Method for simplifying acoustic model analysis through applying audio frame frequency spectrum flatness and device thereof
一种声学模型、音频帧的技术,应用在语音分析、仪器等方向,能够解决影响系统效率、声学模型分析多余、运算量增加等问题
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0034] The invention discloses a method for simplifying acoustic model analysis by applying the spectral flatness of audio frames. The main concept is to use the spectral flatness to determine the block type of an audio signal and whether it is the same or different signal type. (middle / side type, M / S type), thereby simplifying the execution of acoustic model analysis to increase the efficiency of compression.
[0035] Please refer to Figure 4 , Figure 4 It is a schematic diagram of a process 40 according to Embodiment 1 of the present invention. The process 40 applies audio frame spectral flatness to simplify acoustic model analysis, which includes the following steps:
[0036] Step 400: start.
[0037] Step 402: Calculate the frequency-domain energy of multiple audio frames included in an audio signal.
[0038] Step 404: Calculate multiple spectral flatnesses of the multiple audio frames according to the energy of the multiple audio frames in the frequency domain.
[00...
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