Audio data processing method and device for hearing detection and storage medium

• Main Authors: HAN XUEQING, LIAO SHENGBIN
• Format: Patent
• Language: Chinese; English
• Published: 07.04.2023
• Subjects: ACOUSTICS; CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DIAGNOSIS; ELECTRIC DIGITAL DATA PROCESSING; HUMAN NECESSITIES; HYGIENE; IDENTIFICATION; MEDICAL OR VETERINARY SCIENCE; MUSICAL INSTRUMENTS; PHYSICS; SPEECH ANALYSIS OR SYNTHESIS; SPEECH OR AUDIO CODING OR DECODING; SPEECH OR VOICE PROCESSING; SPEECH RECOGNITION; SURGERY

The invention provides an audio data processing method for hearing detection, and the method comprises the steps: inputting the collected audio data of a hearing-impaired child into a hearing detection model, and obtaining the processed data. The hearing detection model is generated by acquiring an audio source comprising specified audio and processing the audio source to obtain an acoustic data set; extracting audio acoustic features from the acoustic data set; establishing a sample set according to the audio acoustic features and training an acoustic model; the hearing detection model is obtained by iteratively optimizing the acoustic model through the audio acoustic features, a machine learning algorithm is fully utilized, and many expensive devices do not need to be arranged. The invention further discloses audio data processing equipment for hearing detection and a storage medium, the audio data processing equipment can be a mobile terminal, is convenient to carry about, can be tested at any time, can be