What software can transcribe a recording with multiple voices?

darlyne koretos February 23, 2013

I interview individuals and small groups of people for articles. The software I’ve read about assumes you will be transcribing your own voice. What about multiple voices on the recording?

  1. Dave Holmes
    April 29, 2013 at 1:04 am

    As ha14 pointed out above, Nuance's method for using Dragon is to "parrot", thanks also to the link to my blog idictate.com.au where I talk about this method. Parroting is not easy, me personally I can not do it, I have a low attention span so it is not an easy way to voice-to-text multi speaker audio.

    Also mentioned above is Koemei who have been around for a while and are trying hard to produce an online solution to auto transcription of multiple voices. I have tried their offerings a few times over the years and it is still not close to being ready for commercial use as yet - but they are trying very hard so a site worth keeping an eye on.

    ha14 mentions isolating each voice which is exactly what the people at Dev-Audio are doing with their ingenious Microcone mic. They can split each speaker into a separate channel and feed that into voice recognition software. Dev-Audio.com is also worth keeping an eye on.

    Hope that helps.

    Dave Holmes
    Dictate Australia


  2. Ron Lister
    February 26, 2013 at 4:50 pm

    I don't believe there are any available "yet" .
    you could try one these two options. record the interview then send that recording to a hired transcription service.

    or you could listen to and repeat the recording to the voice to text software in your own voice.

  3. Oron Joffe
    February 23, 2013 at 8:08 pm
  4. ha14
    February 23, 2013 at 4:20 pm

    read this here
    The fact is that Dragon software was not designed to transcribe multiple voices. However, thousands of Dragon customers have successfully used the software to transcribe interviews using a basic technique called "voice writing" or "parroting." The key is how the interview content is delivered to Dragon.

    Can Dragon NaturallySpeaking Transcribe Meetings Or Interviews?
    A microphone array system from Dev-Audio (www.dev-audio.com), integrated with koemei enables hardware segmented multi-party speech recognition particularly for group meetings.

  5. ha14
    February 23, 2013 at 10:18 am

    if you can isolate every wave then perhaps you can do what you wish.

  6. Saikat Basu
    February 23, 2013 at 6:28 am

    I don't think there is any software of that kind which can transcribe multiple voices. The best workaround you can try is use "Echo Dictating". That is, record your interviews and then listen to the recording through an earphone or headphones and dictate the interview in your own voice.

    Hope this helps.

Ads by Google