ClaritySpeech: Dementia Obfuscation in Speech
This work addresses privacy and accessibility challenges for individuals with dementia by obfuscating their speech patterns, though it appears incremental as it integrates existing technologies like ASR and TTS.
This paper tackled the problem of dementia-affected speech, which creates communication barriers and privacy issues, by developing ClaritySpeech, a framework that corrects such speech while preserving speaker identity, resulting in improved word error rates (e.g., from 0.73 to 0.08 for ADReSS) and speech quality (from 1.65 to ~2.15).
Dementia, a neurodegenerative disease, alters speech patterns, creating communication barriers and raising privacy concerns. Current speech technologies, such as automatic speech transcription (ASR), struggle with dementia and atypical speech, further challenging accessibility. This paper presents a novel dementia obfuscation in speech framework, ClaritySpeech, integrating ASR, text obfuscation, and zero-shot text-to-speech (TTS) to correct dementia-affected speech while preserving speaker identity in low-data environments without fine-tuning. Results show a 16% and 10% drop in mean F1 score across various adversarial settings and modalities (audio, text, fusion) for ADReSS and ADReSSo, respectively, maintaining 50% speaker similarity. We also find that our system improves WER (from 0.73 to 0.08 for ADReSS and 0.15 for ADReSSo) and speech quality from 1.65 to ~2.15, enhancing privacy and accessibility.