Query by humming for ringtone search and download

• US 20080215319A1
• Filed: 03/01/2007
• Published: 09/04/2008
• Est. Priority Date: 03/01/2007
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Xie, Xing, Lu, Lie, Weng, Ruihao, Xie, Yutao, Ou, Jiafan
• Granted Patent: US 8,116,746 B2
• Time in Patent Office: Days
• US Class Current: 704/231
• CPC Class Codes: G06F 16/634 Query by example, e.g. query by humming
• CPC Class Codes: G06F 16/683 using metadata automatically derived from the content
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G10H 2210/056 for extraction or identification of individual instrumental parts, e.g. melody, chords, bass; Identification or separation of instrumental parts by their characteristic voices or timbres
• CPC Class Codes: G10H 2230/021 Mobile ringtone, i.e. generation, transmission, conversion or downloading of ringing tones or other sounds for mobile telephony; Special musical data formats or protocols therefor
• CPC Class Codes: H04M 19/04 the ringing-current being generated at the substations
• CPC Class Codes: H04M 3/02 Calling substations, e.g. by ringing selective calling H04Q
• CPC Class Codes: H04W 4/14 Short messaging services, e.g. short message services [SMS] or unstructured supplementary service data [USSD]
• CPC Class Codes: H04W 4/16 Communication-related supplementary services, e.g. call-transfer or call-hold
• CPC Class Codes: H04W 88/02 Terminal devices

Abstract

Described is a technology by which a user hums, sings or otherwise plays a user-provided rendition of a ringtone (or ringback tone) through a mobile telephone to a ringtone search service (e.g., a WAP, interactive voice response or SMS-based search platform). The service matches features of the user'"'"'s rendition against features of actual ringtones to determine one or more matching candidate ringtones for downloading. Features may include pitch contours (up or down), pitch intervals and durations of notes. Matching candidates may be ranked based on the determined similarity, possibly in conjunction with weighting criterion such as the popularity of the ringtone and/or the importance of the matched part. The candidate set may be augmented with other ringtones independent of the matching, such as the most popular ones downloaded by other users, ringtones from similar artists, and so forth.

Claims

1. In an environment in which ringtones are available for selection and downloading, a method comprising:

receiving user input over a communications medium in which the user input includes a user-provided rendition of a ringtone;

matching the user-provided rendition of the ringtone to actual ringtones to determine a selection set comprising at least one ringtone; and

providing the selection set in response to the user input.

2. The method of claim 1 further comprising, converting the use input to an audio file, and providing the audio file to a matching mechanism.

3. The method of claim 1 wherein matching the user-provided rendition of the ringtone to actual ringtones comprises processing data corresponding to the user-provided rendition of a ringtone into features, and matching the features with features of the actual ringtones.

4. The method of claim 3 wherein processing the data into features comprises, segmenting at least some of the data into notes, and determining characteristics of at least some of the notes.

5. The method of claim 4 wherein determining the characteristics of at least some of the notes comprises determining pitch contours, pitch intervals, or durations, or any combination thereof, for the characteristics.

6. The method of claim 5 wherein matching the user-provided rendition of the ringtone to actual ringtones comprises using the pitch contours, pitch intervals, or durations, or any of combination thereof, to align the features of the user-provided rendition of the ringtone with features of the actual ringtones.

7. The method of claim 1 wherein providing the selection set in response to the user input comprises returning a list of data corresponding to a plurality of candidate ringtones, and further comprising, receiving selection data corresponding to a user selection of a candidate ringtone, and downloading the candidate ringtone as a selected ringtone in response to the selection data.

8. The method of claim 1 wherein providing the selection set in response to the user input comprises returning a matched ringtone.

9. The method of claim 1 wherein providing the selection set in response to the user input comprises returning a list of data corresponding to a plurality of candidate ringtones, including by ranking data in the list based on similarity of each ringtone with respect to the user-provided rendition of the ringtone.

10. The method of claim 9 wherein ranking the data in the list further comprises, using at least one weighting criterion to rank the data.

11. The method of claim 1 wherein providing the selection set comprises adding at least one other recommended ringtone to the selection set independent of matching with the user-provided rendition of the ringtone.

12. The method of claim 1 wherein receiving the user input over the communications medium comprises receiving a telephone call, detecting a user coupling to a voice response server, or receiving user input via a website.

13. In an environment in which ringtones are available for selection and downloading, a system comprising:

a service that receives audio from a client corresponding to a user-provided rendition of a user-desired ringtone;

a processing component coupled to the service to process data corresponding to the audio into feature data;

a matching component coupled to the processing component to match the feature data against features of candidate ringtones to determine a similarity of the user-provided rendition of the ringtone to each of the candidate ringtones; and

the service returning a selection set corresponding to at least one ringtone determined by the matching component by the determined similarity to be similar to the user-provided rendition of the user-desired ringtone.

14. The system of claim 15 wherein the environment includes at least one search platform of a set, the set including a wireless application protocol (WAP)-based search platform, an interactive voice response-based search platform, or a simple message service (SMS)-based search platform, or any combination thereof.

15. The system of claim 13 wherein the service that receives audio from the client converts the audio to a file containing the data processed by the processing component.

16. The system of claim 13 wherein the processing component processes the data into the feature data, including by segmenting at least some of the data into notes, and determining a pitch contour, pitch interval, and duration for each of the notes.

17. The system of claim 13 wherein the service is part of a subscription-based model, a pay-per-download model, a pay-per-call model or an advertisement model, or any combination thereof.

18. A computer-readable medium having computer-executable instructions, comprising:

receiving a user-provided rendition of a ringtone;

processing audio data corresponding to the user-provided rendition of the ringtone into a feature set;

matching the feature set against feature data of each of a plurality of actual ringtones to determine a similarity between the user-provided rendition of the ringtone and each actual ringtone; and

providing a selection set based at least on part of the similarity between the user-provided rendition of the ringtone and at least one actual ringtone.

19. The computer-readable medium of claim 18 wherein processing the audio data comprises segmenting at least some of the audio data into notes, determining a pitch contours, pitch intervals and durations for the notes, and wherein matching the feature set against the feature data comprises using the pitch contours to align the feature set with corresponding feature data of each of the actual ringtones and using the pitch intervals and durations to determine the similarity with corresponding feature data of that actual ringtone.

20. The computer-readable medium of claim 18 wherein providing the selection set comprises ranking data corresponding to each ringtone based on one or more criterion, the criterion including similarity, popularity or importance of a matched part, or any combination of similarity, popularity or importance of a matched part.