Self-Supervised Speech Representations for Cross-Speaker Dysarthria Detection During Awake Craniotomy

Key points

• However, automated detection remains challenging because operating-room recordings contain substantial acoustic interference, clinically relevant speech events are rare, and available cohorts are small and heterogeneous across speakers.1
• This study presents a systematic component-wise evaluation of a pipeline for distinguishing dysarthric from no-trouble speech in the DATABRASE corpus of awake-craniotomy recordings.1
• The pipeline incorporates speaker diarization to isolate patient speech, a multi-view representation combining handcrafted acoustic descriptors with multilayer wav2vec 2.0 embeddings, speaker-conditional normalization and transferability-based feature selection to improve cross-speaker robustness, and a cascaded classifier comprising a gradient-boosted first stage and a neural second stage.1
• These findings indicate that reliable patient-specific speech isolation and strong pretrained representations are more important than increased classifier complexity in low-resource intra-operative settings.1

Sources (1)

• [1]Self-Supervised Speech Representations for Cross-Speaker Dysarthria Detection During Awake Craniotomy
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 12:25 PM

  Detecting intra-operative speech impairment during awake craniotomy is essential for preserving language function.

  However, automated detection remains challenging because operating-room recordings contain substantial acoustic interference, clinically relevant speech events are rare, and available cohorts are small and heterogeneous across speakers.

Extractive summary: sentences quoted from the sources.