C. SCHMANDT. Voice communication with computers. New York: Van Nostrand Reinhold, 1994.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....as the foundation for building speech systems[9] Our practical reason is that in such a system it is easier to evaluate the contribution of prosodic information. Thus the goal of this research is to create a system capable of natural dialog using prosody only. 2 TASK Following Schmandt[6][7], we set our system the task of conveying to the user directions for how to go from one place to another. Unlike Schmandt, who worked with English, we chose to work with Japanese. Specifically, our users were instructed to listen to the directions and take notes so they would be able to go to the ....

....fortunately this response was generally appropriate. This was also followed up by ii , meaning okay , in cases where the user subsequently fell silent. Mumble 1, which has 100ms regions of low pitch cue, always is followed by un , and mumble 2 is never followed by un . In Schmandt s system[6][7], one utterance of the user corresponds to one segment of the system. In our system, user can utter several times for one segment of the system. And Schmandt s system repeats previous segment as answer to user s question, but our system outputs affirmative reply. 5 EVALUATION METHOD We contrived ....

[Article contains additional citation context not shown here]

Schmandt, Christopher. "Voice Communication with Computers", VNR Computer Library :199 -- 204, 1994

....to the square of the number of users, to the new technology. The MIT Wearable Computing Project at the Media Laboratory was developed with this principle in mind 1 . While there have been other such living experiments using pagers, palmtops, cell phones, instrumented environments, and cameras [3, 13, 19, 14, 1, 6], the MIT Wearable Computing Project is unique in its approach to applying computation to common, almost mundane, situations in a user s life. The project was started and maintained by students intent on developing tools for the intimate use of and everyday life with wearable computers. Emphasis ....

C. Schmandt. Voice Communication with Computers. Van Nostrand Reinhold, New York, 1994.

....of automatic methods to index and retrieve spoken documents will become more important. In addition, the development of these methods will have a significant impact on the use of speech as a data type because speech is currently a very di#cult medium for people to browse and search e#ciently [42]. One approach to the task of spoken document retrieval (SDR) is to perform keyword spotting on the spoken documents to obtain a representation in terms of a small set of keywords [12,25,39] In order to process the speech messages, the set of keywords needs to be chosen apriori. This either ....

C. Schmandt, Voice Communication with Computers (Conversational Systems). New York: Van Nostrand Reinhold, 1994.

....The speaker indexing system is currently being incorporated into several application systems in the Speech Group at the MIT Media Lab. 1. Introduction The Speech group at the MIT Media Lab is exploring methods for accessing large amounts of recorded speech efficiently (Arons, 1994; Mullins, 1995; Schmandt, 1994). One approach we are taking is to tag salient segments of a speech recording, and then design interfaces to navigate through the speech using those tags (Arons, 1994; Mullins, 1995) Early versions of these systems relied primarily on pause and pitch information to locate salient segments of ....

Schmandt, C. (1994). Voice Communication with Computers. New York: Van Nostrand Reinhold.

....For example, an indoor paging system might use position information to determine if someone is available for a last minute meeting. Monitoring systems for high security areas can use position information to track employees and visitors. User and interaction modeling systems [Want and Hopper, 1992, Schmandt, 1994, Lamming and Flynn, 1994, Orwant, 1996] might use position information to reroute resources (e.g. an incoming call to the nearest telephone) predict the next action of the user, or provide automatic annotation of a meeting (e.g. to answer queries such as who was I talking with in the stairs on ....

Schmandt, C. (1994). Voice Communication with Computers. Van Nostrand Reinhold, New York.

....Today, most outdoor positioning is performed in relation to the Global Positioning System (GPS) Differential systems can obtain accuracies of less than one meter, and update rates of one second are common. However, indoor systems require different methods. Current systems such as active badges [21, 15, 4, 10] and beacon architectures [6, 14, 18] require increased infrastructure for higher accuracy. This increased infrastructure implies increased installation and maintenance. However, in the Patrol task, we attempt to determine location based solely on the images provided by the Patrol hat cameras, ....

C. Schmandt. Voice Communication with Computers. Van Nostrand Reinhold, New York, 1994.

....to be disturbed, should take messages if phone or electronic messages arrive. However, in the case of an emergency message, the computer should understand enough of the context to grab the user s attention immediately. The computer should also be able to identify urgent or time critical messages (Schmandt, 1994) and wait for a break in the conversation to post a summary message discreetly onto the user s heads up display. A user model should also predict the user s next action or state. Such information can be used to allocate resources pre emptively. For example, suppose the user enjoys music while ....

Schmandt, C. (1994). Voice Communication with Computers.

....was used to generate the graphical components of the interface [Ousterhout] and a C program was used to provide the underlying functionality. Audio functions such as playing selected segments of sounds files were achieved by using the Audio Server developed by the Speech Group at the Media Lab [Schmandt]. The Tcl C based simulation proved to be an extremely efficient way to design the hand held s interface. The Tcl component of the simulation guided the choice of buttons and LCD display used in the hardware design, and about 80 of the C Implementation of the Hand Held 55 code from the ....

Schmandt, C. Voice Communication with Computers. New York: Van Nostrand Reinhold, 1994.

No context found.

C. Schmandt, Voice Communication with Computers.VNR: 1994.

....generated by the system. It also lets the user select stories which it will use for future filtering and newscast construction decisions. 5.2.1 SoundViewer Widget The audio of the current broadcast is the main focus of the application window, as shown in the SoundViewer widget of Figure 5. 2 [25]. Current Playback Time Total Length Annotated Story Boundaries Figure 5.2: Detail of the SoundViewer widget. This widget controls playback of the audio and has many built in features. Via mouse control (clicking and dragging in the widget window itself) the user can start and stop playback, and ....

C. Schmandt, Voice Communication with Computers. New York: Van Nostrand Rheinhold, 1994, pp. 282-285.

....protocol with a user to communicate its abilities, constraints, and level of understanding [Hayes83] It allows a system to gracefully deal with speech recognition errors due to out of vocabulary utterances and unpredictable phenomenon like background noise. An effective conversational approach [Schmandt94a] utilizes directive and time out prompts, implicit, explicit and context free confirmations, and modeling of dialogue states and transitions to better represent conversational flow. Higher levels of linguistic knowledge based on syntactic and semantic constraints as well as discourse structure can ....

Schmandt, Chris. Voice Communication with Computers. Van Nostrand Reinhold, 1994.

No context found.

C. SCHMANDT. Voice communication with computers. New York: Van Nostrand Reinhold, 1994.

No context found.

C. Schmandt. Voice Communication with Computers. Van Nostrand Reinhold, New York, 1994.

No context found.

Schmandt, C. (1994). Voice Communication with Computers. Conversational Systems. New York, NY: Van Nostrand Reinhold.

No context found.

Schmandt, C. (1994). Voice Communication with Computers. Van Nostrand Rheinhold, New York. 193 Interaction. Reading, MA, Addison-Wesley

No context found.

Schmandt, C. Voice Communication with Computers. Van Nostrand Reinhold, New York, 1994.

No context found.

C. Schmandt. Voice Communication with Computers. Van Nostrand Reinhold, New York, NY, 1994.

No context found.

Schmandt, C. Voice Communication with Computers. Van Nostrand Reinhold, 1994.

No context found.

Schmandt, C. (1994). Voice Communication with Computers. Van Nostrand Reinhold, New York.

No context found.

Christopher Schmandt (1994). Voice Communication with Computers. Van Nostrand Reinhold, New York.

No context found.

Schmandt, C. Voice Communications with Computers, Conversational Systems. Van Nostrand Reinhold, New York, 1993.

No context found.

Schmandt, C. 1994. Voice communication with computers. New York: Van Nostrand Reinhold.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC