Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

2results about How to "Improve speech intelligibility" patented technology

An audio enhancement system and method for an underground broadcasting system

ActiveCN122090815Areduce environmental noiseReduce the effects of reverberationSound producing devicesHigh level techniquesEnvironmental noiseNoise
This invention discloses an audio enhancement system and method for underground broadcasting systems, relating to the field of audio enhancement technology. The system acquires noise signals and original audio signals from a mine roadway, processes them through standardization, encodes and transmits them, and then decodes them to obtain a standardized noise signal. The standardized noise signal undergoes frequency band amplitude shaping and time delay compensation, followed by a phase inversion operation to generate a reverse noise signal. Based on the original audio signal and a roadway sound reflection model, the reverberation component within the roadway is predicted. After phase inversion, a reverse reverberation signal is generated, and a reverberation gating coefficient is introduced for weighted control to obtain the actual reverse reverberation signal. The original audio signal, the reverse noise signal, and the actual reverse reverberation signal are then superimposed to obtain the final audio signal. Utilizing the principle of destructive interference, the system effectively reduces the impact of environmental noise and reverberation.
Owner:SHANDONG UNIV OF SCI & TECH

Causal adaptive single-channel speech denoising method and apparatus

ActiveCN116758931BImprove voice qualityImprove speech intelligibilitySpeech analysisGeneralized eigenvalue decompositionNoise
This disclosure provides a causal adaptive single-channel speech denoising method and apparatus. The method includes: acquiring noise information in a first time period and noisy speech information in a second time period; processing the noise information and noisy speech information to obtain a noise correlation matrix and a speech correlation matrix; performing generalized eigenvalue decomposition on the noise correlation matrix and the speech correlation matrix to obtain multiple initial feature vectors; generating a target filter vector based on the multiple initial feature vectors and the filter function of the initial filter; and generating enhanced target output speech information based on the target filter vector and the noisy speech information.
Owner:UNIV OF SCI & TECH OF CHINA