Method and apparatus for the generation of reports

• US 5,051,924 A
• Filed: 03/31/1988
• Issued: 09/24/1991
• Est. Priority Date: 03/31/1988
• Status: Expired due to Term

• Current Assignee: Pitney Bowes Incorporated (Böwe Systec AG), Dictaphone Corporation (Microsoft Corporation)
• Original Assignee: Pitney Bowes Incorporated (Böwe Systec AG)
• Inventors: Chamberlin, David B., Daly, Daniel F., Jachmann, Emil F., Bergeron, Larry E., Su, Jy-Hong J.
• Primary Examiner(s): Kemeny, Emanuel S.
• Assistant Examiner(s): Merecki, John A.
• Application Number:
  US07/175,900
• Time in Patent Office: 1,272 Days
• Field of Search: 381/51-53, 381/41-46, 381/110, 364/200 MS File, 364/900 MS File, 364/513.5, 379/67-68, 379/71, 379/75, 379/88-89, 379/51-52, 369/24-25, 340/825.19, 434/112, 434/116
• US Class Current: 704/200
• CPC Class Codes: G10L 13/08 Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination
• CPC Class Codes: H04M 3/5307 for recording messages comprising any combination of audio and non-audio components
• CPC Class Codes: H04M 3/533 Voice mail systems

Abstract

A method and apparatus for generating, and storing for later retrieval, selected voice messages in response to selected verbal input trigger phrases. The voice signals including predetermined trigger phrases are transmitted from an input device such as a multiline telephone to a voice recognition system. The voice recognition system associates the trigger phrases with predetermined blocks of text message and in response to a sequence of trigger phrases, creates a report. The text is then output to a voice synthesizer system for the creation of synthetic voice signals corresponding to the full text of the report and the synthetic voice signals are output to a voice storage and forward system for later retrieval. The system also provides a printed copy of the full text of the report. In one embodiment of the system, an exception dictionary is provided which substitutes replacement words having a modified spelling for exception words whose pronunciation, as synthesized by the voice synthesizer, is not considered acceptable.

Claims

1. Apparatus for generation of verbal reports comprising:

(a) input means for inputting voice signals;

(b) recognition means for recognizing predetermined ones of said input voice signals as trigger phrases;

(c) synthesis means for synthesizing speech signals from text messages and for outputting said synthesized speech signals;

(d) text memory means for storing predetermined text messages;

(e) storage and retrieval means for storing said synthesized speech signals for later retrieval of identified speech signals, by authorized users, from remote locations; and

(f) control means, connected to said recognition means, said synthesis means, and said text memory means, for;

(f1) responding to said trigger phrases to select particular ones of said text messages from said text memory means;

(f2) establishing a signal path between said synthesis means and said storage and retrieval means; and

(f3) inputting said selected text messages to said synthesis means and controlling said synthesis means to output synthesized speech signals corresponding to said input text messages for storage by said storage and retrieval means.

2. Apparatus as described in claim 1 wherein said control means further comprises means for extracting selected information from the text of said selected text messages, converting said extracted information to dual tone multi-frequency (DTMF) signals and outputting said DTMF signals to said storage and retrieval means to identify said output synthesized speech signals.

3. An apparatus described in claim 1 wherein said trigger phrases are selected by a user of said apparatus.

4. An apparatus as described in claim 1 further comprising printing means responsive to said control means for printing copies of said input text messages.

5. An apparatus as described in claim 1 further comprising parsing means for modifying the spelling of words in said text messages so as to modify said synthesized speech signals.

6. An apparatus as described in claim 5 wherein said parsing means further comprises a predetermined exception dictionary, said dictionary including a list of selected words and alternative spellings for each of said selected words, said parsing means substituting the corresponding alternative spelling for each occurrence of one of said selected words in said selected text messages.

7. Apparatus as described in claim 1 wherein said selected text messages comprise radiological reports.

8. Apparatus as described in claim 1 further comprising means for editing said selected text messages before said selected text messages are input to said synthesis means.

9. A method of generating verbal reports comprising the steps of:

(a) receiving spoken trigger phrases;

(b) recognizing said trigger phrases and associating said recognized trigger phrases with selected ones of predetermined text messages;

(c) synthesizing speech signals corresponding to said selected text messages and

(d) storing said synthesized speech signals for later retrieval of identified speech signals, by authorized users, from remote locations.

10. The method of claim 9 wherein said trigger phrases are selected by a user of said method.

11. The method of claim 9 further comprising the step of printing a copy of said selected text messages.

12. The method of claim 9 further comprising the step of modifying the spelling of selected words in said text messages prior to synthesizing said speech signals.

13. The method of claim 9 further comprising the step of extracting information identifying said synthesized speech signals from said selected text messages and storing said synthesized speech signals in accordance with said extracted information.

14. The method of claim 13 wherein said selected text messages comprise radiological reports.

15. The method of claim 9 wherein said selected text messages comprise radiological reports.

16. The method of claim 9 comprising the further step of editing said predetermined text messages prior to synthesizing said speech signals.