37results about How to "Correct pronunciation" patented technology

The present invention relates to a method for assessing a learner's pronunciation through voices and images, in which variation of the teacher's and the learner's lips are compared in a visual manner. Accordingly, incorrect pronunciation can be pointed out and recorded for assessment and rectification.

The invention discloses a sounding interactive platform with a characteristic of synchronous sounding triggering playing and a synchronous sounding method thereof. The sounding interactive platform comprises a platform body, a sounding device, and a key device, wherein the sounding device and the key device are arranged on the platform body. The sounding device includes a power supply module, a loudspeaker, a voice chip, and an induction circuit board; and the input terminal of the loudspeaker is connected with the output terminal of the voice chip and the output terminal of the induction circuit board is connected with the input terminal of the voice chip. N kinds of sound sources are stored into the voice chip in advance; and N induction regions that correspond to the N kinds of sound sources one by one and trigger the voice chip to output corresponding sound sources to the loudspeaker for playing are arranged on the induction circuit board. Besides, the key device contains N keys that correspond to the N induction regions one by one and trigger the corresponding induction regions to make responses. According to the invention, a puzzle with a specific pattern is used as a switch connecting point; and the platform can make different sounds by using the puzzle in a combination mode by the user, thereby enhancing the interestingness and interactivity.

The invention discloses an access control verification method and an access control verification system. The access control verification method includes steps of receiving verification instructions, transmitting verification voiceprint segment acquisition requesting instructions to a cloud server according to the verification instructions; receiving verification voiceprint segments fed by the cloud server; playing the verification voiceprint segments. The verification voiceprint segment acquisition requesting instructions contain identification information. The verification voiceprint segments are generated by the cloud server according to set rules and registration information which is stored in the cloud server and corresponds to the identification information, and include verification requesting voiceprint segments, unlocking permission voiceprint segments, verification key voiceprint segments and completion voiceprint segments. According to the scheme, the access control verification method and the access control verification system have the advantages that access control verification can be carried out by the aid of the verification voiceprint segments, and accordingly the access control verification method and the access control verification system are convenient to use, high in safety and low in cost.

The invention discloses an English pronunciation matching correction system. The system comprises a standard pronunciation acquisition module, a test pronunciation acquisition module, an information storage module, a comparison processing module, an information export module, an information display module and a sound module, wherein the output end of the standard pronunciation acquisition module is in signal connection with the input end of the information storage module; the output end of the test pronunciation acquisition module is in signal connection with the input end of the information storage module; the output end of the information storage module is in signal connection with the input end of the comparison processing module; the output end of the comparison processing module is insignal connection with the input end of the information export module; the output end of the information export module is in signal connection with the input end of the information display module andthe input end of the sound module. The English pronunciation matching correction system can be used for detecting pronunciation conditions of students from multiple aspects, so that mastering conditions of the students in various aspects can be conveniently and clearly observed, and later-stage key enhancement of correction and extra tutoring can be facilitated.

The invention discloses a speech synthesis method, electronic equipment and a smart home system. The method comprises: obtaining user voice demand data; obtaining user intentions and extracting quasi-intent labels; The tag determines the target intent tag, and queries the speech set associated with the target intent tag from the knowledge graph, determines the speech associated with each text based on the speech collection, and synthesizes the text with the determined speech. The electronic device implements the method through a speech recognition server, a semantic understanding server, a knowledge map server and a speech synthesis terminal, and the smart home system includes one or more of the electronic devices. According to the present invention, through the tags and language sets stored in the knowledge map, after each character associated with the user's intention is obtained, the voice associated with each character can be determined based on the voice set, and the text and the determined voice can be synthesized into pronunciation Voice with high accuracy.

The invention discloses a method, device, electronic equipment and storage medium for generating and displaying lyrics, and belongs to the technical field of the Internet. The method includes: obtaining the lyrics of the target song and the audio file of the target song; determining the candidate pronunciation of the character to be marked according to the characters to be marked in the multiple characters in the lyrics and the audio clips corresponding to the multiple characters in the audio file; When the marked character has a candidate pronunciation, then the candidate pronunciation is determined to be the corresponding pronunciation of the character to be marked in the target song; if the character to be marked has at least two candidate pronunciations, then the semantically matched The candidate pronunciation is determined to be the corresponding pronunciation of the character to be marked in the target song; according to the corresponding pronunciation of a plurality of characters and the character to be marked in the target song, the first lyrics file of the target song is generated, so that when the lyrics are displayed later, you can The pronunciation is displayed synchronously to ensure that the user can correctly sing the pronunciation of each character.