Sometimes we are asked why a person considering transcription should not simply use one of the new and improving programs for computers that type while you talk. These programs recognize your speech as you talk into a microphone and type what you say into a document. The thought is that you would save a lot of money in transcription costs. In fact, several companies have sprung up and have marketed specific systems for the medical and legal communities. In addition, you will find that some transcription companies are claiming to put digital dictation through a speech recognition system before it is given to a transcriptionist. The quick answer:Most professionals should not yet use speech-to-text.  Not only are these programs not accurate enough, you must spend more time on three things:  (1) You usually must talk slower and spend time training the system. (2) You have to correct the errors the program makes.  (3) You have to be your own secretary - correcting the errors you make, know proper grammar, spelling, formatting, etc.  Often times spoken English is not as it will be written.  We take care of this for you. The longer answer is that it is a matter of cost and convenience.  If the total cost to the dictator is less using such text-to-speech systems, then they should use them. Our experience is that these systems are not yet sophisticated enough to pay for themselves, and may actually cost professionals more due to their ongoing time investment.  There is no doubt that in the future these systems will be excellent, but for practical dictation, these systems have a long way to go.  Here's what we think: Type-thing Servicesdoes not use speech recognition for its transcription work.  Why?  Because even if the accuracy of the process was fairly high (and it never is), we would have to listen to the whole audio to verify the transcript was correct.  On top of that, we would have to edit your spoken word to something fitting for your needs.  We often do that on the fly while listening to your audio on the first pass.  All of this editing a recognition transcript takes longer than just doing it ourselves. You might also be interested in a well-referenced article "Rest in Peas: The Unrecognized Death of Speech Recognition," by Robert Fortner, that argues there are multiple barriers for good-accuracy speech-to-text systems.  The show that accuracy has not improved in speech recognition software since about the year 1999.  For limited uses like dialing a cell phone it might work, but for transcripts there are problems. See more information at type-thing.com/tips.html or contact us at 505-922-1000. ...read more

How can you ensure the best transcription for your business? Finding a good transcriptionist is one answer; however, effort to transcribe a tape, the overall quality of the transcript, and the cost of producing the transcript is dependent on the quality of the audio file or tape that is generated. By producing a good recording, you may be able to reduce the cost of your transcription, increase accuracy of transcription and reduce the number of "indiscernible" sections on your transcript. At Type-thing Services, we've compiled a list of transcription DOs and DON'Ts that may be of help. Speak clearly. Speak at good level volume. Have people speak one at a time. For digital or tape recorders, record on fast speed or high quality setting. This makes a clearer recording but uses more memory or tape. Record in a quiet environment. In groups of two or more, make sure each person can be heard equally well. Use recording system with multiple microphones in large groups to ensure you can hear each individual. Use a microphone near the speaker.  If the speaker will move around, use a wired or wireless lapel microphone. Only have one microphone or recorder?  If possible, have all persons speaking the same distance from the recorder.  If that is not possible, place it nearest to the most important part of the conversation or point it in that direction. During question/answer sessions, have people come to a house microphone or bring a wireless microphone to them before they ask their question.  Alternatively, have the person answering questions repeat the question so it is captured on the recorded audio. Use good quality equipment made for the number of people you are recording. Alternatively, if good equipment is not available, use multiple digital or tape recording devices around the room (we will have to listen to each to fill in gaps from the others). Keep recorder going (turned on and recording) well before people talk. In large groups, have each person state their name before talking if they need to be accurately identified. Alternatively, have a note taker make notes each time a person talks including their name and the first few words that they say.  Provide agenda. Provide lists of speakers, agendas for meetings, and other references as available to us so that we can create better annotated, ordered transcripts from your audio. Not all of these hints apply to every situation. A single-person transcription rarely has any of these possible problems. Sometimes you cannot avoid background noise or conversations where people interrupt and talk over one another. A good transcriptionist can help some of these situations; however, they cannot perform miracles. When you are recording important information, especially for group discussions, it pays to invest in a good conference microphone set and recording system. Type-thing Services can work with you or the facility in which you will record your audio to make sure it is the best it can be for transcription.  See type-thing.com/tips.html or contact us at 505-922-1000 for more information. ...read more