Comparison of Speaker Role Recognition and Speaker Enrollment Protocol for conversational Clinical Interviews
This work addresses the need for efficient analysis of clinical dialogues to aid medical follow-up, though it is incremental as it compares existing methods on a specific dataset.
The study tackled the problem of automatically detecting and identifying speaker turns in clinical conversations, particularly for individuals with speech and language disorders, by comparing speaker role recognition and speaker enrollment methods, finding that the speaker role recognition model performed best and that results were independent of interviewee demographics.
Conversations between a clinician and a patient, in natural conditions, are valuable sources of information for medical follow-up. The automatic analysis of these dialogues could help extract new language markers and speed-up the clinicians' reports. Yet, it is not clear which speech processing pipeline is the most performing to detect and identify the speaker turns, especially for individuals with speech and language disorders. Here, we proposed a split of the data that allows conducting a comparative evaluation of speaker role recognition and speaker enrollment methods to solve this task. We trained end-to-end neural network architectures to adapt to each task and evaluate each approach under the same metric. Experimental results are reported on naturalistic clinical conversations between Neuropsychologist and Interviewees, at different stages of Huntington's disease. We found that our Speaker Role Recognition model gave the best performances. In addition, our study underlined the importance of retraining models with in-domain data. Finally, we observed that results do not depend on the demographics of the Interviewee, highlighting the clinical relevance of our methods.