Abstract:
A method of prioritizing emergency calls received at a public safety answering point (PSAP) management system. New emergency calls can be placed on hold and added to a call queue. An audio emergency description message can be recorded from the caller while the emergency call is on hold, and a transcript of the audio emergency description message can be generated using automatic speech recognition. The transcript can be displayed to users in a dashboard while the emergency call is on hold, and a priority level of the emergency call can be adjusted within the call queue based on the transcript, such that urgent emergency calls can be prioritized and answered before less urgent emergency calls.
Abstract:
Embodiments of the present disclosure may relate to a system [100] and a method [400] for blocking or accepting a call received from a first device [102A]. In an embodiment, the first device [102A] transmits an attach request (comprising at least one of the user intent, the call type and the caller details) to the network entity [104]. Subsequently, the network entity [104] extracts at least one of the user intent, the call type and the caller details from the received message to compare the at least one of the user intent, the call type and the caller details with a rejection list. The network entity [104] blocks the call in case any one of the user intent, the call type and the caller details is identified in the rejection list; or else, the network entity [104] establishes the call between the first device [102A] and the second device [102B].
Abstract:
Natural speech dialog system and methods are disclosed. In one example, a method includes identifying a dialog system intent associated with the speech input based on at least one predetermined intent keyword, the dialog system intent having required intent parameters, determining whether data for all required intent parameters of the dialog system are available, based on the determination, selectively initiating a parameter collection dialog associated with the dialog system intent, the parameter collection dialog being operable to collect data for the required parameters not otherwise available to the dialog system intent, and based on the dialog system intent and one or more required parameters, generating an action instruction.
Abstract:
Various embodiments provide real-time translation of a voicemail into a readable format as the voicemail is being recorded. In some cases, a system server records the voicemail by first answering a call from an originating device that goes unanswered by a destination device. Upon answering the call, the voicemail server translates the recording, while it is being recorded, into a readable format. The voicemail server forwards SMS containing portions of the tranlated text to the destination device, the first SMS comprising callpickup infomation. In turn, as the destination device receives portion(s) of the real-time translation, it can display the associated content, and/ or update what is displayed as new portions are received. At times, the destination device provides additional call control that interrupts the voicemail while it is being recorded and converted to text at the voicemail server, and redirects the call to the destination device if the originating device is still connected.
Abstract:
A computer based system and method for translation and communication of messages includes sending a message in a source language using a transmission protocol from a first client device to a second client device. The source language message is transmitted using a transmission protocol to a translation server for translating the message from the source language to a destination language by either the first or second client device. The message, in its destination language form, is displayed and stored. The translation server is either on-line or off-line. Text-to-voice and voice-to-text converters are used for conversion of original text messages to voice, or of original voice to text, for transmission to the second client device.
Abstract:
La presente invención se refiere a un método y un sistema para obtener información relevante de una comunicación por voz entre al menos dos usuarios. El método comprende: proporcionar la comunicación por voz que comprende al menos dos flujos de voz pertenecientes a los al menos dos usuarios; generar marcadores con sellos de tiempo asociados a los al menos dos flujos de voz según determinadas características extraídas de los al menos dos flujos de voz; extraer determinada información de los al menos dos flujos de voz según cierta información que comprenden los marcadores; y transcribir la determinada información en texto para obtener la información relevante de la comunicación por voz.