Data processing: speech signal processing – linguistics – language – Speech signal processing – Application
Reexamination Certificate
1998-06-05
2001-01-16
{haeck over (S)}mits, T{overscore (a)}livaldis I. (Department: 2741)
Data processing: speech signal processing, linguistics, language
Speech signal processing
Application
27, 27, 27, C369S025010, C369S029010, C369S024010, C379S075000, C178S021000
Reexamination Certificate
active
06175822
ABSTRACT:
RELATED APPLICATIONS
Not applicable.
FEDERALLY SPONSORED RESEARCH OR DEVELOPMENT
Not applicable.
MICROFICHE APPENDIX
Not applicable.
BACKGROUND OF THE INVENTION
1. Field of the Invention
The present invention relates to the recording and transcription of audio signals, and more particularly to a method and system for providing network based transcription of free-form speech signals.
2. Description of the Related Art
In many areas, it has often been necessary to translate spoken language into written words. Long before the advent of recording devices such as audio tape, words were taken down with stenography or shorthand as they were spoken. Over time, the introduction and widespread availability of recording devices such as audio tape facilitated recording of spoken words and later listening to and transcribing the words into written form.
Transcription of free-form speech from audio tapes or other physical storage media has become commonplace. In office settings, for instance, a worker commonly dictates a letter to tape and then gives the tape to an assistant for transcription. The assistant in turn places the tape in a player, listens to the recorded speech, and types the spoken words on a typewriter or computer for subsequent processing.
More recently, transcription of free-form speech has been used in connection with telecommunications voice service platforms, for instance, to record free-form speech responses to survey questions. For example, a telecommunications service carrier may provide an enhanced services platform to which callers can connect by dialing toll free phone numbers that are respectively associated with various promotional campaigns. Once connected, for a given promotional campaign, the platform may automatically play messages about a specified product or service and then ask the caller questions.
As the caller responds to these questions, the enhanced services platform will typically record the caller's free-form spoken responses as digital audio files. In turn, workers for the carrier may regularly copy the digital audio files into analog form on tapes (or digital form on CD-ROM), label those tapes to correspond to the respective promotional campaigns, and then ship the tapes to a specialized transcription agency for transcription. In turn, at the transcription agency, skilled transcriptionists play the tapes associated with specified campaigns and transcribe the spoken voice responses into written words for subsequent tabulation and analysis.
Alternatively, the enhanced services platform may compress the digital audio files and then ship computer disks of these compressed files to the transcriptionist agency or electronically transfer the full compressed files to the transcriptionist agency. At the transcriptionist agency, workers may in turn download the digital audio files in full onto computer disk drives. Transcriptionists may then work at those computers, running applications that decompress the stored files and play the decompressed speech signals for transcription.
Unfortunately, the existing methods of recording and transcribing free-form speech signals are deficient. For instance, the process of transferring the recorded speech signals to tapes, labeling those tapes and physically transferring the tapes to a transcription agency is costly, lengthy and prone to error. Further, tapes can be misplaced, lost or damaged in transit to the transcription agency. Still further, tapes can be inadvertently disassociated from their respective surveys, thereby likely rendering the voice responses useless. Yet further, with large promotional campaigns, hundreds of tapes may be generated and shipped per week, and these tapes may be discarded after use, thereby wasting valuable resources.
Additional problems arise when digital audio files are transferred in full to a transcriptionist and then stored on computer hard disks for subsequent playback and transcription. For instance, space limitations on the local computer hard disks may necessarily restrict the ability to store such files, particularly where the files are large. Further, the process of transferring the digital audio files to the transcriptionist agency and then downloading the files in full on computer hard drives or other storage media for subsequent playback is time consuming. Still further, transcription of the recorded speech signal will not begin until after the entire file has been downloaded and played back.
Similar deficiencies exist in other applications of transcription as well. For instance, in an office setting, even the most simple task of dictating and transcribing a letter can be complicated by the process of physically transferring the recorded tape to an assistant for transcription. In some cases, the assistant may not be conveniently located in relation to the person dictating the letter. As a result, the process of transferring the recorded tape can be lengthy. Further, problems can arise in tracking multiple tapes and associating those tapes with their sources and subjects.
Due to the deficiencies in the existing art, a need exists for an improved, more efficient method and system to facilitate transcription of free-form speech signals.
SUMMARY OF THE INVENTION
The present invention provides an improved method and system for transcription of free-form speech signals. According to the invention, a speech signal is recorded as a digital audio file in a storage medium and is then streamed over a data network to a client terminal for transcription. As the speech signal arrives, it is buffered in memory at the client terminal while a streaming player application plays the signal to a transcriptionist. The transcriptionist then conveniently listens to and transcribes the speech signal on the fly, as it is being streamed.
Advantageously, the invention thus avoids the need to physically transfer and download the full digital audio file to a transcriptionist computer or to transport physical storage media, such as tapes or CD-ROM from the place of recording to the place where the recorded voice signals will be transcribed. As a result, the invention avoids the costs and other deficiencies associated with shipping and disposing of the storage media, and the invention facilitates quicker, more efficient transcription.
It is thus an object of the invention to provide a method for network based transcription of a voice signal, including receiving the voice signal, storing a digital audio file representing the voice signal in a file store associated with a server, having the server stream the digital audio file over a network to a client terminal, having the client terminal audibly play the voice signal represented by the digital audio file as the file is received, and having a user at the client terminal listen to and transcribe the voice signal as it is played.
It is another object of the invention to provide a method of transcribing a voice signal, including recording the voice signal on a storage medium accessible over a data network, having a server on the network respond to a request for the voice signal by streaming the voice signal over the data network to a client terminal, having a user at the client terminal operate streaming controls and selectively listen to and transcribe the voice signal.
It is still a further object of the invention to provide a system for network based transcription of a voice signal, including a file store, a server coupled to a network and to the file store, the server receiving and storing in the file store a digital audio file representative of the voice signal and, in response to a request from a client terminal on the network, streaming the digital audio file over the data network to the client terminal, the client terminal receiving and audibly playing the voice signal represented by the streamed digital audio file as it arrives, and a user at the client terminal transcribing the voice signal audibly played by the client terminal.
These as well as other advantages of the present invention will become apparent to those of ordinary skill in the ar
Ball Harley R.
Funk Steven J.
Nolan Daniel A.
Sprint Communications Company L.P.
{haeck over (S)}mits T{overscore (a)}livaldis I.
LandOfFree
Method and system for providing network based transcription... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Method and system for providing network based transcription..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and system for providing network based transcription... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2444321