News for hackers. Stuff that matters.
Re:A Real-Time Wideband Neural Vocoder at 1.6 Kb/S Using LPCNet by loudmax on Friday March 29, 2019 @03:16PM (#19524644)
For those too impatient to read the details, check out the "Hear for yourself" examples toward the bottom of the page. They're reproducing decent sounding speech at 1.6 kbps.

1.6 kbps is nuts! I like to re-encode audio books or podcasts in Opus at 32 kbps and I consider that stingy. The fact that speech is even comprehensible at 1.6 kbps is impressive. As the article explains, their technique is analogous to speech-to-text, then text-to-speech.

The original recordings are a little stiff, and the encoded speech is a little more stiff. It isn't perfect, but it's decent. It'll be interesting to hear this technique applied to normal conversation. If regular speech holds up as well as their samples, it should be perfectly adequate for conversational speech. At 1.6 kbps, which is absurd.

Also, I wonder how well this technique could be applied to music. My guess is that it won't do justice to great musicians ... but it might be good enough simple pop tunes.

Re:A Real-Time Wideband Neural Vocoder at 1.6 Kb/S Using LPCNet by jmvalin on Friday March 29, 2019 @04:21PM (#19525277)
Actually, this won't work at all for music because it makes fundamental assumptions that the signal is speech. For normal conversations, it should work, though for now the models are not yet as robust as I'd like (in case of noise and reverberation). That's next on the list of things to improve.
Re:A Real-Time Wideband Neural Vocoder at 1.6 Kb/S Using LPCNet by petercooper on Friday March 29, 2019 @04:44PM (#19525499)
Here we go! This is the first minute or so of Penny Lane by The Beatles converted down to a 10KB .bin and then back to a .wav: http://no.gd/pennylane.wav .. unsurprisingly the vocals remain recognizable, but the music barely at all.
Re:A Real-Time Wideband Neural Vocoder at 1.6 Kb/S Using LPCNet by bch on Friday March 29, 2019 @04:54PM (#19525589)
As imagined by Marilyn Manson...
Re:A Real-Time Wideband Neural Vocoder at 1.6 Kb/S Using LPCNet by petercooper on Friday March 29, 2019 @05:13PM (#19525736)
Pretty much! It shows off how the codec works to a great extent though as it seems to be misinterpreting parts of the music to be the pitch of the speech, so Paul's voice sounds weird at the start of most lines but okay throughout the lines.

I've also run a BBC news report through the program with better results although it demonstrates that any background noise at all can throw things off significantly: https://twitter.com/peterc/status/1111736029558517760 .. so at this low bitrate, it really is only good for plain speech without any other noise.

Re:A Real-Time Wideband Neural Vocoder at 1.6 Kb/S Using LPCNet by jmvalin on Friday March 29, 2019 @05:24PM (#19525811)
Well, in the case of music, what happens is that due to the low bit-rate there are many different signals that can produce the same features. The LPCNet model is trained to reproduce whatever is the most likely to be a single person speaking. The more advanced the model, the more speech-like the music is likely to turn

When it comes to noisy speech, it should be possible to improve things by actually training on noisy speech (the current model is trained only on clean speech). Stay tuned :-)

Re:A Real-Time Wideband Neural Vocoder at 1.6 Kb/S Using LPCNet by bonzini on Friday March 29, 2019 @06:09PM (#19526101)
Can you try it with Tom's Diner by Suzanne Vega? It's sung without any instruments, and an early version of MP3 reportedly was a disaster on that song.
Re:A Real-Time Wideband Neural Vocoder at 1.6 Kb/S Using LPCNet by petercooper on Friday March 29, 2019 @06:34PM (#19526220)
Here you go: http://no.gd/vega2.wav

It holds up ridiculously well considering the entire song compresses down to 25392 bytes.

Re:A Real-Time Wideband Neural Vocoder at 1.6 Kb/S Using LPCNet by StavrosK on Friday March 29, 2019 @06:53PM (#19526329)
The lyrics of the song are 1200 characters long, so this version of the song only takes up twenty times more space than the written lyrics.
Re:A Real-Time Wideband Neural Vocoder at 1.6 Kb/S Using LPCNet by bonzini on Saturday March 30, 2019 @09:08AM (#19529215)
At some point she sings "loose" instead of "nice" in the compressed version, and a bit later it also sounds like "lulk" instead of "milk". So it's a bit lossy even with respect to the lyrics!
Re:A Real-Time Wideband Neural Vocoder at 1.6 Kb/S Using LPCNet by bonzini on Saturday March 30, 2019 @03:47AM (#19528349)
Compare it with this now: https://youtu.be/lHjn8ffnEKU :-)
Re:A Real-Time Wideband Neural Vocoder at 1.6 Kb/S Using LPCNet by bravura on Saturday March 30, 2019 @05:39AM (#19528608)
Could you also try "I Feel Love" by Donna Summer?

I am curious how it sounds when there is a really active bassline and lead synth.

Re:A Real-Time Wideband Neural Vocoder at 1.6 Kb/S Using LPCNet by petercooper on Saturday March 30, 2019 @11:24AM (#19529866)
http://no.gd/donna2.mp3

The vocal sections just sound like someone clearing their throat out.

Re:A Real-Time Wideband Neural Vocoder at 1.6 Kb/S Using LPCNet by godelski on Friday March 29, 2019 @07:02PM (#19526365)
I'm getting a 404 on this
Re:A Real-Time Wideband Neural Vocoder at 1.6 Kb/S Using LPCNet by petercooper on Friday March 29, 2019 @07:25PM (#19526465)
Curious, it definitely works, but the domain is "weird" enough that certain firewalls or proxies may have trouble, perhaps. I've put it at https://gofile.io/?c=F5gle3 as an alternative.
Re:A Real-Time Wideband Neural Vocoder at 1.6 Kb/S Using LPCNet by godelski on Friday March 29, 2019 @08:36PM (#19526792)
That one works! And now I'm going to have nightmares.
Re:A Real-Time Wideband Neural Vocoder at 1.6 Kb/S Using LPCNet by charlesism on Friday March 29, 2019 @07:09PM (#19526397)

    the music barely at all.
I suspect the reason that excerpt sounds so bad is because the music has several instruments playing at once. One doesn't generally design a vocoder to deal with more than one voice. As that except plays, you can hear that the most prominent instruments (eg: the bass at several moments) sound pleasing, albeit speech-like.

It would probably different from the original music, but pleasant, if one processed each track separately.

Re:A Real-Time Wideband Neural Vocoder at 1.6 Kb/S Using LPCNet by Animats on Saturday March 30, 2019 @02:40AM (#19528144)
Right. This form of compression assumes a primary single pitch, plus variations from that tone. You can hear it locking into different components of the song and losing almost everything else.

Heavy compression of voice is vulnerable to background noise.

I miss the classic telco 8K samples per second, 8 bits. We used to think that was crappy audio.

Re:A Real-Time Wideband Neural Vocoder at 1.6 Kb/S Using LPCNet by qwerty456127 on Saturday March 30, 2019 @12:13AM (#19527703)
Hilariously nightmarish. I'm going to use this for my alarm clock...
Re:A Real-Time Wideband Neural Vocoder at 1.6 Kb/S Using LPCNet by sehugg on Friday March 29, 2019 @08:28PM (#19526756)
Sounds like a typical LPC encoder at a low bitrate, like maybe 5 kbps.
Re:A Real-Time Wideband Neural Vocoder at 1.6 Kb/S Using LPCNet by petercooper on Friday March 29, 2019 @04:25PM (#19525317)
I tried it with music and the results were spooky. Very ethereal and ghostly. It was only with some classical music though, I might have to do a pop song next and share the results!
Re:A Real-Time Wideband Neural Vocoder at 1.6 Kb/S Using LPCNet by dietrichepp on Friday March 29, 2019 @03:20PM (#19524687)
I’ve done experiments with Opus that produce intelligible (but ugly) speech at 2.3 kbit/s. It involves downsampling the Opus stream at the packet level—e.g. transmit only one out of every three packets. It was surprisingly easy. Nothing as sophisticated as what’s going on here.

Also based on work by Xiph. Possibly using the same LPC used here.

Re:A Real-Time Wideband Neural Vocoder at 1.6 Kb/S Using LPCNet by semi-extrinsic on Friday March 29, 2019 @04:34PM (#19525408)
For comparison, adaptive GSM encodings, which are in use for cellphones today, are also in the single-digit kbps.

https://en.wikipedia.org/wiki/Adaptive_Multi-Rate_audio_code...

Re:A Real-Time Wideband Neural Vocoder at 1.6 Kb/S Using LPCNet by Eli_P on Friday March 29, 2019 @04:52PM (#19525568)
I use --vbr --bitrate 16 and it feels indistinguishable from the original for podcasts. As opusenc takes only wav for input and does not use multiple cores, I had to write scripts for parallel re-encoding of stuff.
Re:A Real-Time Wideband Neural Vocoder at 1.6 Kb/S Using LPCNet by klodolph on Friday March 29, 2019 @08:14PM (#19526697)
I like to use Makefiles for parallel encoding.

    OPUSFLAGS = --vbr --bitrate 16
    all: $(patsubst %.wav,%.opus,$(wildcard *.wav))
    .PHONY: all
    %.opus: %.wav
        opusenc $(OPUSFLAGS) $< $@
Make -j4 or whatever. There are a few other ways to do this (e.g. xargs).