Voice Assistant Quality Automation Framework

Voice enabled IoT Solutions have taken center stage in the last few years.  Emerging fields such as natural language processing (NLP) are set to drive the next wave of innovation. However, there are still several barriers before voice will see mass adoption. Accuracy of response, speed at which the response is given, personalized responses, understanding user intent etc. are all critical factors for successful voice assistant rollout. There is also an urgent need for a solution that can automate end to end testing of voice assistants.

At eInfochips, we have developed an automated solution for testing of different voice assistants, known as VAQA (Voice Assistant Quality Automation) framework.  VAQA framework supports automation of voice enabled or voice assisted devices, like smart speakers, headphones, voice controlled home appliances etc.  The automation framework will act as an accelerator resulting in faster time to market and reduced operational costs for end customers.

VAQA framework is capable to automate end-to-end use case from device to cloud including:

  • Device configuration
  • Environment setup
  • Connectivity testing
  • Speech translation and recognition
  • Multi-lingual support
  • Device functionality
  • Device to Cloud connectivity
  • Voice Assisted Companion App automation
  • Data Generation

Key Features

  • QA Generator: AI based Q&A model that enables to generate test data automatically
  • Answer Matcher: Robust answer matching process using Machine learning + NLP. Answer Matcher model is robust enough to handle changes in responses of voice assistants over time
  • Speech Intelligence: Multilingual support, support for different accents, Natural Voice generator
  • Platform Integration: Alexa, Siri, Google Assistant