- This topic has 26 replies, 19 voices, and was last updated 4 months, 3 weeks ago by Anonymous.
15th March 2012 at 1:25 pm #2549
I have interviews recorded with a digital recorder and saved as VLC files. Is there any software available which can help in automatic transcription of interviews into text directly from the VLC file ?21st March 2012 at 3:24 pm #2563Katie MetzlerParticipant
This might be a useful link for you…22nd March 2012 at 3:33 am #2562
Thanks for sharing the link. this is useful. I have used express scribe and found it to be effective.
best wishes.4th April 2012 at 11:13 am #2561Kim JohnstonMember
Dragon has software however you need to “train” it. If you have multiple participants then it is not possbile as most voice recognition software only recognises the voice trained. Short answer is to pay for transcription – much easier!4th April 2012 at 2:55 pm #2560Franklin W. BenderParticipant
I’ve been down this path. I couldn’t find software that would accurately transcribe a digitally recorded interview. Dragon has limitations if what is being transcribed comes from a digital source. I found express scribe the best option because I could slow the audio down while I transcribed the interviews. Based upon what I’ve read, and my experience, it takes a minimum of 4-5 hours to transcribe 1 hour of digitally recorded interviews. Now the real question is, what’s your time worth? You could pay someone to transcribe for you – but then you have to pay for accuracy. When you get to analysis, have you considered using NVivo 9.0. I’m just learning it and conducting my first analysis using it with my interviews data. It has some interesting analytical features. Check it out.4th April 2012 at 2:56 pm #2559Franklin W. BenderParticipant
Agreed.4th April 2012 at 5:56 pm #2558
Thanks for the reply. I have tried to the transcription on my own and yes it take a lot of time as you mentioned. I am using Atlasti for my analysis and I am also learning it as I am working on my analysis.
wishes.4th April 2012 at 5:57 pm #2557
Thanks for the reply. I am aware of the Dragon, but haven’t used it till now. I will plan something soon.
wishes.5th April 2012 at 7:10 pm #2556Ken ViersMember
Hello, S. S.
I have used digital recordings that were manually transcribed as my dissertation data. I have approx. 6000 minutes of audio data. That is one deep pile of transcripts!
Was it worth paying for them all to be transcribed? No. Only key informants and those most likely to be quoted.
QSR Nu*Dist is excellent qualitative software, but be sure the files are in raw text format.
At the start, I purchased Dragon Naturally Speaking because I was told by the vender that it could do automatic transcription. Do not waste your money. Even after extensive training, Dragon only does really well with one speaker, the trainer. Add an accent or a different tone and it hasn’t a clue what was said. Dragon works well if you want to “write” orally. Beyond that, it sits on the shelf unused.
k6th April 2012 at 6:14 am #2555
thanks Ken for the advice. I am using the Atlas ti for my analysis. I am fouding it to be useful and easy to learn.
best wishes9th April 2012 at 1:33 pm #2554Mohd Khairie AhmadMember
I highly encourage you to use NVivo either version 8 or 9. With this qualitative analysis software, you may straight away do the coding. Based on the coding and the analysis, than only you may want to transcribe particular section for your report. Watch this video for some ideas on how NVivo works for transcription and direct coding (no need to transcribe)…http://www.youtube.com/watch?v=TVFJ8YCSKB49th April 2012 at 2:35 pm #2553
Thanks for the time-saving idea. This sound promising.
Sushanta14th July 2012 at 1:57 pm #2552Transcription ServicesMember
Automatic Transcription software is very much useful, If your audio quality is excellent. If your audio files quality is OK or verbatim audio transcription better to go for manual audio transcription. For multiple speakers audio files, better to go for manual audio transcription.
In automatic transcription, much work needs to be done to massage this transcript into final form. Some of the initial work is:
Correct incorrectly transcribed words/phrases.
Correct punctuation/sentence breaks.
Define paragraph breaks.
If you have more than one voice it is almost impossible to get a good transcript. Add to that any background noise or a weak recording and you can pretty much forget it.
For cost effective manual transcription, you can refer to13th February 2013 at 6:47 am #2551
Thanks Lesley. I have already done the transcription manually and it was a very satisfying experience. I got a lot of insights about the data as I was doing the transcription which eventually helped in transcription.
Sushanta20th February 2013 at 10:41 am #2550Anson joseParticipant
you try dragon naturally speaking software
- You must be logged in to reply to this topic.