Autoscribe is our MacOS software that allows you to transcribe and code conversations automatically using the wav2textgrid R package. This tool converts dyadic conversational audio recordings into Praat TextGrids with time-aligned turn boundaries between speech and non-speech segments and transcripts of all spoken dialogue output. The R package is available to download from GitHub. https://github.com/Human-Interaction-Lab/wav2textgrid. To install the Autoscribe desktop application, you must first have R and Praat installed on your computer. Then, you can download the Autoscribe desktop application by clicking the button below.
Autoscore is an open-source application for scoring orthographic listener transcripts for words correctly identified. This is useful in speech perception research, such as studies that examine listener understanding of disordered speech, accented speech, or speech in background noise. The program uses a flexible number of rules that determine whether a response set of words (i.e., listener transcripts) match a target set of words (i.e., speech stimuli corpus). http://autoscore.usu.edu
Using a long list of useful sentences for intelligibility testing, perceptual training, and other intelligibility related tasks, this tool allows you to record each sentence and have the recording processed for use. https://human-interaction-lab.github.io/audio-recorder/
This tool allows users to fill out the PROCS form and get a score of conversational success. The tool has been rigorously developed and psychometrically validated in a four-phase experimental protocol. Associated manuscripts under review. https://human-interaction-lab.github.io/PROCS-Form/