Display apparatus and voice conversion method thereof
AssigneeSamsung Electronics Co., Ltd.
InventorsAditi Garg, Kasthuri Jayachand Yadlapalli
Life of this patent
Estimating the term…
Abstract
The voice conversion method of a display apparatus includes: in response to the receipt of a first video frame, detecting one or more entities from the first video frame; in response to the selection of one of the detected entities, storing the selected entity; in response to the selection of one of a plurality of previously-stored voice samples, storing the selected voice sample in connection with the selected entity; and in response to the receipt of a second video frame including the selected entity, changing a voice of the selected entity based on the selected voice sample and outputting the changed voice.
Claims20
A voice conversion method of a display apparatus, the voice conversion method comprising:
- in response to receipt of a first video frame, detecting, by the display apparatus, one or more entities from the first video frame;
- in response to a selection of one of the detected entities, storing, by the display apparatus, a selected entity;
- in response to a selection of one of a plurality of previously stored voice samples, storing, by the display apparatus, a selected voice sample in association with the selected entity in a storage unit;
- and
- in response to receipt of a second video frame including the selected entity, changing, by the display apparatus, a voice of the selected entity based on the selected voice sample and outputting the changed voice,
- wherein the detected entities comprise faces of characters included in the first video frame.
A display apparatus comprising:
- a detection unit which, in response to receipt of a first video frame, detects one or more entities from the first video frame;
- a user interface (UI) unit which receives a first selection regarding an entity to be a subject to voice conversion and a second selection regarding a voice sample to be applied to a selected entity;
- a storage which stores an entity, which is selected from the detected entities via the UI unit, and a voice sample, which is selected via the UI unit;
- and
- a control unit which, in response to receipt of a second video frame including the selected entity, changes a voice of the selected entity based on the selected voice sample and outputs the changed voice,
- wherein the detected entities comprise faces of characters included in the first video frame, and
- wherein at least one of the detection unit, the UI unit, and the control unit is implemented as a hardware processor.
A method comprising:
- receiving, by a display apparatus, a selection of a face of a character from a first piece of content;
- receiving, by the display apparatus, a selection of a replacement voice for the selected face of the character;
- associating, by the display apparatus, the selected face of the character with the replacement voice;
- subsequently, receiving, by the display apparatus, a second piece of content;
- identifying, by the display apparatus, the selected face of the character in the second piece of content;
- detecting, by the display apparatus, sounds uttered by the selected face of the character, in the second piece of content;
- altering, by the display apparatus, detected uttered sounds with characteristics of the replacement voice;
- and
- outputting, by the display apparatus, the second piece of content, in which the sounds uttered by the selected face of the character are altered with the characteristics of the replacement voice.
Dependencies are inferred from the claim text.