Systems and methods for providing real-time automated language translations
AssigneeVonage Business Inc.
InventorTony Chan Sion Moy
Life of this patent
Estimating the term…
Abstract
Systems and methods for providing one-to-one and audio and video calls or for providing multi-party audio or video conferences also provide language translation services. When language translation services are provided, a party to a call or conference hears both the audio of the speaker, and a translated version of the speaker's audio.
Claims18
A system for providing real-time language interpretation in an audio or video communication session, comprising:
- a communications platform for connecting first and second parties in an audio or video communication session, wherein the communications platform receives spoken audio input in a first language from the first party and spoken audio input from the second party;
- a transcription module operatively connected to the communications platform that is configured to generate separate transcriptions of the spoken audio input provided by the first and second parties;
- a translation module operatively connected to the transcription module and configured to receive a transcription of the first party's spoken audio input from the transcription module and to create a translated transcription of the first party's spoken audio input in a second language;
- and
- a text-to-speech module operatively connected to the translation module that is configured to generate a spoken audio version of the first party's translated transcription in the second language;
- wherein the communications platform is configured to provide to the second party, at approximately the same time, both the first party's spoken audio input in the first language and the spoken audio version of the first party's translated transcription in the second language;
- and
- wherein when the second party begins to provide spoken audio input while the communication platform is still providing the first party's translated transcription in the second language to the second party, the communication platform stops providing the first party's translated transcription in the second language to the second party.
A method of connecting multiple participants to an audio or video communication session and of providing selected translations to the session participants, comprising:
- receiving, from a first communication device, first spoken audio input in a first language provided by a first participant;
- receiving, from a second communication device, second spoken audio input in a second language provided by a second participant;
- obtaining a first transcription of the first spoken audio input;
- obtaining a first translated transcription of the first spoken audio input that is in a second language;
- obtaining a spoken audio version of the first translated transcription in the second language;
- causing the second communications device to play, at approximately the same time, both the first spoken audio input and the spoken audio version of the first translated transcription;
- receiving, from the second communication device, third spoken audio input provided by the second participant while the second communications device is playing the spoken audio version of the first translated transcription;
- and
- causing play of the spoken audio version of the first translated transcription by the second communication device to end when receipt of the third spoken audio input begins.
A non-transitory computer-readable medium containing a set of instructions that, when performed by one or more processors, cause the one or more processors to perform a method of connecting multiple participants to an audio or video communication session and of providing selected translations to the session participants, the method comprising:
- receiving, from a first communication device, first spoken audio input in a first language provided by a first participant;
- receiving, from a second communication device, second spoken audio input in a second language provided by a second participant;
- obtaining a first transcription of the first spoken audio input;
- obtaining a first translated transcription of the first spoken audio input that is in a second language;
- obtaining a spoken audio version of the first translated transcription in the second language;
- causing the second communications device to play, at approximately the same time, both the first spoken audio input and the spoken audio version of the first translated transcription
- receiving, from the second communication device, third spoken audio input provided by the second participant while the second communications device is playing the spoken audio version of the first translated transcription, and
- causing play of the spoken audio version of the first translated transcription by the second communication device to end when receipt of the third spoken audio input begins.
Dependencies are inferred from the claim text.