# US 2022/0044674 A1 · Ai speech recognition system capable of selecting models

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2022/0044674 A1
- Document ID: US20220044674A1
- Status: Published application
- Kind: A1
- Application number: 16/988,745
- Filed: 2020-08-10
- Published: 2022-02-10
- Earliest claimed: 2020-08-10
- Assignees: National Chiao Tung University
- Applicants: National Chiao Tung University
- Inventors: Sin Horng CHEN; Yuan Fu LIAO; Yih Ru WANG; Shaw Hwa HWANG; Bing Chih YAO; Cheng Yu YEH; You Shuo CHEN; Yao Hsing CHUNG; Yen Chun HUANG; Chi Jung HUANG; Li Te SHEN; Ning Yun KU
- Web page: https://patentgrep.com/patent/US20220044674A1

## CPC

- G10L 15/183: using context dependencies, e.g. language models
- G10L 15/32: Multiple recognisers used in sequence or in parallel; Score combination systems therefor, e.g. voting systems
- G06N 3/04: Architecture, e.g. interconnection topology
- G06N 3/0499: Feedforward networks
- G06N 3/08: Learning methods
- G06N 3/09: Supervised learning
- G10L 15/16: using artificial neural networks
- G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L 15/30: Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
- G10L 15/063: {Training}
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

The present invention provides a system for selecting a special speech recognition model through a general model of an AI speech recognition system for users to select an appropriate model. In addition to the AI speech recognition server of a general model, the present invention additionally prepares speech models in various fields, such as sports event model, financial news model, and game live model. Different users can choose different speech models according to their needs or fields, and they can get better services respectively. If the different users have no special choice, the AI speech recognition server of the general model provides speech recognition services for the different users.

## Claims

### Claim 1

An AI speech recognition system capable of selecting models, comprising:
(a) an AI speech recognition server of a general model;
(b) prepare at least one different AI speech recognition server of a special model;
(c) the at least one different AI speech recognition server of the special model is controlled by the AI speech recognition server of the general model to accept a selection of different users for providing speech recognition service for the different users;
(d) if the different users have no special choice, then the AI speech recognition server of the general model provides speech recognition services for the different users.

### Claim 2 (depends on 1)

The AI speech recognition system capable of selecting models according to claim 1, wherein the at least one different AI speech recognition server of the special model is generated by using an artificial neural network as a trainee for learning AI speech recognition; various speech data are inputted into the artificial neural network for generating a text result; thereafter the text result and a text data are inputted into a calculating error; a result of the calculating error is inputted into a parameter model for adjustment, and then to be inputted into the artificial neural network for generating the text result again; repeat in this way for several times to obtain a best parameter model; after a lot of learning and training, the text data and the calculating error are removed to obtain the special model of speech recognition server in relevant field.
