Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020108740 - METHOD FOR CONTROLLING A REAL-TIME CONVERSATION AND REAL-TIME COMMUNICATION AND COLLABORATION PLATFORM

Publication Number WO/2020/108740
Publication Date 04.06.2020
International Application No. PCT/EP2018/082739
International Filing Date 27.11.2018
IPC
H04M 3/527 2006.01
HELECTRICITY
04ELECTRIC COMMUNICATION TECHNIQUE
MTELEPHONIC COMMUNICATION
3Automatic or semi-automatic exchanges
42Systems providing special services or facilities to subscribers
50Centralised arrangements for answering calls; Centralised arrangements for recording messages for absent or busy subscribers
527Centralised call answering arrangements not requiring operator intervention
H04M 3/56 2006.01
HELECTRICITY
04ELECTRIC COMMUNICATION TECHNIQUE
MTELEPHONIC COMMUNICATION
3Automatic or semi-automatic exchanges
42Systems providing special services or facilities to subscribers
56Arrangements for connecting several subscribers to a common circuit, i.e. affording conference facilities
CPC
H04M 2201/40
HELECTRICITY
04ELECTRIC COMMUNICATION TECHNIQUE
MTELEPHONIC COMMUNICATION
2201Electronic components, circuits, software, systems or apparatus used in telephone systems
40using speech recognition
H04M 3/527
HELECTRICITY
04ELECTRIC COMMUNICATION TECHNIQUE
MTELEPHONIC COMMUNICATION
3Automatic or semi-automatic exchanges
42Systems providing special services or facilities to subscribers
50Centralised arrangements for answering calls; Centralised arrangements for recording messages for absent or busy subscribers
527Centralised call answering arrangements not requiring operator intervention
H04M 3/563
HELECTRICITY
04ELECTRIC COMMUNICATION TECHNIQUE
MTELEPHONIC COMMUNICATION
3Automatic or semi-automatic exchanges
42Systems providing special services or facilities to subscribers
56Arrangements for connecting several subscribers to a common circuit, i.e. affording conference facilities
563User guidance or feature selection
Applicants
  • UNIFY PATENTE GMBH & CO. KG [DE]/[DE]
Inventors
  • KLAGHOFER, Karl
  • SCHIFFER, Wolfgang
  • RODENBÜCHER, Michael
Agents
  • FRITZSCHE, Thomas
Priority Data
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) METHOD FOR CONTROLLING A REAL-TIME CONVERSATION AND REAL-TIME COMMUNICATION AND COLLABORATION PLATFORM
(FR) PROCÉDÉ DE COMMANDE D'UNE CONVERSATION EN TEMPS RÉEL ET PLATEFORME DE COMMUNICATION ET DE COLLABORATION EN TEMPS RÉEL
Abstract
(EN)
The present invention relates to a method for controlling a real-time communication between at least two participants (A, B, C) on a real-time conversation and collaboration platform (1) by means of a digital assistant unit (8), wherein clients (2, 3, 18) are connected to a conferencing application via a communications network establishing the communication, the method comprising the steps of identifying, from the at least two participants (A, B, C), a first participant (A) as an active speaker in the conversation by using audio signals received from the first participant (A) via a microphone, activating the digital assistant unit (8) for the first participant (A), if a predetermined event is detected, wherein the audio signals received from the first participant (A) are analyzed so as to identify voice commands therefrom, wherein an Automatic Speech Recognition (ASR) engine (12) performs a voice recognition procedure for identifying and transcribing the identified voice commands, and wherein the transcribed voice commands are analyzed and executed. Communication from the participant to the digital assistant is via an additional audio channel.
(FR)
La présente invention concerne un procédé de commande d'une communication en temps réel entre au moins deux participants (A, B, C) sur une plateforme de conversation et de collaboration en temps réel (1) au moyen d'une unité d'assistant numérique (8), des clients (2, 3, 18) étant connectés à une application de conférence par l'intermédiaire d'un réseau de communications établissant la communication, le procédé comprenant les étapes consistant à : identifier, parmi les au moins deux participants (A, B, C), un premier participant (A) en tant que locuteur actif dans la conversation en utilisant des signaux audio reçus en provenance du premier participant (A) par l'intermédiaire d'un microphone, activer l'unité d'assistant numérique (8) pour le premier participant (A), si un événement prédéterminé est détecté, les signaux audio reçus en provenance du premier participant (A) étant analysés de façon à identifier des commandes vocales à partir de ceux-ci, un moteur de reconnaissance vocale automatique (ASR) exécutant une procédure de reconnaissance vocale pour identifier et transcrire les commandes vocales identifiées, et les commandes vocales transcrites étant analysées et exécutées. La communication du participant à l'assistant numérique se fait par l'intermédiaire d'un canal audio supplémentaire.
Latest bibliographic data on file with the International Bureau