Transcribing audio (wav) interviews to text - how?

[Mike Watson]

Depending on what part of the country you're in, a Craigslist ad offering $10/hr has netted me some pretty good transcription before. A raise to $15/hr keeps them coming back. Couple hundred bucks can get you a LOT of transcription.

[Roberto Diaz]

i heard an anecdote about an early speech recognition system where the person said "recognize speech" into the mic, and the system -- after chugging on it for a while -- decoded it onto the screen as "wreck a nice beach".

:-)

[Adrian Tan]

Originally Posted by Ozzie Alfonso

The most efficient way to edit the interviews is off a text file, then implementing the text edits and cleaning the audio. I know there are many apps that can "transcribe" an audio file to text, but I'm looking for one that can do it well from the get go... I'm using a Mac with Adobe Cloud - Premiere Pro, Audition,etc. Any suggestions will be most appreciated.

If you have Premiere Pro, have you tried the built-in transcription function?

Premiere Pro's Speech to Text Helps You Save Time | Creating Time | Adobe TV

I don't remember it working particularly well though...

[Adrian Tan]

Originally Posted by Don Palomaki

For a quick sample of professional real time text recognition - see the caption on live TV broadcasts like FOX News - and laugh (or cry)

I'm wondering if any of that is voice recognition per se. I think the most popular captioning technologies for live captioning are: (a) stenography (which involves using a lot of short cuts, which sometimes produce the amusing results); and (b) "respeaking" (where the captioner repeats what's said in a more computer-friendly way).

[Adrian Tan]

Originally Posted by Richard Crowley

My understanding is that virtually all the prime-time shows (60 Minutes, et.al.) use human transcription services where they email the audio file to an organization in another time-zone (typically Asia/Oceania) and it is transcribed by humans overnight and ready for use the next day. If you Google for audio transcription service or similar term, you will find hundreds (maybe thousands?) of such services.

That's my understanding too. After all, the producer is unlikely to be the editor, and is unlikely to completely trust an editor to pick out the important parts of an interview. More likely they'll sit in on the edit or do a "paper edit" on a transcription.

Transcriptions for court proceedings here are back in the judges' hands overnight. Not sure what sort of system is now commonly employed, but I've seen controlling the forwards and backwards of the audio with foot pedals.

There's also specialist captioning software ("Swift" and "ISIS", amongst others) that makes it easy to start/stop/rewind/fast forward from the keyboard, time the captions in and out according to timecode, adjust colour, positioning and line breaks, and keep track of reading speed limitations.

[Pete Cofrancesco]

They also make software to sync the transcript to the video. Otherwise you would have to listen to the video to make the edits.

I also agree a human transcriptionist is the way to go but sounds like the OP is doing this on the cheap.