Speech recognition - MP3 to text software

Question

I'm looking for a speaker independent program (commercial or free) that would enable me to transcribe MP3 files containing speech recordings (especially podcasts) to text. I wanted to try Dragon Naturally Speaking, but it seems like it only supports transcribing my own speech recordings. So what are the alternatives?

Solution 1

Dragon Naturally Speaking will import mp3 files and try to transcribe them. It prefers to tune its voice recognition to the individual speaker, but does a fair job without tuning. It would probably work best if your podcast speakers sound like Tom Brokaw.

Solution 2

One possible solution would be to upload your video to Youtube, and try the automatic captions that you can enable...it is not too accurate yet, but you can download the captions file and edit it yourself, if that helps...as for copyright/piracy issues for the song, you could make the video private on your profile, if that's even possible?

Solution 3

I would warn against trying Dragon Naturally Speaking--I wrote some scripts on my jailbroken iphone to copy/convert all the voicemail files from my phone to a folder on my PC and had the Dragon Naturally Speaking transcription service run against them.

The result of running the transcription against files with different speakers was absolutely unusable. I've tried some of the open source alternatives but speaker-independent voice recognition still seems limited to very small dictionaries.

Solution 4

Open Source: CMU Sphinx

Shareware: http://www.e-speaking.com/ (Windows)

Commercial: Dragon NaturallySpeaking (Windows)

You could also try this method if you were trying with osx which can be done using audacity and soundflower

You could also find some relevant links for opensource another shareware worth to try was voxcribecc

If you are an .net programmer you could use this method to make your own kit

Solution 5

I'm using http://www.voicebase.com with podcast and videos on english and it works very well. It's free for 50 audio hours.

You can download audio transcription on rtf, srt or pdf.

You can download machine transcriptions about 10-15 minutes after you upload, and sometimes, early.

View more solutions

Comments

[mickmackusa]

I tried Dragon Naturally Speaking, but it did a terrible job for podcasts with unknown speakers. It only worked fairly well with my own voice after training the program.

[baz]

@studioback: Is this method by Youtube only applied to one's own video, not those uploaded by others?

[baz]

@studiohack: For those videos uploaded by others, how to do that? I mean, without downloading and uploading as my own videos?

[studiohack]

On most videos, there is a CC icon in the bottom, click it and then automatic transcription...

[baz]

Thanks! On most videos I have seen, there is no CC icon. Do you know what kinds of videos have it and what don't? I only refer to English speaking videos.

[studiohack]

I've noticed that @Tim, but don't know why that is...

[Larry Morries]

Can it also import other audio files and transcribe them?

[287352]

Related Question: How Use Google's YouTube Speech Recognition without uploading videos to YouTube? No answers yet; just asked it 10 minutes ago.