http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-108831437-B
Outgoing Links
Predicate | Object |
---|---|
classificationCPCAdditional | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G10H2250-455 |
classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G10L13-02 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G10H7-00 |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G10L13-02 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G10H7-00 |
filingDate | 2018-06-15-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
grantDate | 2020-09-01-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationDate | 2020-09-01-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | CN-108831437-B |
titleOfInvention | Singing voice generation method, singing voice generation device, terminal and storage medium |
abstract | The embodiment of the invention discloses a singing voice generation method, a singing voice generation device, a terminal and a storage medium, wherein the singing voice generation method comprises the following steps: acquiring a voice signal corresponding to a song input by a user; acquiring standard acoustic feature information corresponding to the song from a pre-established acoustic feature template, and updating the acoustic feature information of the voice signal according to the standard acoustic feature information; wherein, the acoustic characteristic template stores standard acoustic characteristic information of at least one song; and storing or outputting the voice signal with the updated acoustic characteristic information as a target voice signal. The embodiment of the invention overcomes the problems that the conversion from voice to singing voice is realized by utilizing a large amount of data to train the acoustic model in the prior art, and the finally formed singing voice does not contain the voice of the user, so that the participation degree and the experience degree of the user are not high, and the effect of converting the voice of the user into the singing voice which keeps the voice of the user without training the acoustic model is realized. |
priorityDate | 2018-06-15-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
Predicate | Subject |
---|---|
isDiscussedBy | http://rdf.ncbi.nlm.nih.gov/pubchem/compound/CID73675 http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID419510426 |
Total number of triples: 15.