35results about How to "Reduce recording costs" patented technology

The embodiment of the invention discloses an acoustic model establishing method, an acoustic model establishing device, a speech synthesis method, a speech synthesis device, a facility and a storage medium. The acoustic model establishing method comprises the following steps: acquiring a phoneme sequence sample of a plurality of training samples from a corpus, and acquiring the context feature ofeach phoneme and the duration of each phoneme in the phoneme sequence sample, wherein the rhotic accent phoneme in the phoneme sequence sample is split to two phonemes; extracting acoustic features from the training samples; and by adopting the phoneme sequence sample, training the acoustic model by taking the context feature of each phoneme and the duration of each phoneme in the phoneme trainingsample as the input of the acoustic model and the acoustic features as the output of the acoustic model, so that the pretrained acoustic model is obtained. The modeling performance of the rhotic accent is good, the synthesis of the rhotic accent can be well realized, then the rhotic accent not appearing in the corpus can be synthesized, and meanwhile, the recording cost of linguistic data in thecorpus can be reduced.

A recording medium, including: an ink-receiving layer configured to receive an ink for inkjet recording; and a transparent sheet having a total luminous transmittance of 50% or more, wherein the recoding medium has a layered structure in which the transparent sheet and the ink-receiving layer are sequentially stacked, and the ink-receiving layer includes a gap-absorption-type ink-receiving layer including a composition including at least inorganic fine particles and polyvinyl alcohol having a weight-average polymerization degree of 2,000 or more and 5,000 or less and a saponification degree of 70 mol % or more and 90 mol % or less.

The invention relates to a field culturing position information storing and verifying method. The technical solution of the method is characterized in that a position information acquisition device based on blockchain automatically acquires position information and uploads the position information to cloud for storage, thereby realizing high convenience in use, low data recording cost, no requirement for third-party intervention, low cost, easy management, effective central attack resistance and no user information leakage; field cultured livestock is strictly bound with blockchain data so that field cultured livestock position information which is recorded has strict verifiability and no-tampering property; and for long-time use of a device, a solar-and-kinetic hybrid power generating mode is utilized, thereby realizing advantages of long-acting and environment-friendly performance. According to the method of the invention, related technology of blockchain realizes an online digital asset attribute of the cultured animals, thereby facilitating development of multiple novel business modes.

The invention discloses a program recording method and device. The program recording method is used for playing videos on a DVB video playing system and an OTT TV playing system simultaneously so as to reduce hardware cost. The program recording method includes: recording a program according to a preset recording time length according to a received IP multicast signal to generate a corresponding recorded file, wherein the recorded file includes a transport stream TS file; virtually segmenting the TS file into a plurality of TS clips according to a preset clip time length; and generating virtual clip files according to the positions of respective TS clips in the TS file.

A recording medium, including: an ink-receiving layer configured to receive an ink for inkjet recording; and a transparent sheet having a total luminous transmittance of 50% or more, wherein the recoding medium has a layered structure in which the transparent sheet and the ink-receiving layer are sequentially stacked, and the ink-receiving layer includes a gap-absorption-type ink-receiving layer including a composition including at least inorganic fine particles and polyvinyl alcohol having a weight-average polymerization degree of 2,000 or more and 5,000 or less and a saponification degree of 70 mol % or more and 90 mol % or less.

The invention discloses a voice synthesis method and device based on tone cloning and electronic equipment. The method comprises the steps: training a TTS basic model through an open source corpus; training the basic model through a target tone corpus in a fine tuning manner to obtain a fine tuning model; generating a variable voice of a target tone according to a variable corpus and the fine tuning model; and synthesizing a target tone voice according to the variable voice and the fixed voice. According to the method, the open source corpus is firstly adopted, and then the fine tuning model of the TTS network is trained through a small amount of target tone corpus in a fine tuning manner. Compared with exhaustive manual recording or a traditional TTS high-quality corpus synthesis mode, the method has the advantages that the recording time of the target timbre corpus can be effectively shortened, and the recording cost is greatly reduced.

The invention provides an information interaction method and a system of the method. The information interaction method includes the steps that a request sent by an interaction requester through a communication terminal is received; an information processing center builds a unique event identification for request information and extracts key information from the request; an information interaction channel, based on the unique event identification, of the requester communication terminal and a scheme resolution end is built; information interaction between the requester terminal and the scheme resolution end is achieved through the information interaction channel, and resolution information matched with the request is obtained; the information interaction channel of the unique event identification is closed after it is confirmed that the requester obtains information provided by the scheme resolution end. According to the method and the system of the method, information interaction generated through a conventional communication means and interaction in an enterprise are more convenient and natural by means of capacity of a mobile internet communication terminal through the unique interaction channel built between the conventional communication means and an IT management system in the enterprise with the event as a unit, and interaction efficiency is improved.

The present invention provides an audio playback control method and system, comprising: acquiring monophonic audio as the first audio; multiplying the sound intensity value of the first audio by the left position angle coefficient to calculate the first left audio output intensity value; multiply the sound intensity value of the first audio by the right position angle coefficient to calculate the first right audio output intensity value; put the first audio in the left audio output intensity value according to the first left audio output intensity value channel output, and output the first audio in the right channel according to the first right audio output intensity value. By using the above method, two-channel stereo output of single audio can be realized, which improves the user's audio-visual experience, and at the same time, it is not necessary to record the audio in two-channel format, which reduces the recording cost.

The embodiment of the present invention discloses an acoustic model establishment, speech synthesis method, device, equipment and storage medium, wherein the acoustic model establishment method comprises: obtaining phoneme sequence samples of a plurality of training samples from a corpus, and obtaining the phoneme sequence samples The context feature of each phoneme and the duration of each phoneme in the phoneme sequence sample; wherein, the childish phoneme in the phoneme sequence sample is split into two phonemes; Acoustic features are extracted from the training sample; with the phoneme sequence sample, The context feature and duration of each phoneme in the phoneme sequence sample are used as the input of the acoustic model, and the acoustic feature is used as the output of the acoustic model, and the acoustic model is trained to obtain a pre-trained acoustic model, which can make The modelling performance of Erhuayin is better, the synthesis of Erhuayin can be better realized, the Erhuayin that does not appear in the corpus can be synthesized, and the recording cost of the corpus in the corpus can be reduced.

The invention discloses a shower room glass storage bin automatic monitoring system. The shower room glass storage bin automatic monitoring system comprises an identification module, a sorting module,a storage monitoring module and a shipping module; each produced shower room glass is pasted with an identification two-dimensional code for recording information of the shower room glass; the identification module mainly performs identification and recording on the two-dimensional code of the shower room glass on the shower room glass, and transmits the identified information to the sorting module; the sorting module transports and sorts the shower room glass into the storage monitoring module according to the identified information after receiving the identified information of the identification module; the storage monitoring module is mainly used for classifying and storing different shower room glasses, recording the number of the shower room glasses, and sending to the shipping module; and the shipping module is mainly used for taking out the shower room glasses in the storage monitoring module for shipment.

The invention is applicable to the technical field of multimedia data processing, and provides a gain control system and method. The system comprises a microphone, an analog gain control unit, an analog-digital converter and a digital gain control unit, wherein the microphone is used for converting sound signals into analog voice signals; the analog gain control unit is connected with the microphone and is used for carrying out coarse tuning on the analog voice signals output by the microphone so as to perform first-stage gain control; the analog-digital converter is connected with the analog gain control unit and is used for converting analog voice signals output by the analog gain control unit into digital voice signals; and the digital gain control unit is connected with the analog-digital converter and the analog gain control unit and is used for carrying out energy measurement on the digital voice signals output by the analog-digital converter, thus dynamically adjusting digital gain factors according to energy measurement results and carry out second-stage gain control on the digital voice signals according to adjusted gain factors. According to the embodiment of the invention, automatic voice-recording gain control is realized through the combination of digital gain control and analog gain control, the voice recording cost is reduced and the voice recording quality is improved.

The invention relates to a field culturing position information storing and verifying method. The technical solution of the method is characterized in that a position information acquisition device based on blockchain automatically acquires position information and uploads the position information to cloud for storage, thereby realizing high convenience in use, low data recording cost, no requirement for third-party intervention, low cost, easy management, effective central attack resistance and no user information leakage; field cultured livestock is strictly bound with blockchain data so that field cultured livestock position information which is recorded has strict verifiability and no-tampering property; and for long-time use of a device, a solar-and-kinetic hybrid power generating mode is utilized, thereby realizing advantages of long-acting and environment-friendly performance. According to the method of the invention, related technology of blockchain realizes an online digital asset attribute of the cultured animals, thereby facilitating development of multiple novel business modes.

The invention relates to a video recording method and provides a video recording method based on vector coding and applied to a touch screen device. The video recording method based on vector coding and applied to the touch screen device comprises the following steps that a user opens software to start recording through a device terminal with a touch screen and a touch screen handwriting pen; the user writes on the screen; the user clicks a shooting button or clicks a picture leading-in button to lead a picture to the screen; the picture on the screen is selected and change such as movement is conducted; after a word button is input, a text input box is inserted in the position of a touch point, and words are input and encoded; when recording goes wrong or the user wants to correct the latest pen trace or picture operation is wrong, a software undoing button is clicked until the recorder thinks that recording is faultless or no content on the screen can be undone; after undoing, if the user wants to recover the latest undone object or redo the latest undone object, a redoing button can be clicked, and therefore the undone object can be displayed on the screen again; if the slips of the tongue occur or voice is wrong, a voice rollback button is clicked, and the voice goes back to a certain moment in last N seconds; when video recording is finished, a recording completion button on a recording interface is clicked.

The invention discloses a voice synthesis method and system. The method includes steps: obtaining a recorded voice correspondingly recorded by a speaker according to a specific text; extracting fundamental frequency information f01 from the recorded voice, performing analysis processing on the recorded voice, and obtaining phoneme duration information corresponding to the recorded voice; generating fundamental frequency information f00 and frequency spectrum information cep0 by employing a preset parameter synthesis model according to the specific text and the obtained phoneme duration information; performing domain adjustment on the fundamental frequency information f01 of the recorded voice by employing the fundamental frequency information f01 of the recorded voice and the fundamental frequency information f00 generated by the preset parameter synthesis model; and obtaining final fundamental frequency information. According to the method and system, the corresponding synthesized voice is obtained through reconstruction of a vocoder by employing the obtained final fundamental frequency information and the frequency spectrum information cep0, the beneficial effect of reducing thevoice recording cost is achieved, and the natural degree of the synthesized voice is further improved.

The invention discloses a speech synthesis method under a small amount of recording samples. The method comprises the following steps of A) obtaining a background speaker model by applying a small amount of training sentences recorded by target recording personnel; B) respectively establishing speaker models for the obtained current speaker sentence and the originally recorded complete speaker sentence through a self-adaptive algorithm; and C) realizing the speech synthesis by adjusting the mean and variance of the speaker models, and synthesizing a small amount of recorded audios into a complete recording sentence. The speech synthesis method under a small amount of recording samples disclosed by the invention has the advantages that an operation of repeatedly recording the same recordingtext by multiple customer service staff is avoided, the speed recording cost is reduced, and the fluency and the naturalness of the whole conversation process effect can be guaranteed.

Provided is a transfer material, including: a coloring material-receiving layer; and a base material sheet. The transfer material has a laminated structure in which the base material sheet and the coloring material-receiving layer are sequentially laminated, the coloring material-receiving layer contains at least inorganic fine particles, a water-soluble resin, and a cationic resin having a weight-average molecular weight of 15,000 or less, and a difference SP2 between a SP value of an image support onto which the transfer material is transferred and a SP value of the coloring material-receiving layer to be brought into abutment with the image support satisfies a relationship of 0≤SP2≤1.0.

The navigation generator 12 sets the time length of a VOB to a time length that is determined in advance depending on a scheduled recording time H. Even if a user makes an operation to stop the recording before the time length of a recorded part of the VOB equals the predetermined time length, the VOB of the predetermined time length is recorded onto a DVD±R. Cell information specifying the part of the VOB preceding the point corresponding to the recording stop is generated. Then, PGC information containing the Cell information is recorded onto the DVD±R.