Between the visits.

A'ber is investigational speech-practice software for speech language pathologists working with dysarthria. The adaptive engine handles session to session exercise selection, intensity calibration, and practice tracking, so the mechanical work of building the next session by hand does not fall to the clinician. Clinical judgment and intervention planning stay with you. A'ber is not a medical device and its output is not a clinical measurement. See the intended-use statement for what has and has not been established.

Practice tracking between visits

Per-exercise measures (speaking rate, pitch range, how long a sound is held, cued loudness change) are shown against the patient's own earlier sessions on the same device, with recording-quality checks first. Model-based skill estimates are marked approximate. This is research-grade software; it is not clinically validated.

Flagged events, not noise

A'ber does not page the clinician on every session. Flagged events fire when the system detects a meaningful deviation from the patient's own baseline: two consecutive sessions missed, practice measures moving beyond this patient's own session-to-session variability on this device, or a run of recordings that failed the quality checks. The SLP receives a structured prompt with the relevant data attached, not a generic alert at two in the morning.

The caseload view

The caseload page is the SLP's home. Each patient row shows the starting practice level (research classifier), current focus sub tracks, last session recency, session count, and any active alerts. Rows needing attention are tinted and ordered above the rest, so triage happens in seconds rather than minutes.