Speech keyword recognition method and apparatus, computer-readable storage medium, and computer device

A speech keyword recognition apparatus, comprising:

• a memory and a processor configured to:
• obtain first speech segments based on a to-be-recognized speech signal;
• obtain first probabilities respectively corresponding to the first speech segments by using a preset first classification model, a first probability of a first speech segment being obtained based on probabilities of the first speech segment respectively corresponding to pre-determined word segmentation units of a pre-determined keyword;
• obtain second speech segments based on the to-be-recognized speech signal, and respectively generate first prediction characteristics of the second speech segments based on first probabilities of first speech segments that correspond to each second speech segment;
• perform classification based on the first prediction characteristics by using a preset second classification model, to obtain second probabilities respectively corresponding to the second speech segments, a second probability of a second speech segment comprising at least one of a probability of the second speech segment corresponding to the pre-determined keyword or a probability of the second speech segment not corresponding to the pre-determined keyword;
• and
• determine, based on the second probabilities, whether the pre-determined keyword exists in the to-be-recognized speech signal.

A non-transitory computer-readable storage medium, storing a computer program, the computer program, when executed by a processor, causing the processor to perform:

• obtaining first speech segments based on a to-be-recognized speech signal;
• obtaining first probabilities respectively corresponding to the first speech segments by using a preset first classification model, a first probability of a first speech segment being obtained based on probabilities of the first speech segment respectively corresponding to pre-determined word segmentation units of a pre-determined keyword;
• obtaining second speech segments based on the to-be-recognized speech signal, and respectively generating first prediction characteristics of the second speech segments based on first probabilities of first speech segments that correspond to each second speech segment;
• performing classification based on the first prediction characteristics by using a preset second classification model, to obtain second probabilities respectively corresponding to the second speech segments, a second probability of a second speech segment comprising at least one of a probability of the second speech segment corresponding to the pre-determined keyword or a probability of the second speech segment not corresponding to the pre-determined keyword;
• and
• determining, based on the second probabilities, whether the pre-determined keyword exists in the to-be-recognized speech signal.