US6173259B1
Expired / Lapsed
US
⏱️ 0.0 years remaining
Speech to text conversion
Assignee: Speech Machines PLC
•
Filing: 1998-03-27
•
Granted: 2001-01-09
•
Expires: 2018-03-27
Abstract
Abstract A speech-to-text conversion system is provided which comprises at least one user terminal for recording speech, at least one automatic speech recognition processor to generate text from a recorded speech file, and communication means operative to return a corresponding text file to a user, in which said at least one user terminal is remote from said at least one automatic speech recognition processor, and a server is provided remote from said at least one user terminal to control the transfer of recorded speech files to a selected automatic speech recognition processor.
Inventors
- 👤 David Bijl
- 👤 Henry Hyde-Thomson
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-03 13:46
CPC Classifications
G; G10; G10L; G10L15/00; G10L15/06; G10L15/065; G06; G06F; G06F3/00; G06F3/16; G10L15/26; H; H04; H04M; H04M3/00; H04M3/42; H04M3/50; H04M3/53; H04M3/5307; H04M2201/00; H04M2201/40; H04M2201/60
Claims Analysis
Total Claims: 18
Claim 1
Independent Claim
134 words
A speech-to-text conversion system comprising at least one user terminal for recording speech, at leant one automatic speech recognition processor to generate text from a recorded speech file, and communication means operative to return a corresponding text file to a user, in which said at least one user terminal is remote from said at least one automatic speech recognition processor, and electronic mail is used to send text data generated by the automatic speech recognition processor, together with corresponding recorded speech data in a single file, to a correction unit for manual connection of the text file, wherein the electronic mail includes timing data for relating text to speech, and wherein at least some of the words of the text have an associated start and end time recorded as part of the timing data.
Claim 2
Dependent Claim
134 words
A speech-to-text conversion system comprising at least one user terminal for recording speech, at leant one automatic speech recognition processor to generate text from a recorded speech file, and communication means operative to return a corresponding text file to a user, in which said at least one user terminal is remote from said at least one automatic speech recognition processor, and electronic mail is used to send text data generated by the automatic speech recognition processor, together with corresponding recorded speech data in a single file, to a correction unit for manual connection of the text file, wherein the electronic mail includes timing data for relating text to speech, and wherein at least some of the words of the text have an associated start and end time recorded as part of the timing data.
Claim 3
Dependent Claim
20 words
A system as claimed in claim 1 , wherein the text data includes text alternatives corresponding to a spoken word.
Claim 4
Dependent Claim
28 words
A system as claimed in claim 1 , wherein said at least one user terminal and said at least one automatic speech recognition processor communicate using electronic mail.
Claim 5
Dependent Claim
44 words
A system as claimed in claim 1 , wherein electronic mail is used for communications between each of said at least one user terminal and a remote server which is operative to control assignment of the speech files to multiple automatic speech recognition processors.
Claim 6
Dependent Claim
23 words
A system as claimed in claim 4 , wherein the automatic speech recognition processors are distributed remote from each other and the server.
Claim 7
Dependent Claim
38 words
A system as claimed in claim 4 , wherein the server acts to control assignment of recorded speech files for processing to automatic speech processors by queuing the received speech files and submitting them according to predetermined rules.
Claim 8
Dependent Claim
26 words
A system as claimed in claim 6 , wherein the predetermined rules by which the server queues jobs is one of urgency and user priority rating.
Claim 9
Dependent Claim
24 words
A system as claimed in claim 1 , wherein electronic mail is used to send said text file to at least one output terminals.
Claim 10
Dependent Claim
17 words
A system as claimed in claim 1 , wherein the recorded speech data is continuous speech data.
Claim 11
Dependent Claim
21 words
A system as claimed in claim 1 , wherein speech to text conversion is done as a single fully automatic operation.
Claim 12
Dependent Claim
38 words
A system as claimed in claim 1 , wherein speech to text conversion is done as a part-automatic and part-manual operation using said at least one automatic speech recognition processor and said at least one correction unit, respectively.
Claim 13
Dependent Claim
30 words
A system as claimed in claim 1 , wherein the correction unit includes a visual display unit for display of the text and a manual interface usable to select text.
Claim 14
Dependent Claim
15 words
A system as claimed in claim 1 , wherein correction is effected by manual operation.
Claim 15
Dependent Claim
46 words
A system as claimed in claim 1 , wherein the correction of the text file by the correction unit is recorded and transmitted back to the automatic speech recognition processor which generated the text file for adaption of the operation of the automatic speech recognition processor.
Claim 16
Dependent Claim
16 words
A system as claimed in claim 1 , wherein said correction is sent by electronic mail.
Claim 17
Independent Claim
141 words
A method of converting speech to text comprising recording speech at at least one user terminal, transferring recorded speech files from said at least one user terminal to at least one automatic speech recognition processor remote from said at least one user terminal, generating text files from said recorded speech files at said at least one automatic speech recognition processor, sending the text files and recorded speech files together in a single file by electronic mail to a correction unit, wherein the electronic mail includes timing data for relating text to speech, and wherein at least some of the words of the text have an associated start and end time recorded as part of the timing data, manually correcting the text files in accordance with the recorded speech files at said correction unit, and returning corresponding text files to respective users.
Claim 18
Independent Claim
141 words
A method of converting speech to text comprising recording speech at at least one user terminal, transferring recorded speech files from said at least one user terminal to at least one automatic speech recognition processor remote from said at least one user terminal, generating text files from said recorded speech files at said at least one automatic speech recognition processor, sending the text files and recorded speech files together in a single file by electronic mail to a correction unit, wherein the electronic mail includes timing data for relating text to speech, and wherein at least some of the words of the text have an associated start and end time recorded as part of the timing data, manually correcting the text files in accordance with the recorded speech files at said correction unit, and returning corresponding text files to respective users.
References Cited (Backward Citations)
GB2082820A
Cited
US5632002A
Cited
US5557659A
Cited
US5528739A
Cited
US5920835A
Cited
US5953392A
Cited
US5799273A
Cited
US5956681A
Cited
US5909667A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2004-01-09 | 2004-07-10 | 2005-01-09 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2008-01-09 | 2008-07-10 | 2009-01-09 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2012-01-09 | 2012-07-10 | 2013-01-09 | $7700.00 | Window Closed / Lapsed |