Call voice recognition system

TWM687579UActive Publication Date: 2026-09-11CATHAY LIFE INSURANCE CO
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
TW115205919
Authority / Receiving Office
TW · TW
Patent Type
Utility models
Current Assignee / Owner
Filing Date
2026-06-26
Publication Date
2026-09-11
Estimated Expiration
2036-06-25

Smart Images

  • Figure TWG2TB001911330_001
    Figure TWG2TB001911330_001
  • Figure TWG2TB001911330_002
    Figure TWG2TB001911330_002
  • Figure TWG2TB001911330_003
    Figure TWG2TB001911330_003
Patent Text Reader

Abstract

A voice recognition system includes a processing unit, a communication unit electrically connected to the processing unit, and a storage unit. The storage unit stores a speech-to-text module. After a call is made between a client device and a client terminal device, the processing unit receives multiple voice messages from the client device and inputs each voice message into the speech-to-text module to obtain multiple text messages corresponding to the voice messages. Each text message includes text content, a speaker identification stamp, and a timestamp. The processing unit stores the voice messages and text messages in the storage unit and provides a call text interface displaying the text messages to the client device via the communication unit, enabling the client device to display the call text interface.
Need to check novelty before this filing date? Find Prior Art

Claims

1. A voice recognition system for a client device and a voice assistant device, comprising: a communication unit for providing network connectivity; a storage unit for storing a voice-to-text module for converting voice into text; and a processing unit electrically connected to the communication unit and the storage unit for communicating with the client device via the communication unit, and receiving multiple voice messages from the client device after a call between the client device and the voice assistant device, wherein the processing unit inputs each voice message into the voice-to-text module, causing the voice-to-text module to perform speaker recognition and semantic segmentation on the voice messages to obtain multiple text messages corresponding to the voice messages, each text message including text content, a speaker identification stamp and a timestamp, the processing unit storing the voice messages and the text messages in the storage unit, and providing a voice text interface for displaying the text messages to the client device via the communication unit, causing the client device to display the voice text interface.

2. The call voice recognition system as described in claim 1, wherein, Only after receiving an interface display instruction from the client device will the processing unit provide the call text interface that displays such text messages to the client device.