Waveform Compiles Speech Database for Concussion Diagnoses
Waveform Communication and Methodist Sports Medicine have compiled a large database of impaired speech and acoustically processed it to help with medical diagnoses of concussions.
The two firms have collected speech from 45 people diagnosed with concussions. Each subject was recorded on the initial visit where he was clinically diagnosed with a concussion and recorded at each additional office visit until medically released from care. Each person went through at least two recording sessions and as many as eight.
The Waveform Communication-Methodist Sports Medicine database contains more than 3,800 .wav files. Each recording was acoustically analyzed every six milliseconds, providing a dataset of thousands of rows of acoustic data.
The Waveform Model of Vowel Perception and Production has been developed into an automatic speech recognition algorithm achieving greater than 99 percent accuracy. The unmatched performance of the Waveform Model was accomplished with measurements made at one point in time per vowel equivalent to less than 1 percent of the complete WCMSM dataset analyzed.
Analysis and interpretation of the WCMSM database using the Waveform Model of Vowel Perception and Production, which was developed into an automatic speech recognition algorithm achieving greater than 99 percent accuracy, is progressing. Waveform is currently taking the data and developing a concussion identification tool named Cobweb.
Objectively identifying impairment in military situations and youth athletics has the potential of saving lives. This will be the focus of the Cobweb product development, and has led to the formation of Cobweb Sports and Contact Trauma Analytics, according to Michael Stokes, president and CEO of Waveform.
Waveform Communications is developing a speech recognition product that compares how people produce vowel sounds to zero in on brain injuries.