System and method for processing speech files

• US 9,369,581 B2
• Filed: 11/26/2013
• Issued: 06/14/2016
• Est. Priority Date: 06/12/2001
• Status: Expired due to Fees

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: Hirschberg, Julia, Whittaker, Stephen
• Primary Examiner(s): Sirjani, Fariba
• Application Number:
  US14/089,839
• Publication Number:
  US 20140079197A1
• Time in Patent Office: 931 Days
• Field of Search: 379/88.14
• US Class Current: 1/1
• CPC Class Codes: G06F 16/316 Indexing structures
• CPC Class Codes: G06F 16/345 Summarisation for human users
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: H04L 51/08 Annexed information, e.g. attachments
• CPC Class Codes: H04L 51/56 Unified messaging, e.g. interactions between e-mail, instant messaging or converged IP messaging [CPM]
• CPC Class Codes: H04M 2201/40 using speech recognition
• CPC Class Codes: H04M 2203/301 Management of recordings
• CPC Class Codes: H04M 3/533 Voice mail systems

Abstract

A system and method for speech file processing which provides users with differentially selectable speech file transcripts which can be sent to one or more other users. The speech files may be voicemail messages from which respective voicemail transcripts are created. The voicemail transcripts are provided in a user selectable format from which users may select non-contiguous portions of the transcript.

Claims

1. A method, at a first device belonging to a recipient of a voicemail message, comprising:

transcribing, via a processor, a voicemail message, to yield a transcription;

indexing, via the processor, the transcription to yield an indexed transcription;

adding the indexed transcription to a transcription index associated with transcripts of a plurality of voicemail messages;

receiving, via a graphical user interface on the first device, a query from the recipient of the voicemail message;

displaying, using the transcription index and the graphical user interface, portions of the plurality of voicemail messages related to the query, to yield identified portions;

generating a speech file stored on a computer system, the speech file comprising the identified portions, wherein the speech file comprises the identified portions in both a textual format and an audible format; and

communicating the speech file as an attachment to a second device via email, the second device being used by a second user different from the recipient.

2. The method of claim 1, further comprising audibly presenting the speech file to the second device via a network.

3. The method of claim 1, wherein each word in the transcription index is indexed relative to a frequency of occurrence in the plurality of voicemail messages.

4. The method of claim 1, wherein the speech file comprises non-contiguous portions of the plurality of voicemail messages.

5. The method of claim 1, wherein the transcribing of the voicemail message occurs upon a threshold number of untranscribed voicemail messages being received.

6. A system belonging to a recipient of a voicemail message, the system comprising:

a processor; and

a computer-readable storage medium having instructions stored which, when executed by the processor, cause the processor to perform operations comprising;

transcribing a voicemail message, to yield a transcription;

indexing the transcription to yield an indexed transcription;

adding the indexed transcription to a transcription index associated with transcripts of a plurality of voicemail messages;

receiving, via a graphical user interface on the system, a query from a recipient of the voicemail message;

displaying, using the transcription index and the graphical user interface, portions of the plurality of voicemail messages related to the query, to yield identified portions;

generating a speech file stored on a computer system, the speech file comprising the identified portions, wherein the speech file comprises the identified portions in both a textual format and an audible format; and

communicating the speech file as an attachment to a device via email, the device being used by a second user different from the recipient.

7. The system of claim 6, the computer-readable storage medium having additional instructions stored which result in the operations further comprising instructing a sound speaker to audibly present the speech file to the device.

8. The system of claim 7, wherein each word in the transcription index is indexed relative to a frequency of occurrence in the plurality of voicemail messages.

9. The system of claim 7, wherein the speech file comprises non-contiguous portions of the plurality of voicemail messages.

10. The system of claim 6, wherein the transcribing of the voicemail message occurs upon a threshold number of untranscribed voicemail messages being received.

11. A computer-readable storage device having instructions stored which, when executed by a first device belonging to a recipient of a voicemail message, cause the first device to perform operations comprising:

transcribing a voicemail message, to yield a transcription;

indexing the transcription to yield an indexed transcription;

adding the indexed transcription to a transcription index associated with transcripts of a plurality of voicemail messages;

receiving, via a graphical user interface on the first device, a query from the recipient of the voicemail message;

displaying, using the transcription index and the graphical user interface, portions of the plurality of voicemail messages related to the query, to yield identified portions;

generating a speech file stored on a computer system, the speech file comprising the identified portions, wherein the speech file comprises the identified portions in both a textual format and an audible format; and

communicating the speech file as an attachment to a second device via email, the second device being used by a second user different from the recipient.

12. The computer-readable storage device of claim 11, the computer-readable storage device having additional instructions stored which result in the operations further comprising audibly presenting the speech file to the second device over a network.

13. The computer-readable storage device of claim 11, wherein each word in the transcription index is indexed relative to a frequency of occurrence in the plurality of voicemail messages.

14. The computer-readable storage device of claim 11, wherein the speech file comprises non-contiguous portions of the plurality of voicemail messages.