaining for the continuous progress of deep learning is the increased work related to interpretability, especially in a medical context. In a recent work, we presented competitive performance achieved with a CNN-based model trained on normal speech for the French phone classification and how it correlates well with different perceptual measures when exposed to disordered speech. This paper extends that work by focusing on interpretability. Here, the goal is to get insights into the way in which neural representations shape the final task of phone classification so that it can be used further to explain the loss of intelligibility in disordered speech. In this way, an original framework is proposed, relying firstly on the neural activity and a novel representation per neuron, here considering the phone classification, and, secondly, permitting to identify a set of neurons devoted to the detection of specific phonetic traits on normal speech. Faced to disordered speech, a degradation of that set of neurons is observed, demonstrating a loss of specific phonetic traits in some patients involved, and the potentiality of the proposed approaches to inform about speech alteration.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信