A speech understanding shunt method based on speech necessity judgment

By performing automatic speech recognition and prosodic acoustic feature extraction on the input speech, and combining confidence and uncertainty to determine the necessity of the speech, the problem of lacking pre-judgment in the existing technology is solved, and path diversion is realized in the pre-stage of speech understanding, thereby improving the accuracy and processing efficiency of speech understanding.

CN122511252APending Publication Date: 2026-08-04HARBIN INST OF TECH
0 Cites 0 Cited by

Patent Information

Application Number
CN202610639746.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-05-11
Publication Date
2026-08-04

AI Technical Summary

Technical Problem

Existing technologies lack a prior assessment of the necessity of preserving the original speech, which makes it difficult for speech understanding processing to accurately understand under different intonations, pauses, stresses and speech rates, and the processing cost is high, especially when the same processing link is used for both simple and complex samples.

Method used

Automatic speech recognition is performed by receiving input speech, extracting prosodic acoustic features, and judging the necessity of speech by combining recognition confidence and text uncertainty. It then decides whether to use the text transcription model path or the end-to-end speech model path, controls processing costs, and calls the context agent for conflict correction.

Benefits of technology

While ensuring the accuracy of speech understanding, processing costs were controlled, improving the ability to process both simple and complex samples and reducing unnecessary high-cost processing overhead.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

This invention discloses a speech understanding triage method based on speech necessity judgment, belonging to the field of speech recognition technology. To address the problems of existing technologies lacking pre-judgment of the necessity of preserving the original speech and struggling to balance speech understanding accuracy and processing cost, this invention performs automatic speech recognition on the input speech and extracts prosodic acoustic features. Based on recognition confidence, prosodic acoustic features, and text uncertainty, it determines whether the current input speech must rely on the prosodic and acoustic information in the original speech, thereby determining whether to use a text transcription model path or an end-to-end speech model path, and outputs the speech understanding result based on the corresponding path result. This invention can control processing costs while ensuring speech understanding accuracy, achieving a beneficial effect that balances understanding accuracy and efficiency. It is applicable to fields such as intelligent terminal voice interaction, speech recognition, natural language understanding, and intelligent human-computer interaction.
Need to check novelty before this filing date? Find Prior Art