Abstract:
This application discloses an artificial intelligence-based (AI-based) wakeup word detection method performed by a computing device. The method includes: constructing, by using a preset pronunciation dictionary, at least one syllable combination sequence for self-defined wakeup word text inputted by a user; obtaining to-be-recognized speech data, and extracting speech features of speech frames in the speech data; inputting the speech features into a pre-constructed deep neural network (DNN) model, to output posterior probability vectors of the speech features corresponding to syllable identifiers; determine a target probability vector from the posterior probability vectors according to the syllable combination sequence; and calculate a confidence according to the target probability vector, and determine that the speech frames include the wakeup word text when the confidence is greater than or equal to a threshold.
Abstract:
A method for detecting a keyword, applied to a terminal, includes: extracting a speech eigenvector of a speech signal; obtaining, according to the speech eigenvector, a posterior probability of each target character being a key character in any keyword in an acquisition time period of the speech signal; obtaining confidences of at least two target character combinations according to the posterior probability of each target character; and determining that the speech signal includes the keyword upon determining that all the confidences of the at least two target character combinations meet a preset condition. The target character is a character in the speech signal whose pronunciation matches a pronunciation of the key character. Each target character combination includes at least one target character, and a confidence of a target character combination represents a probability of the target character combination being the keyword or a part of the keyword.
Abstract:
It is described a bad disk block self-detection method, including: each mounted chunk is partitioned into n sub-chunks, all sub-chunks having a same size, where n is an integer not less than 2; checking information is set at a fixed location of each sub-chunk, data is stored onto locations of each sub-chunk other than the fixed location, where the checking information is parity checking information for the data; and when the data is read or written, data verification is performed based on the checking information set at the fixed location of the read sub-chunk. It is also described a bad disk block self-detection apparatus and a computer storage medium. With the described above, the bad block on the disk can be detected rapidly, and it is able to instruct data migration and disk replacement.
Abstract:
The present disclosure discloses a biological feature recognition method performed at a biological feature recognition apparatus. After obtaining a facial image of a user and current heart rate data of the user, the apparatus determines, according to the facial image, current facial color data of the user and a correspondence between facial color data and heart rate data of the user and then determines, according to the correspondence between the facial color data and the heart rate data of the user, whether the current facial color data matches the current heart rate data. If the current facial color data matches the current heart rate data, the apparatus determines that recognition succeeds, thereby effectively avoiding a loophole of biological recognition in application.
Abstract:
The present invention discloses a content distribution method, system and a server. In one embodiment, the method includes: receiving a content distribution request form a client; obtaining all receiving ends designated by the content distribution request, and marking at least a portion of the receiving ends with a first status code; judging whether all the at least a portion of the receiving ends complete the distribution task, if not, controlling an internal distribution process until all the at least a portion of the receiving ends complete the distribution task.
Abstract:
A method for recovering hard disk data, a server and a distributed storage system relate to a computer technology. In the method, a data recovery request is received. The request includes at least one ID of sectors whose data is to be recovered. Based on the at least one ID of the sectors whose data is to be recovered, at least one sector whose data is to be recovered is located. Obtain at least one standby sector ID and a file backup corresponding to the at least one ID of the sectors whose data is to be recovered, and locate at least one standby sector based on the at least one standby sector ID. Write, into the at least one standby sector, data that is in the file backup and the same as the data stored in the at least one sector whose data is to be recovered.
Abstract:
Automatic trading of virtual characters in online applications comprises publishing virtual characters by a first user in a trading system that involves verification at an application server and locking of the selected virtual characters at the application server. This can ensure that the trading of virtual characters is true, reliable and prompt, and reduces the loss to users arising from the trading of virtual characters.
Abstract:
This application discloses an artificial intelligence-based (AI-based) wakeup word detection method performed by a computing device. The method includes: constructing, by using a preset pronunciation dictionary, at least one syllable combination sequence for self-defined wakeup word text inputted by a user; obtaining to-be-recognized speech data, and extracting speech features of speech frames in the speech data; inputting the speech features into a pre-constructed deep neural network (DNN) model, to output posterior probability vectors of the speech features corresponding to syllable identifiers; determine a target probability vector from the posterior probability vectors according to the syllable combination sequence; and calculate a confidence according to the target probability vector, and determine that the speech frames include the wakeup word text when the confidence is greater than or equal to a threshold.
Abstract:
A mixed speech recognition method, a mixed speech recognition apparatus, and a computer-readable storage medium are provided. The mixed speech recognition method includes: monitoring an input of speech input and detecting an enrollment speech and a mixed speech; acquiring speech features of a target speaker based on the enrollment speech; and determining speech belonging to the target speaker in the mixed speech based on the speech features of the target speaker. The enrollment speech includes preset speech information, and the mixed speech is non-enrollment speech inputted after the enrollment speech.
Abstract:
A neural network training method is provided. The method includes obtaining an audio data stream, performing, for different audio data of each time frame in the audio data stream, feature extraction in each layer of a neural network, to obtain a depth feature outputted by a corresponding time frame, fusing, for a given label in labeling data, an inter-class confusion measurement index and an intra-class distance penalty value relative to the given label in a set loss function for the audio data stream through the depth feature, and updating a parameter in the neural network by using a loss function value obtained through fusion.