Overview

Transcription Features

// Introduction

Most downstream analytics processes rely on transcribed text, making speech-to-text one of the most valuable features in any contact center solution. The noise that is common in call centers (for example, other agents conversing in the background), the conversational flow often branching off in many directions, and the poor quality telephone signals pose unique challenges in accurately transcribing calls in the contact center. Driven by over 20 years of research and billions of contact center interactions, ElevateAI provides unparalleled conversational accuracy and immediate access to transcripts formatted phrase-by-phrase or punctuated, sentence-by-sentence.



// Transcription-Elevated Accuracy

NOTE: Effective v1.11 on February 29, 2024 all declared interactions will be processed with Elevated Accuracy.

When declaring an audio interaction for processing, you will define the audioTranscriptionMode parameter to prioritize results for either speed or accuracy.

Prioritizing for highAccuracy leverages the latest in transformer-based technology when processing the interaction to provide industry-leading transcription accuracy (and up to a 15% improvement in word error rate (WER)).



// PII Redaction

Personally Identifiable Information (PII) associated with social social security numbers, credit card numbers and CVV numbers is automatically redacted prior to the transcription being stored or returned to you.



Details related to the timing, type, and confidence for each redacted segment are returned when retrieving either a phrase-by-phrase or punctuated transcript.



Remember: All source data is deleted immediately and promptly upon processing. See data retention & security for additional detail



Sample Transcription Output



// Speaker Labels

ElevateAI automatically identifies and associates each phrase with a given participant (up to two) in the phrase-by-phrase and punctuated transcript.

Speaker Diarization (BETA)

For single channel audio files, ElevateAI leverages speaker diarization to identify and label each phrase within the transcript as one from participantOne or participantTwo.

Channel Labels

For dual channel audio files, such as a phone recording with the agent and customer on separate channels, ElevateAI will associate each phrase with a specific channel. Note that leveraging stereo recordings does not impact processing speed or fees.