https://aurora.auburn.edu/handle/11200/44232 2026-04-06T16:06:36Z https://aurora.auburn.edu/handle/11200/49918 Automated Phonetic Transcription Grading Tool The Automated Phonetic Transcription Grading Tool (APTgt) is an online Learning Management System (LMS) that facilitates the comparison of phonetic transcriptions for instruction and clinical training purposes. It uses an embedded IPA graphical keyboard for transcription input. A custom edit distance algorithm aligns transcriptions in an intuitive way and then calculates differences quantitatively. This allows for objective scoring of transcriptions of even severely impaired productions, which may be difficult to score via traditional comparison methods. APTgt also includes support for comparing narrow phonetic transcriptions with diacritics. Contact the Technologies for Speech Language Pathology Research Lab at techslp@auburn.edu for registration information. https://aurora.auburn.edu/handle/11200/49809 Automated Phonetic Transcription Comparison Tool The Automated Phonetic Transcription (APT) Comparison Tool (APTct) is an online tool that facilitates the comparison of phonetic transcriptions for a variety of clinical and research purposes. It uses an IPA graphical keyboard for straightforward transcription input, and a custom edit distance algorithm designed to align transcriptions in an intuitive way and then calculate differences quantitatively. This allows for objective scoring of transcriptions of even severely impaired productions, which may be difficult to score via traditional comparison methods. APTct also includes support for comparing narrow phonetic transcriptions with diacritics. It does this by assigning gradated penalties for phoneme edits versus diacritic edits: For any substitution, addition, or deletion of an entire phoneme, the algorithm assigns a penalty of 1; for any substitution, addition, or deletion of a diacritic, the algorithm assigns a penalty of 0.5. APTct also provides average edit distance scores for all transcription comparisons input in a session. Potential uses of the tool include the following: tracking a client’s productions over time and in response to treatment, estimating the severity of sound production accuracy impairments, and calculating inter-rater reliability of multiple transcribers. https://aurora.auburn.edu/handle/11200/49618 Intelliturk: Speech Intelligibility Perception Study Platform for Amazon Mechanical Turk A web application, IntelliTurk, was developed using Microsoft .NET Technologies to investigate the difficulties listeners in the general population might encounter when listening to speakers from different speech disorder populations. The name IntelliTurk reflects the integration between our web application and Amazon Mechanical Turk. A special feature is the Direct Magnitude Estimation (DME) measurement tool provided to rate speech intelligibility that is configurable to capture the rating under three conditions: numerical, linguistic, or a combination of both. The web application has also been designed to be used independently from AMT by sending a participation link directly to a potential listener. The IntelliTurk platform is currently being expanded to facilitate other perceptual listening experiments. https://aurora.auburn.edu/handle/11200/49140 SEED - Speech Exemplars and Evaluation Database This is a database of recordings of children's speech patterns, with and without pathologies.