# The Far Side of Failure: Investigating the Impact of Speech Recognition Errors on Subsequent Dementia Classification

arXiv: https://arxiv.org/abs/2211.07430 · HTML: https://mlsanity.com/paper/2211.07430/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 36 references that are in the map.
- First posted on arXiv 11 Nov 2022.

## Builds on (most cited first, 9 of 9)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [Libri-Light: A Benchmark for ASR with Limited or No Supervision](https://mlsanity.com/paper/1912.07875/) (2019)
- [Alzheimer's Dementia Recognition through Spontaneous Speech: The ADReSS Challenge](https://mlsanity.com/paper/2004.06833/) (2020)
- [Self-training and Pre-training are Complementary for Speech Recognition](https://mlsanity.com/paper/2010.11430/) (2020)
- [To BERT or Not To BERT: Comparing Speech and Language-based Approaches for Alzheimer's Disease Detection](https://mlsanity.com/paper/2008.01551/) (2020)
- [Impact of ASR on Alzheimer's Disease Detection: All Errors are Equal, but Deletions are More Equal than Others](https://mlsanity.com/paper/1904.01684/) (2019)
- [Influence of ASR and Language Model on Alzheimer's Disease Detection](https://mlsanity.com/paper/2110.15704/) (2021)

## Built on by (most cited first, 2 of 2)

- [Useful Blunders: Can Automated Speech Recognition Errors Improve Downstream Dementia Classification?](https://mlsanity.com/paper/2401.05551/) (2024)
- [Not All Errors Are Equal: Investigation of Speech Recognition Errors in Alzheimer's Disease Detection](https://mlsanity.com/paper/2412.06332/) (2024)

## Abstract (arXiv)

Linguistic anomalies detectable in spontaneous speech have shown promise for various clinical applications including screening for dementia and other forms of cognitive impairment. The feasibility of deploying automated tools that can classify language samples obtained from speech in large-scale clinical settings depends on the ability to capture and automatically transcribe the speech for subsequent analysis. However, the impressive performance of self-supervised learning (SSL) automatic speech recognition (ASR) models with curated speech data is not apparent with challenging speech samples from clinical settings. One of the key questions for successfully applying ASR models for clinical applications is whether imperfect transcripts they generate provide sufficient information for downstream tasks to operate at an acceptable level of accuracy. In this study, we examine the relationship between the errors produced by several deep learning ASR systems and their impact on the downstream task of dementia classification. One of our key findings is that, paradoxically, ASR systems with relatively high error rates can produce transcripts that result in better downstream classification accuracy than classification based on verbatim transcripts.