Aural similarity measuring system for text

• US 8,346,548 B2
• Filed: 03/05/2008
• Issued: 01/01/2013
• Est. Priority Date: 03/12/2007
• Status: Active Grant

• Current Assignee: Mongoose Pictures Limited
• Original Assignee: Mongoose Pictures Limited
• Inventors: Owen, Mark
• Primary Examiner(s): COLUCCI, MICHAEL C
• Application Number:
  US12/042,690
• Publication Number:
  US 20080228485A1
• Time in Patent Office: 1,763 Days
• Field of Search: 704/260, 704/4, 704/258, 704/254, 704/209, 704/231, 715/863, 705/27, 706/267
• US Class Current: 704/231
• CPC Class Codes: G06F 16/3343 using phonetics

Abstract

The aural similarity measuring system and method provides a measure of the aural similarity between a target text (10) and one or more reference texts (11). Both the target text (10) and the reference texts (11) are converted into a string of phonemes (15) and then one or other of the phoneme strings are adjusted (16) so that both are equal in length. The phoneme strings are compared (12) and a score generated representative of the degree of similarity of the two phoneme strings. Finally, where there is a plurality of reference texts the similarity scores for each of the reference texts are ranked (13). With this aural similarity measuring system the analysis is automated thereby reducing risks of errors and omissions. Moreover, the system provides an objective measure of aural similarity enabling consistency of comparison in results and reproducibility of results.

Claims

1. An aural similarity measuring system for measuring the aural similarity of texts comprising:

a text input interface;

a reference text source providing access to a plurality of reference texts;

a processor adapted to

a) convert an input text into a string of phonemes,

b) to adjust the phoneme string of the input text and a phoneme string of a reference text from said reference text source so that the two phoneme strings are equal in length,

c) to assign a similarity score to the reference text representative of the similarity of the two phoneme strings, and

d) to repeat steps b) and c) for at least one further reference text from said reference text source; and

an output interface adapted to output a plurality of reference texts to which similarity scores have been assigned and their respective assigned similarity scores.

2. An aural similarity measuring system as claimed in claim 1, further comprising a data store in which is stored said plurality of reference texts.

3. An aural similarity measuring system as claimed in claim 2, wherein the data store further contains a plurality of phoneme strings each string being associated with a reference text.

4. An aural similarity measuring system as claimed in claim 2, wherein the processor is further adapted to select from the reference texts to which similarity scores have been assigned a sub-group of reference texts and their assigned similarity scores for outputting via the output interface, the selection being based on the similarity score assigned to each reference text.

5. An aural similarity measuring system as claimed in claim 1, wherein the processor is adapted to determine all possible adjustments of one or both of the input text phoneme string and the reference text phoneme string and is adapted to identify the similarity score representing the highest measure of similarity with respect to all of the possible phoneme string adjustments.

6. An aural similarity measuring system as claimed in claim 1, wherein the processor is adapted to adjust the phoneme strings of both of the input text and the reference text by inserting gaps into the phoneme strings.

7. An aural similarity measuring system as claimed in claim 1, wherein the processor is adapted to identify aligned phonemes which differ;

to allocate predetermined phoneme scores for each pair of differing aligned phonemes; and

to summing the individual phoneme scores to thereby assign a similarity score to the reference text.

8. An aural similarity measuring system as claimed in claim 7, wherein the processor is adapted to weight the phoneme scores in dependence upon the position of the pair of phonemes in the phoneme strings.

9. An aural similarity measuring system as claimed in claim 7, wherein the processor is adapted to weight the phoneme scores such that phoneme scores arising from partial text predetermined as less relevant which is present in the input text are lower than equivalent phoneme scores arising from other partial text in the input text.

10. An aural similarity measuring system as claimed in claim 7, wherein the processor is adapted to allocate a higher phoneme score to a grouping of non-adjusted aligned phonemes than to an equivalent grouping of aligned phonemes which have been adjusted.

11. An aural similarity measuring system as claimed in claim 1, wherein the processor, input interface and output interface are provided in a desktop computer.

12. A trademark searching system comprising an aural similarity measuring system in accordance with claim 1, wherein the reference text source comprises a trademark data source providing access to a plurality of trademarks and the processor is adapted to generate a plurality of similarity scores with respect to the aural similarity between an input trademark and a plurality of reference trademarks from the trademark data source.

13. An aural similarity measuring server comprising:

an input/output interface adapted for communication with one or more remote user terminals and further adapted to receive an input text;

a data store in which is stored a plurality of reference texts; and

a processor adapted to

a) convert the input text into a string of phonemes,

b) to adjust the phoneme string of the input text and a phoneme string of a reference text from said data store so that the two phoneme strings are equal in length,

c) to assign a similarity score to the reference text representative of the similarity of the two phoneme strings, and

d) to repeat steps b) and c) for at least one further reference text from said data store, wherein

said input/output interface is further adapted to output a plurality of reference texts to which similarity scores have been assigned and their respective assigned similarity scores.

14. An aural similarity measuring server as claimed in claim 13, wherein the data store further contains a plurality of phoneme strings each string being associated with a reference text.

15. An aural similarity measuring server as claimed in claim 13, wherein the processor is further adapted to select from the reference texts to which similarity scores have been assigned a sub-group of reference texts and their assigned similarity scores for outputting via the output interface, the selection being based on the similarity score assigned to each reference text.

16. An aural similarity measuring server as claimed in claim 13, wherein the processor is adapted to determine all possible adjustments of both the input text phoneme string and the reference text phoneme string and is adapted to identify the score representing the highest measure of similarity with respect to all of the possible phoneme string adjustments.

17. An aural similarity measuring server as claimed in claim 13, wherein the processor is adapted to adjust the phoneme strings of both the input text and/or the reference text by inserting gaps into the phoneme strings.

18. An aural similarity measuring server as claimed in claim 13, wherein the processor is adapted to identify aligned phonemes which differ;

to allocate predetermined phoneme scores for each pair of differing aligned phonemes; and

to summing the individual phoneme scores to thereby assign a score to the reference text.

19. An aural similarity measuring server as claimed in claim 18, wherein the processor is adapted to weight the phoneme scores in dependence upon the position of the pair of phonemes in the phoneme strings.

20. An aural similarity measuring server as claimed in claim 18, wherein the processor is adapted to weight the phoneme scores such that phoneme scores arising from partial text predetermined as less relevant which is present in the input text are lower than equivalent phoneme scores arising from other partial text in the input text.

21. An aural similarity measuring server as claimed in claim 18, wherein the processor is adapted to allocate a higher phoneme score to a grouping of non-adjusted aligned phonemes than to an equivalent grouping of aligned phonemes which have been adjusted.

22. A trademark searching server comprising an aural similarity server in accordance with claim 13, wherein a plurality of reference trademarks are stored in the data store and the processor is adapted to generate a plurality of similarity scores with respect to the aural similarity between an input trademark and a respective plurality of reference trademarks from the data store.

23. A computer readable medium encoded with a computer program for execution on a computer or server comprising at least one processor to cause the computer or server to perform an aural similarity measuring method, the computer program comprising program instructions for performing the following steps:

a receiving step in which an input text for which an aural similarity score is required is received;

a conversion step in which the input text is converted into a string of phonemes;

an adjustment step in which the phoneme string for the input text and a phoneme string associated with a reference text is adjusted so that the two phoneme strings are equal in length;

a ranking step in which the similarity of the two phoneme strings is assigned a similarity score;

a repeating step in which the adjustment step and the ranking step are repeated for further reference texts; and

an output step in which a plurality of reference texts to which similarity scores have been assigned and their assigned similarity scores are output to the user.

24. A computer readable medium encoded with a computer program as claimed in claim 23, further comprising a selection step in advance of the output step wherein a sub-group of reference texts is selected from the plurality of reference texts to which similarity scores have been assigned for outputting, the selection being based on the similarity score assigned to each reference text.

25. A computer readable medium encoded with a computer program as claimed in claim 23, wherein the adjustment step comprises determining all possible adjustments of both of the input text phoneme string and the reference text phoneme string and the ranking step identifies the lowest similarity score with respect to all of the possible phoneme string adjustments.

26. A computer readable medium encoded with a computer program as claimed in claim 23, further comprising the step of accessing one or more reference texts and their associated phoneme strings from a data store.

27. A computer readable medium encoded with a computer program as claimed in claim 23, wherein the adjustment step comprises adding one or more gaps in the phoneme string.

28. A computer readable medium encoded with a computer program as claimed in claim 27, wherein the one or more gaps made be added to the beginning or end of a phoneme string.

29. A computer readable medium encoded with a computer program as claimed in claim 23, wherein the ranking step comprises identifying aligned phonemes which differ;

allocating predetermined phoneme scores for each pair of differing aligned phonemes and summing the individual phoneme scores.

30. A computer readable medium encoded with a computer program as claimed in claim 29, wherein the phoneme scores are weighted in dependence upon the position of the pair of phonemes in the phoneme strings.

31. A computer readable medium encoded with a computer program as claimed in claim 29, wherein the phoneme scores are weighted such that phoneme scores arising from partial text predetermined as less relevant in the input text are lower than equivalent phoneme scores arising from other partial text in the input text.

32. A computer readable medium encoded with a computer program as claimed in claim 29, wherein a higher phoneme score is allocated to a grouping of non-adjusted aligned phonemes than to an equivalent grouping of aligned phonemes which have been adjusted.

33. A computer readable medium encoded with a computer program having instructions for trademark searching, the computer program comprising program instructions in accordance with claim 32 wherein the reference text comprises a plurality of reference trademarks and the processor is adapted to generate similarity scores with respect to the aural similarity between an input trademark and said plurality of reference trademarks.

34. An aural similarity measuring method for measuring the aural similarity of texts, the method comprising the steps of:

via a user input interface receiving an input text for which an aural similarity score is required; and

causing a computer or server to perform the following steps;

a) converting the input text into a string of phonemes;

b) accessing a reference text from a data store;

c) adjusting the phoneme string for the input text and a phoneme string associated with the reference text so that the two phoneme strings are equal in length;

d) ranking the similarity of the two phoneme strings to assign a similarity score; and

e) repeating steps b) to d) for at least one further reference text; and

via an output interface outputting a plurality of reference texts to which similarity scores have been assigned and their assigned similarity scores to the user.

35. A trademark searching method for measuring the aural similarity of trademarks, the method comprising the steps of:

via a user input interface receiving an input trademark for which an aural similarity score is required; and

causing a computer or server to perform the following steps;

converting the input trademark into a string of phonemes;

accessing a reference trademark from a data store;

adjusting the phoneme string for the input trademark and a phoneme string associated with the reference trademark so that the two phoneme strings are equal in length;

ranking the similarity of the two phoneme strings to assign a similarity score;

repeating the accessing, adjusting and ranking steps for further reference trademarks; and

via an output interface outputting a plurality of reference trademarks to which similarity scores have been assigned and their assigned similarity scores to the user.