Audio call evaluation method, evaluation device and computer storage medium
A technology for audio calls and evaluation equipment, applied in speech analysis, speech recognition, instruments, etc., can solve the problems of inability to objectively reflect the effect of calls and low efficiency, and achieve the effect of solving evaluation errors and improving evaluation efficiency.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
example 1
[0123] The audio call evaluation method provided in this example includes three stages: corpus preparation, test execution, and quality evaluation.
[0124] Corpus preparation (comprising audio and the corresponding text of audio) may comprise the following steps:
[0125] Step p1. Select a speech recognition program that can convert speech output into text output. A speech recognition program can be used for speech recognition.
[0126] Step p2. Prepare a piece of reference audio (referred to as reference audio) and corresponding text (referred to as reference text). The reference audio may be but not limited to a piece of news broadcast. The reference audio can include: different versions of audio, for example, male voice version audio, female voice version audio, children's voice version audio, official language version audio, and dialect version audio. The normal playback speed of the reference audio can last for The predetermined duration is, for example, about 2 minut...
example 2
[0155] Figure 5 It is a complete audio call evaluation system, which consists of two parts: the reference audio sending end, the reference audio receiving end and the evaluation end. The transmitting end of the reference audio transmits the prepared reference signal of the reference audio to the device under test. The acquisition module collects the damaged audio data received by the device under test through the acquisition interface; the recognition module recognizes the voice data, converts the voice data into recognition text, and the evaluation module uses the recognition text output by the recognition module and the reference audio The relative reference text is used as input, and the MSS score is calculated.
[0156] Taking the test of the handheld mobile station as an example, a voice call is first established between two mobile stations (1 and 2). The reference signal sending end transmits the reference audio signal to the mobile station 1 under test; the evaluatio...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com