Multiple voice recognition model switching method and apparatus, and storage medium

1. A method for switching multiple speech recognition models, the method comprising:

acquiring at least one piece of speech information in user input speech;

recognizing the speech information and matching a linguistic category for the speech information to determine a corresponding target linguistic category based on a matching degree; and

switching a currently used speech recognition model to a speech recognition model corresponding to the target linguistic category,

wherein the recognizing the speech information and matching a linguistic category for the speech information to determine a corresponding target linguistic category based on a matching degree comprises:

recognizing at least two pieces of speech sentences included in the speech information to obtain a matching degree between each speech sentence and a linguistic category; and

determining an initial linguistic category based on the matching degree, and calculating a product of probabilities of the speech sentences not belonging to the initial linguistic category, and determining the corresponding target linguistic category based on the product.

2. The method according to claim 1 , wherein the recognizing the speech information and matching a linguistic category for the speech information to determine a corresponding target linguistic category based on a matching degree comprises:

recognizing the speech information based on features of at least two linguistic categories to obtain a similarity between the speech information and each of the linguistic categories, and defining the similarity as the matching degree of the linguistic category.

3. The method according to claim 1 , wherein before the recognizing the speech information and matching a linguistic category for the speech information to determine a corresponding target linguistic category based on a matching degree, the method further comprises:

performing any one of following preprocessing on the speech information: a speech feature extraction, an effective speech detection, a speech vector representation, and a model scoring test.

4. The method according to claim 1 , further comprising:

recognizing the speech information, and displaying a prompt message to prompt a user to perform manual switching if a recognition result does not meet a preset condition.

5. The method according to claim 1 , wherein the recognizing the speech information and matching a linguistic category for the speech information to determine a corresponding target linguistic category based on a matching degree comprises:

recognizing the speech information and matching a linguistic category for the speech information;

determining at least two candidate linguistic categories having matching degrees meeting a preset condition;

querying a user historical speech recognition record to determine a linguistic category used by the user historically; and

selecting a linguistic category consistent with the linguistic category used by the user historically from the at least two candidate linguistic categories as the target linguistic category.

6. An apparatus for switching multiple speech recognition models, the apparatus comprising:

at least one processor; and

a memory storing instructions, the instructions when executed by the at least one processor, cause the at least one processor to perform operations, the operations comprising:

acquiring at least one piece of speech information in user input speech;

recognizing the speech information and matching a linguistic category for the speech information to determine a corresponding target linguistic category based on a matching degree; and

switching, a currently used speech recognition model to a speech recognition model corresponding to the target linguistic category,

wherein the recognizing the speech information and matching a linguistic category for the speech information to determine a corresponding target linguistic category based on a matching degree comprises:

recognizing at least two pieces of speech sentences included in the speech information to obtain a matching degree between each speech sentence and a linguistic category; and

determining an initial linguistic category based on the matching degree, and calculating a product of probabilities of the speech sentences not belonging to the initial linguistic category, and determining the corresponding target linguistic category based on the product.

7. The apparatus according to claim 6 , wherein the recognizing the speech information and matching a linguistic category for the speech information to determine a corresponding target linguistic category based on a matching degree comprises:

recognizing the speech information based on features of at least two linguistic categories to obtain a similarity between the speech information and each of the linguistic categories, and defining the similarity as the matching degree of the linguistic category.

8. The apparatus according to claim 6 , the operations further comprising:

performing any one of following preprocessing on the speech information: a speech feature extraction, an effective speech detection, a speech vector representation, and a model scoring test.

9. The apparatus according to claim 6 , the operations further comprising:

recognizing the speech information, and displaying a prompt message to prompt a user to perform manual switching if a recognition result does not meet a preset condition.

10. The apparatus according to claim 6 , wherein the recognizing the speech information and matching a linguistic category for the speech information to determine a corresponding target linguistic category based on a matching degree comprises:

recognizing the speech information and match a linguistic category for the speech information;

determining at least two candidate linguistic categories having matching degrees meeting a preset condition;

querying a user historical speech recognition record to determine a linguistic category used by the user historically; and

selecting a linguistic category consistent with the linguistic category used by the user historically from the at least two candidate linguistic categories as the target linguistic category.

11. A non-transitory computer storage medium storing a computer program, the computer program when executed by one or more processors, causes the one or more processors to perform operations, the operations comprising:

acquiring at least one piece of speech information in user input speech;

recognizing the speech information and matching a linguistic category for the speech information to determine a corresponding target linguistic category based on a matching degree; and

switching a currently used speech recognition model to a speech recognition model corresponding to the target linguistic category,

wherein the recognizing the speech information and matching a linguistic category for the speech information to determine a corresponding target linguistic category based on a matching degree comprises:

recognizing at least two pieces of speech sentences included in the speech information to obtain a matching degree between each speech sentence and a linguistic category; and

determining an initial linguistic category based on the matching degree, and calculating a product of probabilities of the speech sentences not belonging to the initial linguistic category, and determining the corresponding target linguistic category based on the product.