Evaluation of media content in media files

• US 5,983,176 A
• Filed: 04/30/1997
• Issued: 11/09/1999
• Est. Priority Date: 05/24/1996
• Status: Expired due to Term

• Current Assignee: The Procter & Gamble Company
• Original Assignee: Magnifi, Inc. (Emmperative Marketing, Inc.)
• Inventors: Degen, Leo, Cremin, Karl, Hoffert, Eric M.
• Primary Examiner(s): Dorvil, Richemond
• Assistant Examiner(s): SAX, ROBERT L
• Application Number:
  US08/848,357
• Time in Patent Office: 923 Days
• Field of Search: 704/233, 704/231, 704/236
• US Class Current: 704/233
• CPC Class Codes: G06F 16/638 Presentation of query results
• CPC Class Codes: G06F 16/683 using metadata automatically derived from the content
• CPC Class Codes: G06F 16/685 using automatically derived transcript of audio data, e.g. lyrics speech recognition G10L15/00
• CPC Class Codes: G06F 16/78 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G06F 16/7834 using audio features
• CPC Class Codes: G06F 16/7844 using original textual content or text extracted from visual content or transcript of audio data
• CPC Class Codes: G06F 16/785 using colour or luminescence
• CPC Class Codes: G06F 16/786 using motion, e.g. object motion or camera motion
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 16/953 Querying, e.g. by the use of web search engines
• CPC Class Codes: G10H 1/0058 Transmission between separate instruments or between individual components of a musical system G10H1/0083 takes precedence
• CPC Class Codes: G10H 2210/046 for differentiation between music and non-music signals, based on the identification of musical parameters, e.g. based on tempo detection
• CPC Class Codes: G10H 2240/056 MIDI or other note-oriented file format
• CPC Class Codes: G10H 2240/066 MPEG audio-visual compression file formats, e.g. MPEG-4 for coding of audio-visual objects MP3 G10H2240/061
• CPC Class Codes: G10H 2240/135 Library retrieval index, i.e. using an indexing scheme to efficiently retrieve a music piece
• CPC Class Codes: G10H 2240/305 Internet or TCP/IP protocol use for any electrophonic musical instrument data or musical parameter transmission purposes

Abstract

A method and apparatus for searching for multimedia files in a distributed database and for displaying results of the search based on the context and content of the multimedia files.

Claims

1. A method of determining if an audio file comprises music or speech comprising the steps:

examining time slices of said audio file to determine amplitude changes with time during each time slice;

classifying said audio file as music or speech based on said amplitude changes.

2. The method as recited by claim 1 wherein said step of examining time slices comprise computing normalized amplitude deviation values for each time slice.

3. The method as recited by claim 2 wherein said step of examining time slices further comprises averaging the normalized amplitude deviation values for all time slices to compute a music-speech metric.

4. The method as recited by claim 2 wherein said step of computing a normalized deviation value comprises computing maximum amplitude for all time slices, computing a deviation from the maximum amplitude for a particular time slice and normalizing the deviation value.

5. A method of analyzing audio file content comprising:

a) dividing said audio file into time segments of a predetermined size;

b) computing values of normalized amplitude deviation with time during each time segment;

c) averaging the normalized amplitude deviation values to compute a music speech metric; and

d) assessing whether the audio file represents music or speech based on the music-speech metric value.

6. The method as recited by claim 5 wherein said step of computing a normalized deviation value comprises computing an average maximum amplitude for each time slice, computing a deviation from the average maximum amplitude for a particular time slice and normalizing the deviation value.

7. The method as recited by claim 5 wherein the step of normalizing the deviation value comprises:

a) computing a value MAX-DEV as the absolute value of the difference between the maximum amplitude of a time slice and the average maximum amplitude for all time;

b) normalizing MAX-DEV over a reference value range by computing a value NORMALIZED-MAX-DEV=MAX-DEV*(REF-VAL/MAX) where REF-VAL is the maximum reference value in the range and MAX is the maximum amplitude for all time slices.

8. A method of assessing the volume of an audio file comprising the steps of:

a) dividing said audio file into time slices;

b) computing the average amplitude AVG-AMPLITUDE for each time slice;

c) computing the average of the AVG-AMPLITUDE to provide a metric;

d) assessing a volume level based on said metric.

9. The method as recited by claim 8 wherein said value AVG-AMPLITUDE is computed by summing amplitude values in each time slice and dividing.

10. A method of analyzing content of an audio file comprising the steps of:

a) assessing whether said audio file represents music or speech by examining slices of said audio file to determine amplitude changes with time during the time slice and classifying said audio file as music or speech based on said amplitude changes;

b) assessing a volume level of said audio file.

11. The method as recited by claim 10 wherein said step of examining time slices comprise computing normalized amplitude deviation values for each time slice.

12. The method as recited by claim 11 wherein said step of examining time slices further comprises averaging the normalized amplitude deviation values for all time slices to compute a music-speech metric.

13. The method as recited by claim 11 wherein said step of computing a normalized deviation value comprises computing an average maximum amplitude for each time slice, computing a deviation from the average maximum amplitude for a particular time slice and normalizing the deviation value.

14. The method of claim 10 wherein said step assessing the volume of an audio file further comprises the steps of:

a) dividing said audio file into time slices;

b) computing the average amplitude AVG-AMPLITUDE for each time slice;

c) computing the average of the AVG-AMPLITUDES to provide a metric;

d) assessing a volume level based on said metric.

15. The method as recited by claim 14 wherein said value AVG-AMPLITUDE is computed by summing amplitude values in each time slice and dividing.