Voiceprint recognition method and apparatus
The present disclosure provides a voiceprint recognition method and apparatus, comprising: according to an obtained command speech, recognizing, in a voiceprint recognition manner, a user class sending a command speech; according to the user class, using a corresponding speech recognition model to perform speech recognition for the command speech, to obtain a command described by the command speech; providing resources according to the user class and command. The present disclosure can avoid the problems that in a conventional voiceprint recognition method in the prior art, a client needs to participate in voiceprint recognition, and the user's ID needs to be further recognized through a voiceprint training process, and that the user's degree of satisfaction is not high. While the user speaks naturally, it is feasible to perform processing for these very “ordinary” speech, and meanwhile complete the work of voiceprint recognition.
1. A voiceprint recognition method, wherein the method comprises:
pre-establishing a user interest model, comprising:
obtaining a user history log, where the user history log includes at least: a user identifier, user attribute information, and user historical behavior data; and
classifying the user historical behavior data according to a user category and a vertical class to obtain the user interest model;
performing model training according to speech features of different user classes, and building voiceprint processing models of different user classes;
according to an obtained command speech, recognizing, in a voiceprint recognition manner, a user class sending a command speech;
collecting language materials having colloquial features of different user classes to form a corpus, using the corpus to train a speech recognition model, and obtaining a speech recognition model of the corresponding user class;
according to the user class, using the speech recognition model to perform speech recognition for the command speech, to obtain a command described by the command speech;
determining a current vertical class, according to the command;
according to the user class and the current vertical class, using the pre-built user interest model to obtain a recommended interest class associated with the user class and current vertical class;
searching, from a multimedia resource library, for a target resource matched with the recommended interest class, and presenting the target resource to the user.
2. The voiceprint recognition method according to claim 1 , wherein, the user class comprises the user's sex and user's age group.
3. A device, wherein the device comprises:
one or more processors;
a storage for storing one or more programs,
said one or more programs, when executed by said one or more processors, enable said one or more processors to implement a voiceprint recognition method, wherein the method comprises:
pre-establishing a user interest model, comprising:
obtaining a user history log, where the user history log includes at least: a user identifier, user attribute information, and user historical behavior data; and
classifying the user historical behavior data according to a user category and a vertical class to obtain the user interest model;
performing model training according to speech features of different user classes, and building voiceprint processing models of different user classes;
according to an obtained command speech, recognizing, in a voiceprint recognition manner, a user class sending a command speech;
collecting language materials having colloquial features of different user classes to form a corpus, using the corpus to train a speech recognition model, and obtaining a speech recognition model of the corresponding user class;
according to the user class, using the speech recognition model to perform speech recognition for the command speech, to obtain a command described by the command speech;
determining a current vertical class, according to the command;
according to the user class and the current vertical class, using the pre-built user interest model to obtain a recommended interest class associated with the user class and current vertical class;
searching, from a multimedia resource library, for a target resource matched with the recommended interest class, and presenting the target resource to the user.
4. The device according to claim 3 , wherein,
the user class comprises the user's sex and user's age group.
5. A computer readable storage medium on which a computer program is stored, wherein the program, when executed by a processor, implements a voiceprint recognition method, wherein the method comprises:
pre-establishing a user interest model, comprising:
obtaining a user history log, where the user history log includes at least: a user identifier, user attribute information, and user historical behavior data; and
classifying the user historical behavior data according to a user category and a vertical class to obtain the user interest model;
performing model training according to speech features of different user classes, and building voiceprint processing models of different user classes;
according to an obtained command speech, recognizing, in a voiceprint recognition manner, a user class sending a command speech;
collecting language materials having colloquial features of different user classes to form a corpus, using the corpus to train a speech recognition model, and obtaining a speech recognition model of the corresponding user class;
according to the user class, using the speech recognition model to perform speech recognition for the command speech, to obtain a command described by the command speech;
determining a current vertical class, according to the command;
according to the user class and the current vertical class, using the pre-built user interest model to obtain a recommended interest class associated with the user class and current vertical class;
searching, from a multimedia resource library, for a target resource matched with the recommended interest class, and presenting the target resource to the user.
6. The computer readable storage medium according to claim 5 , wherein,
the user class comprises the user's sex and user's age group.