Caller Name Pronunciation Audio for Pre-Answer Call Routing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems fail to accurately pronounce the names of inbound callers, leading to potential mispronunciation and customer dissatisfaction during interactions, especially in contact centers where agents may not be native speakers.
Innovation Solution
A computerized system that includes an inbound routing software, CRM software, and a name pronunciation engine, which detects inbound interactions, retrieves caller names, fetches audio files with correct pronunciations, and plays them on the recipient's device before the interaction begins, using media servers or TTS servers when necessary.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If agents are trained for accent neutralization and pronouncing names, then pronunciation accuracy may improve, but training time and cost increase
Solution Approach 1:
The system performs preliminary action by automatically playing audio files with correct name pronunciations to agents before interactions begin. The name pronunciation engine fetches and transmits audio files containing the correct pronunciation of caller names, allowing agents to hear and learn the proper pronunciation in advance without requiring extensive training programs.
2Measurement precision
If audio files with name pronunciations are played to recipients before interactions, then pronunciation accuracy improves, but system complexity increases
Solution Approach 1:
The system achieves universality by integrating the name pronunciation functionality into existing infrastructure. The name pronunciation engine leverages available audio files from media servers or generates them using text-to-speech technology, allowing the same system to serve multiple purposes: storing audio files, retrieving them based on caller information, transmitting to appropriate agents, and playing them through existing media players without requiring separate dedicated systems.
Solution Approach 2:
The system implements self-service through automated processes. The inbound routing software automatically detects incoming interactions and triggers the name pronunciation engine. The engine autonomously retrieves caller names from CRM software, fetches corresponding audio files, transmits them to the appropriate recipient's computerized device, and the media player automatically plays them. This eliminates the need for manual intervention in the pronunciation delivery process.
3Reliability
If name pronunciations are automatically transmitted and played before interactions, then customer satisfaction improves, but data processing time increases
Solution Approach 1:
The system performs preliminary action by preparing and transmitting name pronunciation audio files to agents before the actual interaction begins. The audio file is fetched from media servers or generated by text-to-speech, transmitted to the agent's device, and played automatically, ensuring the agent has the correct pronunciation ready before speaking with the customer.
Solution Approach 2:
The system maintains continuity of useful action by seamlessly integrating the name pronunciation delivery into the existing call routing workflow. As the inbound routing software continuously routes calls and the name pronunciation engine continuously fetches and transmits audio files, there is no interruption or pause in the overall process. The pronunciation delivery happens in parallel with call routing operations, maintaining the continuous flow of interaction setup.
Data Source
AI summary
A computerized-system for playing an audio-file of a pronunciation of a name of an inbound-caller via a computerized-device of a recipient. The computerized-system includes: an inbound-routing software, a CRM software, a name-pronunciation engine; and processors. The processors are configured to: (i) detect an inbound-interaction to the inbound-routing software; (ii) retrieve a name of the inbound-caller from the CRM software based on an ANI number of the inbound-caller; (iii) forward the retrieved name of the inbound-caller to a name-pronunciation engine to fetch an audio-file with pronunciation of the name of the inbound-caller; (iv) check an identity of a recipient of the inbound-interaction; (v) detect routing of the inbound-interaction to the recipient by the inbound-routing software; (vi) transmit the audio-file to the computerized-device of the recipient based on the identity thereof; and (vii) play the audio-file with the pronunciation of the name by a media-player before the recipient answers the inbound-interaction.