James A. Larson
Larson Technical Services
James A. Larson, Ph.D., is co-program chair SpeechTEKConference, former co-chair of the World Wide Web Consortium's Voice Browser Working Group. Larson also teaches courses in speech application development and user interfaces at Portland State University.
Articles By James A. Larson
App developers' jobs might be getting less complicated, again
From karaoke assistance to talking robots, here's a roundup of speech industry developments you'll be hearing about soon
These apps can already understand what you say; soon they'll understand who you are and how you're feeling
As we enter the 'immersive age,' we need to prepare for a whole new way of interacting
ITR systems let callers blend texting and talking
Developers have to design both visual and voice experiences for today's devices
In the smart home of the (near) future, a unified user interface—letting you touch, type, or speak—will control all of your systems and devices
It's time to leverage developers' know-how to improve lives
Up-and-coming tools add new accessibility to product information.
Continuing demand gives these applications an impetus for improvement.
What we all have in common with an HVAC repairman.
Users seeking voice-enabled service and support have several choices.
Advances emphasize the role of the human mind.
Radar O'Reilly is a tough act to follow.
When consumers use multiple devices, give help where it's needed.
Stop using frugal policies and start satisfying customers.
Trend driven by statistical language models, speaker verification, video clips, and multilingual apps
Take advantage of today's visual displays and develop consumer product apps
With the smartphone's growing popularity comes a slew of new speech apps.
Social media can incorporate voice to better engage users.
Setting the standard for determining what a caller wants
Who will get the ball rolling on creating the rules?
User property extraction systems pull more information.
Both allow for greater use of voice on mobile devices
Technology exists to help the elderly live on their own.
We need to look beyond basic processing to fuller understanding.
Multimodal applications present a new type of user interface.
The next phases of IVR development centers on multimodality and faster transactions.
New stars present opportunities for using speech technologies.
Creating and implementing automatic classifiers is not as easy as it sounds.
Technology is available to handle many of the more mundane translation tasks
Speech vendors should support SISR for easier porting of grammars and applications between platforms
Electronic companions are the wave of the future in consumer electronics
The customer experience isn't about completion rates and ROI; it's about achieving an intended task easily, efficiently, and even enjoyably
When many people hear the words, "natural language," they immediately think of Star Trek's android, Data, who speaks and understands everyday English. Some software vendors claim anything beyond discrete speech recognition (in which users must pause between speaking each word) as "natural."
Developing and sharing content is a growing activity on the Internet. In addition to passively observing Internet content, users are actively adding to it by uploading their pictures to flickr.com, and sharing their thoughts in blogs and wikis. Readers rate books on amazon.com, and teens post real and fantasy personas on the extremely popular myspace.com, hoping to attract the attention of other teens.
Case study by PIKA Technologies>
NuVoxx focuses on developing and marketing advanced IVR (Interactive Voice Response) services, which it provides on a hosted model on a pay-per-use basis. The company also builds productivity solutions for call centers, and recently developed and deployed an advanced call recording and monitoring solution for NuComm International, its sister company and the largest privately-held Canadian provider of customer relationship and contact center services.>
Posted 13 Jun 2006
James A. Larson
Three trends that enable IVR systems for mom and pop shops without costing an arm and a leg include prepackaged applications, free starter VoiceXML platforms, and reusable dialog components.
Graphical user interfaces have been the standard user interface for computer users for over 20 years. It's time to up-level the user's computing experience by voice-enabling applications.
Because many telephones do not have hardware that supports speech processing, a voice server is placed in the network to act as a client on behalf of telephones.
Researchers and practitioners are extending VoiceXML using various techniques to provide new functionality. These include the RDC library tags, xHMI meta language, and a prototype implementation of VoiceXML which supports dictation speech recognition. RDC Tag Library Developers frequently use Struts1 or other application frameworks to generate HTML. The goal of the Reusable Dialog Component (RDC) project is to provide a similar framework for VoiceXML. Like Struts, RDC has a tag library that hides the
A Toolkit of Metrics for Evaluating VUIsInvestors use standard metrics such as stock price and projected revenue per share to choose investment opportunities. Likewise, consumers use standard metrics such as floor space, number of bedrooms, or number of bathrooms when purchasing houses. This paper presents a toolkit containing some specific metrics for evaluating voice user interfaces (VUIs). The speech industry should use criteria from this toolkit to: Judge the most efficient of several VUIs for
Many Web developers use XML to represent data and a transformation language, such as XSLT, ASP, or ColdFusion, to transform the XML data to an HTML user interface. Developers change the values of the XML data without having to manually recode the HTML user interface.
Michael Chavez, vice president of client services at ClickFox, explains that "by leveraging a strategic combination of customer behavior intelligence, customer service interviews and surveys, organizations can reduce customer frustration with IVR systems, which will result in drastic savings, while also improving customer satisfaction."
Posted 01 May 2005
James A. Larson
Matt Nickerson describes how mobile phones enable callers to speak and listen to virtual agents. Using the same device to speak with family, friends and business associates, callers speak with software agents that enable synthetic interviews with individuals in photographs of historical events in a museum. This represents a new way of interacting with objects that are usually only viewed.
At SpeechTEK 2004, a group of leading VUI designers attended the Voice User Interface (VUI) workshop directed by Dr. James A. Larson. Taking the lead for an article on the best practices in VUI, Dr. Larson collected and coordinated this team of VUI specialists to compile the Ten Guidelines for Designing a Successful Voice User Interface. Speech Technology Magazine would like to thank the authors for their contributions to this article and Dr. Larson for
Customers often ask questions about products, services, delivery dates and account information, as well as, offer suggestions and complaints. If customers do not receive satisfactory answers to their questions, they become disillusioned with the company and take their business elsewhere. In short, good customer service support is the key to repeat business.
Have you ever wished you could change your VoiceXML platform to use a speech synthesizer or speech recognizer from a different vendor? Have you ever wanted to move your speech synthesizer or speech recognizer to a different server? The Internet Engineering Task Force is proposing a new standard that will provide this flexibility.
The W3C Voice Browser Working Group reviewed more than 700 requests for change to VoiceXML 1.0. After careful deliberation, many of these were adopted, resulting in VoiceXML 2.0 which became a recommendation in March 2004. The VBWG is now working on two efforts to make VoiceXML even better.
A user profile contains information that describes how to personalize a speech user interface to meet the needs for a specific user.
New technology will change the way people interact with computers. PCs enabled users to use a keyboard and screen rather than review printed reports. The Xerox Star and Apple Macintosh introduced Graphical User Interfaces (GUIs) which made the mouse and other pointing devices popular. Now, we are on the verge of a revolution in technology that makes computing portable. Separating user interface devices from the computing device will dramatically change how people interact with computers.
A speech application does not work if users do not speak when prompted with a question.
Recently, the W3C Multimodal Working Group published a first working draft of EMMA the Extended MultiModal Annotation markup language EMMA (www.w3.org/TR/emma/). EMMAs intended use is to represent the semantics for information entered via various input modalities and the resulting integrated information.
Have you ever been in a place where speaking to a VoiceXML application on a cell phone is impractical? As you know, not all locations or situations are suitable for using speech-enabled handheld devices.
"Welcome to the Ajax speech application. It is possible to perform any of several actions at any time during this application, including the common actions of asking for help, transferring the call to an operator, stopping the application and returning to the main menu." This sample prompt is too long and confusing for most users. However, by using a controlled language, you can improve the prompt for your customers.
Speech standards include terminology, languages and protocols specified by committees of speech experts for widespread use in the speech industry. Speech standards have both advantages and disadvantages. Advantages include the following: developers can create applications using the standard languages that are portable across a variety of platforms; products from different vendors are able to interact with each other; and a community of experts evolves around the standard and is available to develop products and services based on the standard.
The Voice Browser Working Group has finished the technical work on the three major languages in the W3C Speech Interface FrameworkVoiceXML 2.0, the Speech Recognition Grammar Specification, and the Speech Synthesis Markup Language. These languages will soon become check-off items in a list of features provided by the leading speech platforms.
In the past three years, the World Wide Web Consortium Voice Browser Working Group has produced several reports that define languages in the W3C Speech Interface Framework. Developers use the W3C Speech Interface Framework languages to create speech applications.
Information processing and the Internet are merging with the telecommunications industry to develop mobile devices using interactive services with global access. Speech recognition offers the most natural way for consumers to use new communication devices and services.
PC users access the World Wide Web using a graphical user interface (GUI) that is commonly specified with HTML. Telephone and cell phone users access the Web using a verbal user interface (VUI) often specified with VoiceXML.
As the cartoon illustrates, users become frustrated when speech applications dont work. Testing minimizes this frustration by detecting and resolving many speech application problems before they cause user frustration.
VoiceXML has revolutionized the development of telephony applications, in that telephone users can call Web sites and converse with VoiceXML applications. The system uses a TTS synthesizer or prerecorded voice and users can respond by speaking answers to the questions. Currently VoiceXML is weak in telephony controls. About all you can do in VoiceXML is and , which are powerful enough for many applications, but not powerful enough for many others, such as event notification and conferencing. However, with the coming of new call control capabilities, many of these restrictions will be overcome.
VoiceXML and SALT are both markup languages that describe a speech interface. However, they work in very different ways, largely due to two reasons: (i) they have different goals, (ii) they have different Web heritages.
Student teams are very creative when asked to design and implement speech applications of their choice. Here are some of the prototype speech applications recently implemented by students at Georgia Institute of Technology, Washington State University, Portland State University and Oregon Health and Sciences University.
Users can choose from among several devices to access the World Wide Web. These devices include PCs with a visual Web browser, such as Netscape's Navigator or Microsoft's Internet Explorer, to interpret HTML files downloaded from a Web server and executed on the PC; telephones and cell phones with a verbal browser to interpret VoiceXML files downloaded from a Web server and executed on a voice server; and WAP phones with a visual browser to interpret WML files downloaded from a server and executed on the WAP phone.
The goal of speaking to your computer, and having it do what you say, has been a goal of IBMs speech recognition research team for over 25 years.
Tuesday Keynote Lunch Sponsor
Tuesday Break Sponsor
Press Room Sponsor