Method and system for transcription of spoken language

摘要

A method and system for transcription of spoken language into continuous text for a user comprising the steps of inputting spoken language of at least one user or of a communication partner of the at least one user into a mobile device of the respective user, wherein the input spoken language of the user is transported within a corresponding stream of voice over IP data packets to a transcription server; transforming the spoken language transported within the respective stream of voice over IP data packets into continuous text by means of a speech recognition algorithm run by said transcription server, wherein said speech recognition algorithm is selected depending on a natural language or dialect spoken in the area of the current position of said mobile device; and outputting said transformed continuous text forwarded by said transcription server to said mobile device of the respective user or to a user terminal of the respective user in real time.

主权项

1. A transcription method for transcription of spoken language into continuous text for a hearing impaired user comprising the steps of:
(a) inputting spoken language of at least one hearing impaired user or of a communication partner of the at least one hearing impaired user into a mobile device of the respective user, (b) transporting the input spoken language as payload data within a corresponding stream of voice over IP data packets from said mobile device via a communication network to a transcription server; (c) detecting a current position of said mobile device by evaluating position data carried in a header of said voice over IP data packets and selecting a source language automatically depending on the detected current position of said mobile device wherein the position data is provided by a GPS unit integrated in the mobile device or corresponds to an assigned IP address of the mobile device; (d) selecting a target language of the hearing impaired user automatically by evaluating a user-ID carried in the header of said voice over IP data packets; (e) switching streams of voice over IP data packets transporting the spoken language as payload data received by said transcription server via said network from said mobile device by a switching unit of said transcription server to different terminals of speech repeating operators depending on the area of the detected current position of said mobile device of the user, wherein the terminals of the different speech repeating operators are located in a call center or in a home office connected to said transcription server via said communication network; (f) outputting said transported spoken language to said speech repeating operators which re-voice the output spoken language, wherein the speech repeating operators are suited operators speaking the matching native language of the detected current position of said mobile device of the user; and (g) forwarding the re-voiced language by said switching unit of said transcription server to a speech recognition unit of said transcription server which transforms the re-voiced spoken language into continuous text by use of a suited speech recognition algorithm selected from different speech recognition algorithms depending on the detected current position of said mobile device.