Semi-automatic generation of multimedia content

1. A method for multimedia content generation, comprising:

receiving a textual input;

before receiving an audio narration of the textual input, estimating occurrence times of respective components of the audio narration;

automatically retrieving from one or more media databases a plurality of media items that are relevant to the textual input;

receiving user input, which selects one or more of the automatically-retrieved media items and correlates one or more of the selected media items in time with the textual input; and

automatically constructing a video clip, which comprises the audio narration and the selected media items scheduled in accordance with the user input, by scheduling the selected media items in accordance with the estimated occurrence times.

2. The method according to claim 1 , wherein retrieving the media items comprises automatically deriving one or more search queries from the textual input, and querying the media databases with the search queries.

3. The method according to claim 1 , wherein retrieving the media items comprises assigning ranks to the retrieved media items in accordance with relevance to the textual input, filtering the media items based on the ranks, and presenting the filtered media items to a human moderator for producing the user input.

4. The method according to claim 1 , wherein receiving the user input comprises receiving from a human moderator an instruction to synchronize a selected media item with a component of the textual input, and wherein automatically constructing the video clip comprises synchronizing the selected media item with a narration of the component in the audio narration.

5. The method according to claim 1 , wherein receiving the user input is performed before receiving the audio narration.

6. The method according to claim 1 , wherein automatically constructing the video clip comprises defining multiple scheduling permutations of the selected media items, assigning respective scores to the scheduling permutations, and scheduling the selected media items in the video clip in accordance with a scheduling permutation having a best score.

7. A method for multimedia content generation, comprising:

receiving a textual input;

automatically retrieving from one or more media databases a plurality of media items that are relevant to the textual input;

receiving user input, which selects one or more of the automatically-retrieved media items and correlates one or more of the selected media items in time with the textual input; and

automatically constructing a video clip, which comprises an audio narration of the textual input and the selected media items scheduled in accordance with the user input, including dividing a timeline of the video clip into two or more segments and scheduling the selected media items separately in each of the segments,

wherein dividing the timeline comprises scheduling a video media asset whose audio is selected to appear as foreground audio in the video clip, configuring a first segment to end at a start time of the video media asset, and configuring a second segment to begin at an end time of the video media asset.

8. The method according to claim 1 , wherein automatically constructing the video clip comprises training a scheduling model using a supervised learning process, and scheduling the selected media items in accordance with the trained model.

9. Apparatus for multimedia content generation, comprising:

an interface for communicating over a communication network; and

a processor, which is configured to receive a textual input, to estimate, before receiving an audio narration of the textual input, occurrence times of respective components of the audio narration, to automatically retrieve, from one or more media databases over the communication network, a plurality of media items that are relevant to the textual input, to receive user input, which selects one or more of the automatically-retrieved media items and correlates one or more of the selected media items in time with the textual input, to receive an audio narration of the textual input, and to automatically construct a video clip, which comprises the audio narration and the selected media items scheduled in accordance with the user input, by scheduling the selected media items in accordance with the estimated occurrence times.

10. The apparatus according to claim 9 , wherein the processor is configured to automatically derive one or more search queries from the textual input, and to retrieve the media items by querying the media databases with the search queries.

11. The apparatus according to claim 9 , wherein the processor is configured to assign ranks to the retrieved media items in accordance with relevance to the textual input, to filter the media items based on the ranks, and to present the filtered media items to a human moderator for producing the user input.

12. The apparatus according to claim 9 , wherein the processor is configured to receive from a human moderator an instruction to synchronize a selected media item with a component of the textual input, and to automatically construct the video clip by synchronizing the selected media item with a narration of the component in the audio narration.

13. The apparatus according to claim 9 , wherein the processor is configured to receive the user input before receiving the audio narration.

14. The apparatus according to claim 9 , wherein the processor is configured to define multiple scheduling permutations of the selected media items, to assign respective scores to the scheduling permutations, and to schedule the selected media items in the video clip in accordance with a scheduling permutation having a best score.

15. The apparatus according to claim 9 , wherein the processor is configured to train a scheduling model using a supervised learning process, and to schedule the selected media items in accordance with the trained model.

16. Apparatus for multimedia content generation, comprising:

an interface for communicating over a communication network; and

a processor, which is configured to receive a textual input, to automatically retrieve, from one or more media databases over the communication network, a plurality of media items that are relevant to the textual input, to receive user input, which selects one or more of the automatically-retrieved media items and correlates one or more of the selected media items in time with the textual input, to receive an audio narration of the textual input, and to automatically construct a video clip, which comprises an audio narration of the textual input and the selected media items scheduled in accordance with the user input, including dividing a timeline of the video clip into two or more segments and scheduling the selected media items separately in each of the segments,

wherein the processor is configured to schedule a video media asset whose audio is selected to appear as foreground audio in the video clip, to configure a first segment to end at a start time of the video media asset, and to configure a second segment to begin at an end time of the video media asset.