Efficient content classification and loudness estimation

A loudness, payload technology, used in speech analysis, instrumentation, etc., to solve problems such as imperfection, misclassification that affects loudness calculations, and no additional processing work expected

A loudness, payload technology, used in speech analysis, instrumentation, etc., to solve problems such as imperfection, misclassification that affects loudness calculations, and no additional processing work expected

CN103582913AInactive Publication Date: 2014-02-12DOLBY INT AB
5 Cites 16 Cited by

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Efficient content classification and loudness estimation
  • Efficient content classification and loudness estimation
  • Efficient content classification and loudness estimation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0166] According to one embodiment, the scale factor band energy is used instead of the spectral power density used to calculate the average spectral slope described above. An example table of MDCT index 0 sets (Nm) for a sampling rate of 48kHz is shown in the table below. The scaling factor band energy is calculated as follows:

[0167] Z m = Σ n = N m N m + 1 - 1 | x n 2 | for 0 m ≤ 46

[0168] Z m = scale factor band (sfb) energy of index m

[0169] x n = MDCT coefficient of index n, 0

[0170] N m = MDCT index offset of sf...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The present document relates to methods and systems for encoding an audio signal. The method comprises determining a spectral representation of the audio signal. The determining a spectral representation step may comprise determining modified discrete cosine transform, MDCT, coefficients, or a Quadrature Mirror Filter, QMF, filter bank representation of the audio signal. The method further comprises encoding the audio signal using the determined spectral representation; and classifying parts of the audio signal to be speech or non-speech based on the determined spectral representation. Finally, a loudness measure for the audio signal based on the speech parts is determined.

Description

technical field [0001] This paper relates to methods and systems for active content classification and loudness estimation of audio signals. In particular, it relates to active content classification and gated loudness estimation within audio encoders. Background technique [0002] Portable handheld devices such as PDAs, smartphones, mobile phones, and portable media players often include audio and / or video rendering capabilities and have become important entertainment platforms. The continued penetration of wireless or wired transmission capabilities into such devices drives their development forward. Thanks to the support of media transmission and / or storage protocols such as the High Efficiency Advanced Audio Coding (HE-AAC) format, media content can be continuously downloaded and stored to portable handheld devices, providing a practically unlimited amount of media content . [0003] HE-AAC is a lossy data compression scheme for digital audio defined as the MPEG-4 aud...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
12 Feb 2014
Publication
CN103582913A
IPC
G10L19/16; G10L19/24; G10L25/78
CPC
G10L2025/783; G10L19/167; G10L19/24; G10L25/93
Inventors
哈拉尔德·蒙特; 阿里希特·比斯瓦斯