Patent classifications
G
PHYSICS
Load children
G10
MUSICAL INSTRUMENTS; ACOUSTICS
Load children
G10L
SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
Load children
19/00
Speech or audio signals analysis-synthesis techniques for redundancy reduction, e.g. in vocoders; Coding or decoding of speech or audio signals, using source filter models or psychoacoustic analysis
Load children Filter patents View analytics View as hierarchy Open in page
G10L19/08
Determination or coding of the excitation function; Determination or coding of the long-term prediction parameters
Load children Filter patents View analytics View as hierarchy Open in page
G10L19/10
the excitation function being a multipulse excitation
Load children Filter patents View analytics View as hierarchy Open in page

G10L19/10

Method and a Decoder for Attenuation of Signal Regions Reconstructed with Low Accuracy
20170061977 · 2017-03-02 ·

The embodiments of the present invention improves conventional attenuation schemes by replacing constant attenuation with an adaptive attenuation scheme that allows more aggressive attenuation, without introducing audible change of signal frequency characteristics.

Method and a Decoder for Attenuation of Signal Regions Reconstructed with Low Accuracy
20170061977 · 2017-03-02 ·

The embodiments of the present invention improves conventional attenuation schemes by replacing constant attenuation with an adaptive attenuation scheme that allows more aggressive attenuation, without introducing audible change of signal frequency characteristics.

SYSTEMS AND METHODS FOR CONTINUOUSLY DETECTING AND IDENTIFYING SONGS IN A CONTINUOUS AUDIO STREAM
20170024441 · 2017-01-26 ·

A system and method for detecting songs in a continuous audio stream are disclosed. A detection server segments the continuous audio stream, and analyzes the audio stream to determine song candidates according to various processes disclosed herein. In one embodiment, the candidates are determined to be accurate when temporally ordered fingerprints exceed a predetermined threshold, adjacent audio stream segments are determined to have the same best song candidate, and the determined song detection has not been previously detected in the data stream within a predetermined period of time.