Specific person speech recognition (Speaker-Dependent) This article refers to the address: http:// The standard template or model of speech recognition is only adapted to a person. In fact, the template or model is created by the person by inputting the voice of each word, word or phrase in the vocabulary. When others use it, they need to create their own standard templates or models. Non-specific person speech recognition (Speaker-Independent) The standard template or model of speech recognition is adapted to a specified category of speakers (eg, standard Mandarin), and the standard template or model is generated by training by multiple people in the category. It is used by the speaker (inner) who can participate in the training when identifying, and can also be used by the speaker (outside circle) in the same category who is not participating in the training. ALLIN , https://www.displayapio.com
April 06, 2024