Continuous Accuracy Tuning overview
The Tune Transcript workspace Area within an application window where the user interacts with the program. allows language model Repository used with Speech Analytics and Real Time Speech Analytics that contains words for a specific language, where each word has its own phonetic representation (one or more words) and frequency grade, for the purpose of accurate word recognition and subsequently transcription. managers to enhance transcription Process in Speech Analytics of converting audio files of the recorded agent-customer conversation to text. accuracy by integrating incorrectly transcribed terms and phrases into the language model.
Employees submit suggestions for an interaction In Speech Analytics, an interaction represents a single part of the contact between one employee and the same customer. In Text Analytics, an interaction is the communication session between one or more employees and the same customer with a unifying contextual element.'s transcription (Transcription tab). The workspace collates all suggestions submitted by employees for transcriptions, per language and vocabulary. Language model managers can review each suggestion in its context, overwrite with a different suggestion, and approve or reject the suggestion. The approved suggestions are manually exported for integration into the language model through Phonetics Boosting.