VoiceXML is an XML-based markup language that allows the creation of audio dialogs utilizing synthesized speech, recorded audio, speech recognition, and touch-tone input. It was designed to work with technologies like text-to-speech, automatic speech recognition, and enable integration with enterprise software. VoiceXML provides a common language for developers, tool providers, and platform providers to build voice applications and services while shielding them from low-level implementation details. Some examples of applications include order inquiries, package tracking, driving directions, emergency notifications, and voice access to email.
In this document
Powered by AI
Presentation by Abbas Hashmi on VoiceXML, a markup language for audio dialogues.
VoiceXML enables audio dialogs using speech synthesis, recognition, and digitized audio.
Overview of previous technologies like IVR and pre-VoiceXML engines, detailing their limitations.
Introduction to the architectural model underlying VoiceXML applications.
Enabled technologies include Automatic Speech Recognition (ASR) and Text-To-Speech (TTS).
Sample VoiceXML code demonstrating user interaction via prompts and field inputs.
VoiceXML minimizes server interactions, separates code from logic, and is user-friendly.
Limitations include lack of speech training support and slower conversational bandwidth compared to GUI.
Commercial applications of VoiceXML include order tracking, emergency notifications, and CRM.
VoiceXML is poised to bridge the digital divide with support from major tech companies for speech applications.
Conclusion slide thanking participants and prompting for questions.
Slide prompting for any questions from the audience.
VoiceXML Voice ExtensibleMarkup Language is designed for creating audio dialogs that feature synthesized speech, digitized audio, recognition of spoken and DTMF key input, recording of spoken input, telephony, and mixed initiative conversations.
3.
Previously used voiceappl. IVR(Interactive Voice Responce) Application A special purpose computer outfitted with telephony hardware Pre-VoiceXML dialogue engines Non-programmable
Example <?xml version="1.0"encoding="UTF-8"?> <vxml xmlns=“url" xmlns:xsi=“url“ xsi:schemaLocation=“url" version="2.0"> <form> <field name="drink"> <prompt>Would you like coffee, tea, milk, or nothing? </prompt> <grammar src="drink.grxml" type="application/srgs+xml"/> </field> <block> <submit next=“url"/> </block> </form> </vxml>
7.
ADVANTAGES VoiceXML isa markup language that: Minimizes client/server interactions by specifying multiple interactions per document. Shields application authors from low-level, and platform - specific details. Separates user interaction code (in VoiceXML) from service logic (e.g. CGI scripts). Promotes service portability across implementation platforms. VoiceXML is a common language for content providers, tool providers, and platform providers. Is easy to use for simple interactions, and yet provides language features to support complex dialogs.
8.
DISADVANTAGES No specialanalysis of speech input Not suitable for training speech skills—Reading, ESL, singing, etc. VUI conversational bandwidth is slower than GUI conversational bandwidth Using a VUI is like drinking from Lake Superior with a straw
9.
Applications Many commercialVoiceXML applications have been deployed, processing millions of telephone calls per day. Few are order inquiry package tracking driving directions emergency notification voice access to email customer relationship management
10.
Conclusion Reduce thedigital devide VoiceXML is an exciting new standard with support from the largest companies in the computing and telecommunications industries VoiceXML has been proposed as a standard language to develop Internet speech applications. Besides, the distributed architecture of VoiceXML documents makes speech applications possible to be shared in the Internet