Filtering transcriptions of utterances
A method for facilitating mobile phone messaging, such as text messaging and instant messaging, includes receiving audio data communicated from the mobile communication device, the audio data representing an utterance that is intended to be at least a portion of the text of the message that is to be sent from the mobile phone to a recipient; transcribing the utterance to text based on the received audio data to generate a transcription; and applying a filter to the transcribed text to generate a filtered transcription, the text of which is intended to mimic language patterns of mobile device messaging that is performed manually by users. The method may also be applied to the audio data of a voicemail, with the filtered, transcribed text being communicated to a mobile phone as, for example, an SMS text message.
1. A computer-implemented method comprising:
under control of one or more computing devices configured with specific computer executable instructions,
receiving audio data representing an utterance;
transcribing the utterance to text based on the received audio data to generate a transcription; and
applying, to the transcribed text, a sentence punctuation filter that inserts a sentence punctuation character into the transcribed text based on a duration of silence between two words in the received audio data to generate a filtered transcription.
2. The computer-implemented method of claim 1 , wherein the sentence punctuation character is inserted into the transcribed text when the duration of silence between two words in the received audio data exceeds a predetermined threshold value.
3. The computer-implemented method of claim 1 , wherein:
the sentence punctuation character comprises a comma; and
the comma is inserted into the transcribed text when the duration of silence between two words in the received audio data exceeds a first predetermined threshold value but does not exceed a second predetermined threshold value, the second predetermined threshold value being greater than the first predetermined threshold value.
4. The computer-implemented method of claim 2 , wherein the sentence punctuation character comprises a period.
5. The computer-implemented method of claim 4 , further comprising capitalizing a first letter of a word immediately following the duration of silence that exceeds the predetermined threshold value.
6. The computer-implemented method of claim 1 , wherein the audio data representing the utterance is received via a microphone of a first mobile communication device.
7. The computer-implemented method of claim 6 further comprising communicating the filtered transcription to the first mobile communication device.
8. The computer-implemented method of claim 6 further comprising communicating the filtered transcription to a second mobile communication device.
9. The computer-implemented method of claim 8 , wherein the transcribed text represents a message intended for a recipient, and wherein the second mobile communication device is associated with the intended recipient.
10. The computer-implemented method of claim 9 , wherein an indication of the intended recipient is received together with the audio data.
11. A computer-implemented method comprising:
under control of one or more computing devices configured with specific computer executable instructions,
receiving audio data representing an utterance;
transcribing the utterance to text based on the received audio data to generate a transcription; and
applying, to the transcribed text, a digit homonym filter that inserts a digit, in substitution for a word that is a homonym to the digit, when such word is found immediately in-between two digits in the transcribed text to generate a filtered transcription.
12. The computer-implemented method of claim 11 , wherein a digit filter is applied to the transcribed text before the digit homonym filter is applied to the transcribed text.
13. The computer-implemented method of claim 11 , wherein the digit homonym filter comprises a list of predetermined words that are homonyms to digits.
14. The computer-implemented method of claim 13 , wherein the list of predetermined words further comprises a hash table.
15. The method of claim 13 , wherein the words “for”, “won”, “ate”, “to”, and “too” are represented in the list of predetermined words and are replaced respectively by the digit homonym filter with “4”, “1”, “8”, “2”, and “ 2,” respectively.
16. The computer-implemented method of claim 11 , wherein the audio data representing the utterance is received via a microphone of a first mobile communication device.
17. The computer-implemented method of claim 16 further comprising communicating the filtered transcription to the first mobile communication device.
18. The computer-implemented method of claim 16 further comprising communicating the filtered transcription to a second mobile communication device.
19. The computer-implemented method of claim 18 , wherein the transcribed text represents a message intended for a recipient, and wherein the second mobile communication device is associated with the intended recipient.
20. The computer-implemented method of claim 19 , wherein an indication of the intended recipient is received together with the audio data.
21. A non-transitory computer-readable medium comprising a transcription filtering module configured to be executed in one or more processors of an electronic communication device comprising a speech recognition engine, the transcription filtering module being further configured to:
receive, at the electronic communication device, audio data representing an utterance;
via the speech recognition engine, transcribe the utterance to text based on the received audio data to generate a transcription; and
apply, to the transcribed text, a sentence punctuation filter that inserts a sentence punctuation character into the transcribed text based on a duration of silence between two words in the received audio data to generate a filtered transcription.
22. The non-transitory computer-readable medium of claim 21 , wherein the audio data representing the utterance is received from a microphone of the electronic communication device.
23. The non-transitory computer-readable medium of claim 21 , wherein the sentence punctuation character comprises at least one of a period, a comma, a semi-colon, or a colon.
24. The non-transitory computer-readable medium of claim 21 , wherein the transcription filtering module is further configured to apply, to the transcribed text, a digit homonym filter that inserts a digit, in substitution for a word that is a homonym to the digit, when such word is found immediately in-between two digits in the transcribed text to generate the filtered transcription.
25. The non-transitory computer-readable medium of claim 24 , wherein the words “for”, “won”, “ate”, “to”, and “too” are replaced by the digit homonym filter with “4”, “1”, “8”, “2”, and “2,” respectively.
26. The non-transitory computer-readable medium of claim 24 , wherein the transcription filtering module is further configured to apply a digit filter that inserts a digit in substitution for a word associated with the digit to generate the filtered transcription, wherein the digit filter is applied to the transcribed text before the digit homonym filter is applied to the transcribed text.
27. A system for providing transcription filtering, the system comprising:
a server; and
a first mobile communication device in communication with the server;
the server being configured to:
receive, from the first mobile communication device, audio data representing an utterance;
transcribe the utterance to text based on the received audio data to generate a transcription; and
apply, to the transcribed text, a sentence punctuation filter that inserts a sentence punctuation character into the transcribed text based on a duration of silence between two words in the received audio data to generate a filtered transcription.
28. The system of claim 27 , wherein the server is further configured to transmit the filtered transcription to the first mobile communication device.
29. The system of claim 27 , wherein the server is further configured to transmit the filtered transcription to a second mobile communication device.
30. The system of claim 27 , wherein:
the duration of silence is at least about 0.50 milliseconds; and
the sentence punctuation character comprises a period.
31. The system of claim 30 , wherein the server is further configured to capitalize a first letter of a word immediately following the duration of silence.
32. The system of claim 27 , wherein:
the duration of silence is between about 0.20 milliseconds and 0.49 milliseconds, inclusive; and
the sentence punctuation character comprises at least one of a comma, semicolon, or colon.