Microsoft is helping to reshape the automotive industry in the way it serves its drivers with infotainment systems. For example, Azure works with XPeng to deliver AI language experiences for automotive brands and customers. The solution offers the industry a new way of looking at text-to-speech and expressive voice, global languages, speaker fidelity and self-service customization. XPeng joins a growing trend for automakers to rethink investments in environmental awareness.

“This is cutting-edge research into vehicle voice interaction in the auto industry,” said Hao Chao, Xpeng’s senior expert on AI products. “The experience offers a whole new level of natural language. With a deep understanding of urban mobility, we can find many more scenarios to use AI technology for a high level of driver-machine intuition. “

XPeng has approached Microsofts neural text-to-speech technology for their in-car user experience. By using Microsoft’s neural text-to-speech feature with emotional styles, Xpeng can provide a more enjoyable listening experience for its customers and combat listening fatigue. Microsoft’s neural text-to-speech technology offers fluency and naturalness comparable to that of a human voice. In conjunction with multi-emotional voices, Microsoft Text-to-Speech acts as a refreshing replacement for the monotonous sound that many car assistants have today.

“We look forward to reinventing how speech and voice can improve the lives of drivers,” said Binggong Ding, Azure AI Speech product director. “Although from a technical point of view we really want to develop a model that can serve all car brands and their developers. How can we best optimize the use of synthetic speech to deliver a high fidelity speech experience without compromising sound quality? XPeng builds on this challenge to provide the voice assistant that customers have been looking for. “

Microsoft’s long-term goal is to make advanced, multi-emotional, global voice capabilities the new standard for global auto brands and consumers. Technology adopted by XPeng added dozen of vocal styles, unique control of emotional intensity, and deduction skills. It comprises 90 certifications worldwide, including national guidelines, regulatory requirements for data centers and EU GDPR as well as higher requirements for the owner of data protection guidelines. Together with the automobile manufacturers, Microsoft is creating new driving experiences with speech based on the text-to-speech and speech-to-text functions within Azure Cognitive Services for speech.

Accelerated language innovation

Language is the new interface in ambient computing technology. The quality of text-to-speech and speech-to-text has improved in recent years due to research and technology leaps made possible by the development of neural networks. High quality speech-to-text and text-to-speech meet the demands of automakers to create the next generation of modern in-car speech experience. Microsoft Speech-to-Text offers robust recognition functions that are speaker-independent and can process ambient noise while driving. Microsoft Text-to-Speech also offers a smoother, more natural-sounding voice that can make a difference for automakers and customers alike. Both speech-to-text and text-to-speech also increase hands-free control of the car’s infotainment system. Microsoft Text-to-Speech supports several speaking styles, including chat, messaging, and customer service. These advances allow drivers to have a more comfortable driving experience. For more information on recent advances in speech-to-text and text-to-speech, see Speech-to-text with his research results, Reaching human parity on the Switchboard Research Benchmark and neural text-to-speech is close to human parity.

Offer global languages

Microsoft helps automakers cover their global business and recently hit a milestone of 100 languages ​​and now supports 119 languages ​​and variants with 278 voices out-of-box. This is in line with our corporate vision of empowering every person and organization on the planet to achieve more. “One hundred languages ​​is a good milestone for us to achieve our goal everyone will be able to communicate regardless of the language they speak, “said Xuedong Huang, Microsoft Technical Fellow and Azure AI Chief Technology Officer. With more languages ​​and their variants, we are pleased to enable car manufacturers to have natural and intuitive language experiences.

Differentiation through individualization

Microsoft enables automakers to use the custom neural language feature to create a highly realistic brand voice for more natural conversational interfaces. Based on neural text-to-speech technology and the multi-lingual, multi-speaker universal model, you can use custom neural voice to create synthetic voices that are rich in speaking styles or adaptable across languages ​​with just 30 minutes of audio. The realistic and natural sounding voice of the custom neural voice can represent brands and specific personalities, and allow users to interact with applications naturally, conversational style. Check out this blog for a Step-by-step guide to creating a custom neural voice.

Compliance and responsible AI

Microsoft is committed to investing in regulatory compliance around the world to meet automotive manufacturers’ compliance requirements. The voice service, part of Azure Cognitive Services, is certified by SOC, FedRAMP, PCI DSS, HIPAA, HITECH and ISO. Supported by an Azure infrastructure, the voice service also offers enterprise-grade security, availability, compliance and manageability.

Microsoft is committed to the responsible development of AI technology. We use various technical and policy features to prevent misuse of the technology. For example, we develop and publish Custom Neural Voice with the intention of protecting the rights of individuals and society, promoting transparent human-computer interaction and preventing the spread of harmful deepfakes and misleading content. This corresponds to that of Microsoft Commitment to responsible AI. This commitment includes Transparency noticesthat communicates the purpose, capabilities and limitations of an AI system.

Learn more

Azure Cognitive Services brings AI within reach. Learn how to accelerate innovation with groundbreaking AI research.


Source link

Leave a Reply