43 results about "Audio restoration" patented technology

An audio restoration apparatus is provided which restores an audio to be restored having a missing audio part and being included in a mixed audio. The audio restoration apparatus includes: a mixed audio separation unit which extracts the audio to be restored included in the mixed audio; an audio structure analysis unit which generates at least one of a phoneme sequence, a character sequence and a musical note sequence of the missing audio part; an unchanged audio characteristic domain analysis unit which segments the extracted audio to be restored into time domains in each of which an audio characteristic remains unchanged; an audio characteristic extraction unit which identifies a time domain where the missing audio part is located, and extracts audio characteristics of the identified time domain in the audio to be restored; and an audio restoration unit which restores the missing audio part in the audio to be restored.

The present invention is a small high fidelity full spectrum speaker, which arranges a passive speaker and two active speakers such that fidelity of a larger speaker or one with a cross-over network is achieved.

An audio reproduction device comprises an interruption information storage memory (202) for holding the frame information during the interruption of reproduction, a compressed stream control unit (203) for calculating and reading the position at which a compressed stream is read from a recording medium (201), a compressed stream decoding part (204) for decoding the compressed stream and transmitting decoding information on the frame to the compressed stream control unit (203) as resume additional information, and an output control unit (205) for outputting the results of the decoding. When the reproduction is once interrupted and resumed, the read position of the compressed stream is calculated and read from the resume additional information and the frame information during the interruption, thereby allowing the reproduction to be resumed with no section or no frequency band not reproduced in terms of time.

The invention relates to a training method for a speaker information extraction model. The method comprises the steps: enabling a voice synthesis system and a voice recognition system to be correlatedinto a training system through the speaker information extraction model; removing residual data information after text content information corresponding to voice data is extracted by the speaker information extraction model from an audio processing result to obtain a first high-dimensional vector, and obtaining a second high-dimensional vector output by a text processing network for processing the text data of a first data pair; training an audio processing network, the text processing network and the speaker information extraction model, and training convergence when a loss function reachesthe minimum value; combining the audio processing network and an audio recovery network into an audio processing network, and combining the text processing network and a text recovery network into a text processing network; and training the audio processing network and the speaker information extraction model until convergence to obtain a parameter set of the speaker information extraction model.The generalization ability of the speaker information extraction model is improved.

The invention relates to an ultrasonic coding and decoding system based on jitter sound wave signals. The system comprises a data processing module, a data buffer module, a network communication module, an address coding module, a clock module, a clock signal frequency division module, a digital-to-analogue conversion module, a data communication bus module, a drive module, a control unit, an audio frequency signal collection unit, a filter module and an audio frequency coding module. The data communication bus module is electrically connected with the data buffer module, the network communication module, the address coding module, the clock module, the clock signal frequency division module, the drive module, the filter module and the audio frequency coding module. The data buffer module is electrically connected with the data processing module and the audio frequency coding module. The drive module is electrically connected with the control unit and the audio frequency signal collection unit. According to the invention, the work efficiency and the accuracy of audio frequency signal coding can be effectively improved, and the efficiency of audio frequency decoding and the accuracy of audio restoration can be effectively improved.