Hot answers tagged

8

Technically, it's next to impossible to remove specific sound from a waveform containing many sounds. The problem is similar to trying to find which car the city pollution belongs to. That said, 'voice removal' techniques do exist, and rely on a few principles: If you take any digital mono sound, invert (or flip) the phase and mix-it over itself you will ...


7

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.


6

Is it possible? No. When you look at a piece of music from a signal processing standpoint, it's all just signal with certain frequencies. Humans are great at psychoacoustically filtering out human speech or singing from music, but a computer cannot do that. The problem is that both music and vocals are mixed together, and that the frequencies of the ...


4

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?


4

Skype should work fine How much bandwidth does Skype use while I'm in a call? Skype automatically selects the best codec depending on the connection between yourself and the person you are calling. On average, Skype uses between 3-16 kilobytes/sec depending on bandwidth available for other party, network conditions in between, callers ...


4

I have a Plantronics Calisto B70 Bluetooth headset that came with Dragon Naturally Speaking (Amazon.com: Dragon NaturallySpeaking Premium 11 Bluetooth). If I try using sound recorder, I can hear some crackling noise as well as my voice, so I don't think the quality is great. One time, I was able to get it working 99% accurately with DNS, but since then I ...


4

If you are looking to isolate audible speech try combining a lowpass filter with a high pass filter. For usable audio I have noticed that filtering out 200hz and below then filter out 3000hz and above does a pretty good job of keeping usable voice audio. ffmpeg -i <input_file> -af "highpass=f=200, lowpass=f=3000" <output_file> In this example ...


3

Empathy or Pidgin i prefer Pidgin... :D


3

Windows 7 comes with speech recognition already built-in, just open Start > Control Panels > Speech recognition, and turn it on. Accuracy is acceptable for note-taking, though you can get better quality by going through the tutorial. Speech recognition is supported by the OS, so it works with most programs. If you are looking for a speech-enabled note-...


3

I believe the best free speech recognition software is CMU Sphinx. It looks quite mature, though I have not used it. It is however more a research project than focussed on end users, so while it apparently works well, it's a bit of work setting it up; in particular, you will need to train it before using it. Other software you might want to try: http://en....


3

This app claims to do what you want Music Morpher and this also http://www.blazeaudio.com/howto/vocalremover/


3

Have a closer look at the movies where the "voices disappear". Do they have DTS or other surround sound audio tracks? Maybe your Player doesn't downmix the 6 (?) channels to stereo (i assume the headphones are stereo?) and just discard every channel but two. I had the same problem and noticed, that only the left-back and right-back channels were used. ...


2

Repeat After Me is an application that allows for the recording of one's own voice along side the TTS technology built into OS X. The software graphs both your voice and the TTS(Text-to-speech) voice and allows for imposing the pitch of your voice to that of the computer TTS voice, thus allowing an attempt of a more humanized infliction upon the TTS audio. ...


2

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'...


2

Being a producer of hip hop myself I know it's nearly impossible to do this without the original project file I get begged all the time by dj's to send the master of the instrumental because they could not "filter out voices from the track" The only trick I know of is looping which only works with short hip hop beats.


2

I haven't been able to get my HP (has a Gobi 2000) to do voice but I did get my Acer 1420p to make calls. It has a Huawei chip in it. Here is how: http://forum.notebookreview.com/acer/482532-enabling-ussd-voice-support-em770w-3g-module.html


2

They won't have as good quality as normal mics since the audio data is compressed before transmission. They are, however, generally good enough for speech recognition. Two hours might be a bit too long for the cheaper ones, but it certainly is doable.


2

I've got a Linksys PAP2 which I use for British Telecom SIP VoIP. You could use one with Vonage, without having to need to turn your computer on. They are very cheap on eBay. There are also various Skype phones available on their website. I can only seem to link to the UK site here.


2

On a mac the say {text} command in terminal will do a text-to-speech conversion that sounds somewhat like GLaDOS. There are different voices available the default is female and sounds a bit lower tone than the Portal voice.


2

I'm not sure that you can do this in real time, unfortunately. Her voice is highly processed using formant shifting and manipulation of artifacting to get it to kind of slide up and down but still be robotic. It is demonstrated in this video. If you know any music production techniques or programs, you could get a similar effect by using the Mac's built in ...


2

To be clear from the beginning on: It is a highly complicated task to automatically analyze audio recordings. Trying to differentiate between speech and noise is theoretically possible, but I doubt there is a one-click solution available on the Internet. This sounds more like research work. Also, your recording will probably not have passages of complete ...


2

There's a web site here that can do this (they support a number of Mandarin voices, one of which uses a Cantonese dialect; please also note that the "Taiwanese" voice listed is actually speaking Mandarin rather than the local Taiwanese dialect {which is not the same as Mandarin despite some misunderstanding by many foreigners that it is}):   SitePal - ...


2

On linux I use festival, where I can easily transform any line into speech (like cat text.txt > festival |tts. On Windows there used to be Microsoft Sam, nowadays called Microsoft Anna. This is a reasonably good text2speech service, unless you are willing to pay for a commercial variant. It should be installed on Windows 7 by default. Just open the Control ...


2

I imagine you're not old enough to remember PC Speaker sounds... intelligible speech and more was done with ONE bit per sample. All you really need is some method in indicating WHERE the speaker cone should be at any given time. With 2 bits per sample, as you showed, you get 4 positions. As long as you can MOVE the speaker cone ANY distance, you can ...


2

Speaking the punctuation is the norm. IIRC, there is a mode that will insert commas and periods automatically, but it's not enabled by default in the new v12.0.


2

Canta is free, hooks up to your mic, and gives you notes to sing and shows how close you are. Pretty similar to Rock Band vocals, but a little more sophisticated. http://www.singintune.org/ Some others are: http://www.singandsee.com/forsingers.php http://www.earpower.com/earpower.php


2

On Windows and Mac you can use the speech recognition software Dragon NaturallySpeaking (I'm writing this answer with it, as well as all my e-mails, reports, etc., even coding to some extent). On Linux there exist some programs tapping Google's voice technology but I haven't tried it myself.


2

You can go here to use Google's "Web Speech API Demonstration" -- it works very fast and well and in multiple languages: https://www.google.com/intl/en/chrome/demos/speech.html There's even a "Create Email" button! Update: I couldn't resist, so I wrote a Chrome extension that does exactly this. Try it out and let me know. :-)


2

Set up your home connection as a VPN then you will always be on your isp when you connect to the VPN.


1

Unless they're separate audio tracks in your video, not easily. What you'll probably have to do is extract the audio track from the video into a separate file, edit the audio file with a dedicated tool, then remux the result back into the video. The demux/remux part is easy. What's going to be difficult is attempting to isolate the background music. You'...



Only top voted, non community-wiki answers of a minimum length are eligible