When people talk to each other, they use more complex sentences than when talking to computers. There are several challenges in conducting natural conversations: natural language is hard to understand, natural behavior is tricky to model, latency expectations require fast processing, and generating natural sounding speech, with the appropriate intonations, is difficult. We’ll be experimenting with the right approach over the coming months. We want to be clear about the intent of the call so businesses understand the context. It’s important to us that users and businesses have a good experience with this service, and transparency is a key part of that. The Google Duplex technology is built to sound natural, to make the conversation experience comfortable. While sounding natural, these and other examples are conversations between a fully automatic computer system and real businesses. Here are examples of Duplex making phone calls (using different voices):ĭuplex scheduling a hair salon appointment: It cannot carry out general conversations. Duplex can only carry out natural conversations after being deeply trained in such domains. One of the key research insights was to constrain Duplex to closed domains, which are narrow enough to explore extensively. For such tasks, the system makes the conversational experience as natural as possible, allowing people to speak normally, like they would to another person, without having to adapt to a machine. The technology is directed towards completing specific tasks, such as scheduling certain types of appointments. Today we announce Google Duplex, a new technology for conducting natural conversations to carry out “real world” tasks over the phone. They don’t engage in a conversation flow and force the caller to adjust to the system instead of the system adjusting to the caller. In particular, automated phone systems are still struggling to recognize simple words and commands.
Still, even with today’s state of the art systems, it is often frustrating having to talk to stilted computerized voices that don't understand natural language. In recent years, we have witnessed a revolution in the ability of computers to understand and to generate natural speech, especially with the application of deep neural networks (e.g., Google voice search, WaveNet). Posted by Yaniv Leviathan, Principal Engineer and Yossi Matias, Vice President, Engineering, GoogleĪ long-standing goal of human-computer interaction has been to enable people to have a natural conversation with computers, as they would with each other.
0 kommentar(er)
