IVR Speech Setting Adaptation From User Speech Characteristics
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Interactive voice response systems (IVRs) often generate speech that annoys or frustrates users due to inappropriate speech rates, loudness, language, accent, or other characteristics, leading to terminated communication sessions and increased resource consumption as users attempt to avoid interacting with IVRs.
Innovation Solution
A communication platform establishes a communication session with a user device, generates speech based on initial settings, receives user speech, determines its characteristics, and updates speech generation settings to match user preferences, using natural language processing and machine learning to adapt speech characteristics in real-time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If the IVR uses fixed speech generation settings, then the system is simple to implement, but the speech characteristics do not match user preferences leading to frustration
Solution Approach 1:
The system analyzes user speech characteristics (rate, loudness, language, accent) and uses this feedback to dynamically adjust speech generation settings. This closed-loop feedback mechanism enables the IVR to adapt speech characteristics to match user preferences, resolving the contradiction between adaptability and complexity by implementing intelligent adjustment based on observed user behavior.
Solution Approach 2:
The speech generation settings transition from static fixed values to dynamic adjustable parameters. The system continuously monitors user speech and modifies speech rate, loudness, language, and accent in real-time during the interaction, making the speech generation process dynamic rather than fixed, thereby achieving adaptability without excessive complexity.
2Productivity
If the IVR uses inappropriate speech characteristics, then resource consumption increases due to repeated calls, but adjusting speech settings requires additional processing
Solution Approach 1:
The system performs self-adjustment by automatically analyzing user speech characteristics and modifying its own speech generation parameters without external intervention. This self-service capability allows the IVR to optimize interaction completion rates while managing processing energy efficiently, as the adjustment is driven by the interaction data itself rather than requiring extensive external configuration or retraining.
Solution Approach 2:
The system changes speech generation parameters (rate, loudness, language, accent) based on analyzed user speech characteristics. By dynamically adjusting these parameters during interaction, the system improves productivity through better user matching while the processing energy cost is offset by the reduction in repeated calls and improved interaction efficiency.
3Ease of operation
If the IVR generates speech at fixed rate and loudness, then the implementation is straightforward, but user satisfaction decreases due to mismatched speech characteristics
Solution Approach 1:
The system performs preliminary analysis of user speech characteristics early in the interaction to proactively adjust speech generation settings before user frustration occurs. By detecting user speech patterns and pre-adjusting rate, loudness, language, and accent parameters, the system improves ease of operation and user satisfaction while managing complexity through targeted rather than continuous adjustment.
Data Source
AI summary
A device causes a communication session to be established between the device and a user device to allow the device and the user device to communicate speech, and receives user speech from the user device. The device processes the user speech using a natural language processing technique to determine a plurality of characteristics of the user speech, and updates a speech generation setting of a plurality of speech generation settings based on the plurality of characteristics of the user speech. The device generates, after updating the speech generation setting, device speech using a text-to-speech technique based on the speech generation setting, and sends the device speech to the user device.