System and method of providing generated speech via a network

摘要

A system and method of operating an automatic speech recognition application over an Internet Protocol network is disclosed. The ASR application communicates over a packet network such as an Internet Protocol network or a wireless network. A grammar for recognizing received speech from a user over the IP network is selected from a plurality of grammars according to a user-selected application. A server receives information representing speech over the IP network, performs speech recognition using the selected grammar, and returns information based upon the recognized speech. Sub-grammars may be included within the grammar to recognize speech from sub-portions of a dialog with the user.

主权项

1. A method comprising:
selecting a spoken dialog application from a plurality of spoken dialog applications; transmitting, over a network, an identification of the selected spoken dialog application, the spoken dialog application having a grammar identifier; selecting a grammar from a plurality of grammars based on the grammar identifier, wherein the grammar is provided by the selected spoken dialog application and chosen from a predetermined group of grammars based upon information provided by the selected spoken dialog application; transmitting digitized user speech over the network while receiving user speech which is digitized into the digitized user speech; receiving partially synthesized speech in response to the digitized user speech, wherein the selected spoken dialog application recognizes the digitized user speech using the grammar; and receiving final synthesized speech in response to the digitized user speech, wherein the receiving of the final synthesized speech occurs after receiving the partially synthesized speech.