Speech Technology Magazine

 

Speech Is a Key Component of iPhone 4S

Apple, on October 4, unveiled its iPhone 4S, packed with a host of speech capabilities, including an intelligent assistant that helps users get things done simply by asking.
By Leonard Klie - Posted Nov 1, 2011
Page1 of 1
Bookmark and Share

Apple, on October 4, unveiled its iPhone 4S, packed with a host of speech capabilities, including an intelligent assistant that helps users get things done simply by asking.

The assistant, powered by voice technologies from Siri (which Apple acquired last year) and Nuance Communications, accepts verbal commands and queries, understands context, and figures out which apps to use based on the type of query. For example, if a user asks, "Will I need an umbrella this weekend?" it understands that she is looking for a weather forecast. If the user tells Siri "Remind me to call Mom when I get home," it can find Mom in the address book and schedule a call. Ask Siri "What's the traffic like around here?" and it can figure out the user's current location based on his GPS coordinates.

Siri can also help users make calls, send text messages or email, schedule meetings and reminders, make notes, search the Internet, find local businesses, get directions, play music, and more. Additionally, users can get answers, find facts, and even perform complex calculations simply by talking to the application.

The Siri Assistant also offers a conversational aspect, in which the system can ask the user questions to clarify and refine its understanding of what is being requested. The system speaks back and forth with the user to gain the most information to provide the best results.

Voice-powered features also include speech-to-text transcription from Nuance. "The success of Nuance's voice technologies has proven that millions of consumers around the world love voice and want more," said Vlad Sejnoha, chief technology officer at Nuance, in an email. "Voice truly works, and today's Apple iPhone 4S announcement is further evidence that voice is becoming a mainstream mobile interface."

David McQueen, principal analyst at Informa Telecoms & Media, calls the voice offering one of several "neat features," along with iCloud integration, an instant message application called iMessage, integration with social networks, double-tap use of the home button to activate the camera, and iTunes Match to scan and match a user's library.

"Of these, voice recognition has the capability to be a key differentiator, as its tight integration with the hardware and ability to work organically should offer market-leading performance," he said in an email.

Bill Meisel, speech strategist and president of TMA Associates, maintains that this latest iPhone release might have an advantage over some other mobile phones in handling speech input. "Previous versions have included a chip from Audience that has advanced noise-canceling features," he said in a statement. "This capability, if present, could allow using voice interaction in environments where phones without noise-canceling features can't."

"One bottom line take-away," Meisel said, "is that, given the market share of Apple's iPhone and the likely competitive response from other vendors, speech understanding is now a key and growing part of the user interface for mobile devices."

Page1 of 1