Dismiss
InnovationQ will be updated on Sunday, Oct. 22, from 10am ET - noon. You may experience brief service interruptions during that time.
Browse Prior Art Database

Method of individual Text to Voice message in instant messaging

IP.com Disclosure Number: IPCOM000248702D
Publication Date: 2016-Dec-28
Document File: 2 page(s) / 52K

Publishing Venue

The IP.com Prior Art Database

Abstract

As we know, social chat and instant messaging are becoming more and more popular and essential whatever for our daily work or our life. Currently in the existing instant messaging methods, rich text, audio, video messages are all alternative for users during chat, but generally only one method per time can be selected, and when the situation is inconvenient for user to view the message, a more flexible and cognitive method provided for users is required. For example, when user is driving car, it's dangerous if he wants to see the text message. This article will involve transformation from text messages to audio automatically to improve the convenience and user experiences.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 100% of the total text.

1

Method of individual Text to Voice message in instant messaging

This invention will involve transformation from text messages to audio automatically to improve the convenience and user experiences.

And the key point for our invention is to focus each individual during chat, through analysis a specific person's original audio, then transform his new messages by his own voice and play for receiver. When user chat in IM, software can according to the contact list, classification, then collect and analyst of the contacts of voice recording, according to audio recording, when the person input and send text messages to chat, users can automatic converse to the corresponding person's voice.

Steps:

1. Get the list of contacts for the user.

2. Analysis of each contact stored in the server side of the voice records, extract the contact tone of voice and audio and other personal characteristics of the sound information.

3. According to the analysis of step 2 the results of the synthesis of the voice of each contact.

4. When user uses the text content convert to voice chat, with the sound of step three to read text messages.

Architecture:

2

Components:

Voice Analyzer - Analyze the voice of each contact, gather the voice characteristic data;

Voice Simulator - Simulate individual and personalized voice via his voice characteristic;

Audio Player - Play and transmit the individual voice to user from text message;

DataStore - Store voice characteristic data for each individual.