Image: Visual China
BEIJING, January 7, 2022 (TMTPOST) — Multinational tech giant Microsoft announced on Friday that Chinese smart electric vehicle brand Xpeng Motors has upgraded its voice assistant for vehicles with the support of TTS (Text to Speech), a neural network based on Microsoft Azure.
Owners of Xpeng Motors P7 model in China can now upgrade their vehicle’s voice assistant to equip it with a “human voice” through OTA (over the air) upgrade. The new voice assistant is named XPILOT. Xpeng Motors is also planning to bring XPILOT to other EV models in the future through OTA upgrade.
Microsoft’s technological advancement in speech, natural language processing and machine translation in the past few years has enabled the company to make drastic improvements in voice assistant technology in coherence, fluency and quality.
After integrating the new technologies to Azure, Microsoft starts to support startup companies like Xpeng Motors to improve the user experience for the consumers.
It reportedly took Microsoft and Xpeng Motors several months to solve three major challenges in TTS application.
Microsoft and Xpeng Motors first solved the issue of network jitters that could appear in the use of vehicles. Xpeng Motors built a multi-level cache architecture to ensure the smooth operation of high-quality TTS function. The multi-level cache architecture allows the system to preset and cache high-quality speech files, which drastically reduces the system’s reliance on network connection.
The two companies then moved on to work on ensuring XPILOT can deliver a human-like voice without taking up too much system resources. Xpeng Motors made use of Microsoft Azure’s cache and compression features and reduce speech files to 24KHz and 16 bits, significantly reducing XPILOT’s demand for data networks and vehicle computing power.
In addition, Microsoft and Xpeng Motors worked on improving speech accuracy and reducing the ambiguity of the generated speeches.
"This is a cutting-edge exploration of vehicle voice interaction in the auto industry," said Hao Chao, a Senior Expert with XPENG Motors AI Products. “It required months of dedicated work by our team to overcome the challenges, and now delivers a whole new level of natural speech. With a deep understanding of urban mobility, we are finding many more scenarios to leverage AI technology for a high level of driver-machine intuition.”
“With advancements in research and technology, Azure Cognitive Services like vision and speech, will play a pivotal role in defining unique in-vehicle experiences,” said Sanjay Ravi, General Manager, Automotive, Mobility, and Transportation Industry at Microsoft. “With speech as a primary interaction tool within the vehicle, Microsoft’s custom neural voice services enable automakers to develop their own differentiated and authentic branded experiences.”
Besides Xpeng Motors, Microsoft would also establish cooperation with several other automakers on intelligence vehicle development.