Posts Tagged ‘Transcription’

Human Versus Software Audio Transcription: Cage Match!

Tuesday, July 29th, 2014

robot vs humansIn the ring today we have human verified audio transcription and automated software…

Who will come out on top? Find out below:

98% Guaranteed — With our proprietary review process, audio transcriptions come out at a 98% accuracy (or higher) every single time… This is due to the rigorous transcription process we implement on all of our clients’ files. First, your audio file is broken into bite-sized 6 minute pieces for our transcriptionists to take a first-attempt. Then the text goes through a review process which ends with timestamps and speaker-tracking being integrated into the text. Finally the work goes through a proofreading phase and a final quality check to ensure we stand behind our guarantee 100%!

Mumbling… background noise? Not a problem! (Usually) – Another huge benefit to taking advantage of humans (instead of an automated software program that attempts the same) comes from audio quality. In a perfect (transcription) world, everyone speaks the same language with the same vocabulary, accent, and tone. Unfortunately, one of the largest stepping stones that needs to be dealt with in audio transcription is the large variance in audio files. Sometimes, people forget to turn on their fancy microphone and instead the important class lecture is recorded on a low-quality device.

This can lead to buzzing, background noise, and unclear audio… a huge problem if your transcription software is designed to work off a specific type of audio. (Hint: This is why audio transcription apps tell you to get one of their recommended recording devices, and to speak very clearly and slowly.) The same exact issue is present with accents and multiple speakers talking over each other.

On the other hand, humans have a huge edge in this department. We’re able to utilize context clues, our own professional experience/knowledge, and our superior brain power to get the most out of each file. We can decipher audio files that software couldn’t dream of handling! Humans aren’t perfect though, sometimes audio files are so far from perfect that even a professional transcriber can’t revive it.

What about my grammar and punctuation?!?! – Unfortunately, this is another issue with software-transcription… how can a computer know when you paused to take a sip of water mid sentence, versus stopping for a sentence (period) or paragraph (period and return).

Slang Vocab… Yo!  – Think of software transcription services as having the vocabulary of your nearest dictionary. A wealth of knowledge… that’s for sure, but how long has that old Merriam-Webster been sitting in your closet? (
Hint: If there’s dust on your dictionary, it’s probably outdated when it comes to colloquial terms.) The main difference here between a human and an application is that humans adapt, grow, and learn with time which static dictionaries become outdated the day they are conceived.

Homonyms “They’re there! Right in the audio.” – Similarly, when your brain is analyzing the speech coming from your friend’s voice… you understand the difference between “To, Too, and Two” but that’s due to your complex understanding of language (not just knowing how words sound). For better or worse, unless your software can analyze, and understand your audio file… you’re not going to see correct homonym usage.

We have a ways to go with vocal recognition before a computer can decipher complex sentence structures, non-common word usage, or mumbling… for everything else, there’s our transcriptionists. 

Relaxed Location-Independent Money Through Freelance Audio Transcribing

Tuesday, July 22nd, 2014

freelance-audio-transcriptionThese days with a tough economy in many countries throughout the world… money is hard to come by. And easy, job-less work from home money is even harder to find.

That’s why online transcribing jobs are helping thousands of people supplement their income. Scribie’s freelance transcription program provides an easy way to make additional money on YOUR terms. The key here is that you are able to be your own boss, work when you want… where you want, and how you want.

While millions of people are stuck in less than desirable office jobs that have stringent hours and requirements, freelance positions are starting to thrive. Why’s that? The answer is simple… people want a way to generate money without the stress.

New systems like our freelance transcription program are allowing everyone from work-from-home moms, new freelancers, and experienced professionals to make some extra money. The biggest benefit is truly the laid-back operation of the system that ensures everyone wins.

The clients get high-quality audio transcription for their audio/video files, with industry-leading turnaround times and accuracy. The freelancers get paid a fair wage with huge benefits from being their own boss. No more headaches, no more corporate life, no more issues.

How is this all possible?

Scribie has spent countless hours perfecting the entire system to ensure a “win-win” situation for all parties involved. Everyone gets what they want, and then some!

Can’t wait to get started? We understand — here’s how to do it:

  1. Go to our Freelance Transcription Program page and get acquainted with the entire system (hint: it’s pretty simple).
  2. Make sure you fit the requirements and can handle this commitment (albeit a small one). The most important ones include having a great comprehension of the english language and a fast typing speed.
  3. Apply — it’s a very simple process that involves mostly basic information about yourself.
  4. Wait (just a little while) and go through the final stage of the application process that involves a test piece of audio transcription
  5. Boom! Now you’re ready to get going. As long as everything went smoothly, no strings attached money is right around the corner.

A Win-Win Transcription Service

At Scribie we really believe in giving back to the community and this freelance program is our way of funding many jobs that wouldn’t be possible otherwise. Think of us as a conduit to audio transcription services — we connect our clients to capable transcribers at an affordable, effective rate.

Recently, Sam Altman of YCombinator was talking about wanting to fund a tech startup that could provide “one million jobs.” The caveat, of course, was that the business couldn’t employ these one million people through traditional means (aka. having one million employees, because that would be too simple). Instead, he insisted that the jobs would be created through disruption of an industry… similar to how Uber allows regular people to make money from driving in their free time.

In a way, our freelance transcription program follows a comparable system. Stress-free, work from home, work at your own pace… what more could you want from a job that allows you to work when you want, where you want, and as much as you want. 

Self-Transcribe

Monday, May 26th, 2014

The Integrated Editor has proven to be one of the most useful tool at Scribie.com. We always get great comments about it in our customer surveys. We use it as the primary editor in all the four steps of our process; transcription, review, proofreading and QC and also make it available to our customers for files which have been transcribed and delivered. But today we are changing that. The editor is now available for all files which are uploaded to our website. You can always order the transcript, but if you wish to transcribe it yourself, you are more than welcome.

The following are some notable features.

  1. Supported file formats: mp3, wav, wma,  m4a, ogg, aif, aiff, amr, 3gp, 3gp, wmv, avi, flv, mpg, mp4, m4v, mov, webm, mts
  2. Configureable shortcuts
  3. Autocapitalization and autocorrect
  4. Autosave
  5. Live spellchecker
  6. Multi-cursor
  7. Terms and Phrase Analysis
  8. Conversion of transcript to Word/PDF/ODT formats.
  9. Tab completion (coming soon)
  10. Word prediction (coming soon)

The following additional features are available on Google Chrome browser.

  1. Variable speed playback
  2. Amplifier
  3. Dynamics Compressor
  4. Dictation

The editor has been extensively tested and works on all HTML5 supported browsers. However we recommend the latest version of Google Chrome for the best performance.

The following is a brief step-by-step guide.

  1. Upload your file at https://scribie.com/files/upload
  2. Wait for the upload to complete
  3. Click on the Transcribe link as show below.

Transcribe audio/video files

As usual, comments and feedback is most welcome.

Transcription Skill

Wednesday, March 5th, 2014

One of the misconceptions about of audio/video transcription is that it’s all about typing. Typing is definitely one of the key skills required, but there are other skills which are equally important, if not more. In this post we’ll elaborate on some of those skills.

Context:

Applying meaning to words and interpreting them is a uniquely human ability. It’s a feat which machines are yet to achieve. We listen to spoken words and combine it with our own knowledge and thoughts to interpret it. During transcription we come across a lot of words which sound similar and have to use context to arrive at correct word. Eg. illicit vs elicit. These words sound similar, but the meanings are vastly different. The correct word depends on the usage.

Memory: 

We often face the situation that the speaker’s voice is partly un-clear and only a syllable or two can be heard. These are the places where we leave blanks. However,  sometimes we can recall the word or the phrase being used in a similar sentence, which fills in the last piece of the puzzle. This is quite similar to the fill-in-the-blanks type of exercise, with additional hints from the audio file.

Research:

Research is one of our strengths. Since multiple people are involved in the transcription of each file, we have that many hands for the research. Google is our best friend for the research, but even searching on Google is a skill in itself. We have to use context again and add something to the search terms. It requires few tries before we find what we are looking for. Names of people and products, acronyms etc. are good examples. Google Maps works amazingly well for names of places.

Knowledge:

Knowledge is not a skill per se, but we use it everyday in our work. The discussion topic in our files vary widely. So general knowledge, current affairs, etc. is good to have.

At the end of the day, it’s accuracy which matters the most. We have to rely on much more than our typing skills to ensure that the transcript is 98% or more accurate. If you are looking to start transcription and/or getting your audio/video files transcribed, then you should consider these factors as well.

Rewarding Careers At Scribie

Thursday, January 2nd, 2014

Scribie is a fast growing online audio transcription service. We are on a high growth trajectory and looking to grow our QA team. If you are based in Bangalore, India and are proficient in English, then we may have the right job for you. We are hiring for the following positions.

  • Proofreader/QA (Code: SC/PR/1)
  • Transcriber/Reviewer (Code: SC/TR/1)
  • Trainees (Code: SC/FR/1)

We look for following skills primarily.

Listening ability:

Good listening ability is a key skill that is required. The QA work involves listening to the audio file and correcting the mistakes in the transcript. We depend on only one sense for this; our hearing. If you watched Snatch and didn’t feel the need of subtitles, then you should definitely come in and take our skills test.

Comprehension: 

Comprehension  is another basic skill required. In our work, we have to interpret what is spoken and understand it so as to find that one sound-alike mistake, that one contextual mistake out of the thousands of words in the transcript. So if you got the plot of Snatch, and found it amazing, then you do have the chops for it.

Western Culture:

Exposure to western culture is an added plus. Our customers are mostly from the America, Australia and Europe. Therefore exposure to the culture, the way of speaking, terms and phrases used is helpful. Watching Star World, FX, Hollywood movies, and watching/reading BBC, English fiction, non-fiction etc., listening to hard rock/metal music would expose you to western culture.

How to Apply:

Please send your updated resume to jobs@scribie.com and mention the job code in the subject line. The first step will be a phone screening, followed by a face-to-face interview and skills test. During the skills test, you’ll be asked to transcribe and review a 6 minute file. It usually takes around 3 hours to complete.

Why Work at Scribie:

We offer great career growth opportunities, meritocratic system and a good working environment. We are looking for leaders for our growing organization and we reward good performance. We also provide a peaceful and stress-free working environment. The work itself is enriching due to the vast range of topics. There is something new to learn every day. And then, there’s the joy of finding delight in a perfectly done transcript.

Transcription is a hard job. It requires lot of manual effort and knowledge. Our mission is to make it as painless and rewarding as possible. So come, join in our journey and discover a new career.

Re-inventing Audio Transcription

Friday, April 13th, 2012

Last month we completed four years of our company. We launched CallGraph Skype Recorder in April of 2008 with intention of offering services around it. The transcription service was one of those and it quickly became the most popular. The past four years we have invested all our time and effort in developing a human-powered transcription system with a single goal in mind: deliver the best quality transcript with the lowest amount of effort. In this series of posts we are going to write about this system in-depth.

So why build another human-powered transcription system? Why not just use a Automatic Speech Recognition system. Speech recognition has been in the limelight recently most notably because of Siri which uses Nuance’s Technology. In fact in Google Glass it’s a central component. Even Evernote recently added the support for it. However all of these systems employ keyword recognition; eg. commands that are spoken aloud. Our requirement was conversational speech recognition. The technology for that is still very immature. In fact we tried out CMU Shpinx and results were so poor that we ruled it out.

The big issue with human-powered systems is that it produces inconsistent results. Transcription is very labor intensive. And just like any labor intensive workflow, if you do not have processes in place, you will not be able to control the quality. The typical transcription process involves one person doing the typing work and maybe, another person proofreading it. On an average it  takes around four hours to type one hour of audio and around the same amount to edit it. This increases the cost of transcription. And even after that the transcript is bound to have mistakes, thereby affecting its quality.

So that was the starting point for us. Our system manages the transcription process end-to-end. It’s like a machine where you input the audio file and it outputs a high quality transcript in one day. This system is powered by our certified transcriptionists who do all the work. We have a well defined workflow and a robust process in place. We use some Machine Learning and Information Retrieval tools as well, but for the most part, it is all done by hand.

With this system we have completed more than 3000 hours of audio transcription till date and managed to survive four years in a highly competitive market. The best part is that we a high return rate of customers. For a startup, it might not be a stellar achievement like Instagram’s, but we believe that we have built something substantial; a scalable and reliable transcription service. The next post will cover the first part of our system, the transcriber certification process. Till then, if you are in need of a transcription service then you should try out our transcription service today. You will not be disappointed.

The next part of the series can be found here.

New Transcript Order Options

Tuesday, July 5th, 2011

We have recently added two new options which can be specified when ordering Transcripts. A screenshot is below.

The first one is Flexible Delivery. If Flexible Delivery is enabled then the we will deliver the transcript anytime within a week as per our schedule. In the worst case the delivery will be done after 1 week. But it can also happen before that if we find a slot for it. We offer a 10% discount for Flexible Delivery orders.

The second option is Additional Proofreading. In our transcription process we do one mandatory round of proofreading. For Additional Proofreading orders we do a second round of proofreading as well. This is useful for files which are difficult to transcribe, i.e. files which poor audio quality where the speakers can’t be heard clearly or which have noisy environment, or files which have non-native speakers whose diction is hard to comprehend. We charge $0.50 per minute extra for this option.

In addition to these options we have also do more quality checking than before. We also pay more attention to blanks which are leftover after proofreading and try to correct them as much as possible.

We’d like to thank you for using our service and your valuable feedback.

How to Transcribe Audio File

Wednesday, May 11th, 2011

So, you have an audio file which needs to be transcribed to text and have no idea how to go about it. Here’s how to do it.

The first thing you would need is ExpressScribe. It’s a free tool which enables quickly to start/stop/pause playback with hotkeys (or foot pedals) so that your hands are freed up for typing. To setup the hotkeys go to Control -> Hotkeys setup and enter your preferred keys. We suggest the following.

  • F7 -> rewind
  • F8 -> forward
  • F9 -> play
  • F10 -> stop

The useful thing is that these hotkeys are global. So you can control ExpressScribe even if it’s not the active application, which means you can type, play, stop, rewind, and forward without leaving your text editor. Very useful. Load up a test file and play around with the setup.

The second thing you would need is a good headset. Transcription is time consuming and when you wear it for long periods of time you may start feeling a bit of pain around your ears. Any headset with some padding around the earpiece will do. Do not play it on your speakers because then you will make lots of mistakes.

The third thing you would need is a text editor. You can use Word, OpenOffice.Org or any other editor of your choice. At a minimum it should have word completion and spelling auto-correction. While typing you’ll find that you misspell lot of words and to correct them you’ll have to stop and go back constantly. Auto-correction will save you time. Similarly auto-completion will save you typing, at least for common words.

Once everything is set up, you’re good to go. Bring up your editor, play the file, pause and type whatever you understood. Play-pause-type. Rinse and repeat till the file is complete. One pro-tip is try not to rewind too much. Rewind as few times as possible. Better still, instead of rewinding just mark the inaudible portion with a blank or make a guess, and after you’re finished go back and review the file. You’ll finish the file faster this way.

On an average it takes around 4 to 6 hours to finish 1 hour of audio. It varies by your typing speed,  the audio file quality and/or the diction of the speaker. Difficult files take longer. Plus, you’ll notice sometimes you cannot catch a few words, no matter how many times you rewind and play it back. Ask for a second opinion if you can.

As you would have guessed by now, it’s a painstaking task. It takes a lot of time and effort. That is exactly why we have the Audio Transcription Service. We do all the work for you and deliver a high quality transcript after 1 business day. For $75 you can get an hour of audio transcribed. We have a rigorous process and have transcribed over thousands of hours of audio to date. Try it out and check out the results for yourself.

On the other hand, if you like transcribing then check out our Freelance Transcription Program. You can work as a homebased freelance transcriber and get paid on an hourly basis for the work done.

Hiring a Transcriber: audio hour vs man hours

Monday, May 2nd, 2011

If you’re looking to sell our your own e-book then have a look at Jared’s post at Startups Open Sourced. He’s had great success with it and has written up a detailed how-to of the steps involved. One of his tips is, get your interviews recorded and hire a transcriber to transcribe everything which you can work off.

One of the things to remember while hiring a transcriptionist keep in mind the difference between audio hour and man hours, which Jared mentions in his post. An hour of audio can take anywhere from 4 to 6 hours to transcribe. If you’re paying by the hour then your cost will basically be multiplied by that factor. On the other hand if you’re paying by the audio hour, then the amount of effort spend does not matter. You’ll pay for the amount of audio transcribed and not time taken for it to transcribe.

On Scribie.com we charge always by the audio hour. You don’t have to worry about the amount of actual time taken. Even if the audio is hard to transcribe and takes a more effort, you wont have to pay extra. At the end of the day you’ll still get a high quality transcript of your audio file.

CallGraph.Biz is now Scribie.com

Tuesday, March 15th, 2011

We have moved to a new domain; Scribie.com. All the accounts data from CallGraph.Biz has been migrated to Scribie.com. If you had an account on CallGraph.Biz then you can now login to your Scribie.com account and check.

https://scribie.com/account/login

With Scribie.com the focus is more on our audio transcription service. We have been working on our outsourcing platform for a long time and we are very confident about it. It’s the best audio transcription service you’ll find out there.

We have also discontinued the online backup and Skype Group Collaboration services. We are not accepting new accounts for those. If you had been using those services then your files will still be available and you can still keep uploading. But, we are not planning to add any new features or maintain it.

We still offer the CallGraph Skype Recorder for free and plan to continue working on it.