Confident as I may be that OPs intentions are good and pure, a quick CTRL-F on the comment threads finds no references to “abuse” or “ethics”, and I propose that synthesis of voice raises issues for which society has few natural defenses.
Ask HN: My wife might lose the ability to speak in 3 weeks – how to prepare?
161–170 of 229 posts
Re: Ask HN: My wife might lose the ability to speak in 3 weeks – how to prepare?
#162Hey, speech ML researcher here. Make sure you have different recordings of different contexts. fifteen.ai's best TTS voices use ~90 min of utterances, some separated by emotion. If you're having her read a text, make sure it's engaging--we do a lot of unconscious voicing when reading aloud. Tbh, if she has a non-Anglophone accent, you're going to need more because the training data is biased towards UK/US speakers. I…
Make sure to get recording of true honest laughter of hers too
Depending on your desired level of hedging...
I would say also consider recording a variety of honest utterances of all kinds, situations, and emotions. Anger outbursts, apathetic grunts, sexual even if you so desire (hence throwaway account)... Please dont be offended by this, just thinking of all scenarios for you to decide for yourself...
Re: Ask HN: My wife might lose the ability to speak in 3 weeks – how to prepare?
#163Earlier quoted context omitted.
Also buy a (half) decent mic! They're much cheaper than you might expect.
Seconding this, it's worth a hundred or so for at least a Yeti or something, considering it's not like you'll get another chance to do this.
Also, in a similar vein as testing backups, make sure to test + listen to the recorded audio, if you can.
Re: Ask HN: My wife might lose the ability to speak in 3 weeks – how to prepare?
#164We get quite a few requests for this at Resemble ( https://resemble.ai ). We can get her to record right on our website or you can upload an existing file (along with a video of her consent) on the platform. Feel free to shoot me a message and I'd be happy to help build a voice for her.
Just FYI, your page keeps jumping on mobile as it renders and erases words. Not a good experience if I'm trying to read.
Re: Ask HN: My wife might lose the ability to speak in 3 weeks – how to prepare?
#165I have a progressive neurodegenerative disease and lost most my ability to speak about 3 years ago. What you are proposing is super cool, but you might be overthinking this. These things (text to speech, etc) are more awkward than practical in real life. Also, make sure your wife is completely on board. Seeing old clips and hearing my voice is actually kind of depressing to me. Here is my actual advice: Outside of so…
How do you communicate with your wife?
Did you ever consider learning sign language?
Re: Ask HN: My wife might lose the ability to speak in 3 weeks – how to prepare?
#166Earlier quoted context omitted.
Much of the work in speech synthesis has been about closing the gap in vocoders, which take a generated spectrogram and output a waveform. There's a clear gap between practical online implementations and computational behemoths like WaveNet. As you implied it's hard to quantitatively judge which result is better, papers usually use surveys to judge. Here's a recent work that has a good comparison of some vocoders: ht…
WaveRNN (and even slimmer versions, like LPCNet) are great, and run for a tiny fraction of the compute of the original WaveNet. Pruning is also a good way to reduce model sizes. I'm not sure what's up with the WaveGLOW (17.1M) example in the linked wavenode comparison... The base WaveGLOW sounds reasonable, though. They're also using all female voices, which strikes me as dodgy; lower male voice pitch tracking is oft…
Agreed. I didn't have a better comparison at hand.
I'm looking at you GAN papers.
Re: Ask HN: My wife might lose the ability to speak in 3 weeks – how to prepare?
#167Hey, speech ML researcher here. Make sure you have different recordings of different contexts. fifteen.ai's best TTS voices use ~90 min of utterances, some separated by emotion. If you're having her read a text, make sure it's engaging--we do a lot of unconscious voicing when reading aloud. Tbh, if she has a non-Anglophone accent, you're going to need more because the training data is biased towards UK/US speakers. I…
I have an open source web service for rapidly recording lots of text prompts to flac: https://speech.talonvoice.com (right now the live site prompts for single words because I’m trying to build single word training data, but the prompts can be any length)
You can set it up yourself with a bit of Python knowledge from this branch: https://github.com/talonvoice/noise/tree/speech-dataset
There are keyboard shortcuts - up/down/space to move through the list and record quickly.
If you want to use it on arbitrary text prompts, you can modify this function to return each line from a text file: https://github.com/talonvoice/noise/blob/speech-dataset/serv...
If you use this, before recording too much, do some test recordings and make sure they sound ok. Web audio can be unreliable in some browsers.
The uploaded files are named after the short name, so make sure you can correspond the short name with the original text prompts, eg with string_to_shortname().
If you aren’t easily able to do this yourself, I’d be happy to spin up an instance of it for you with text prompts of your choosing.
Re: Ask HN: My wife might lose the ability to speak in 3 weeks – how to prepare?
#168I don't really have anything to add to all the helpful comments under your thread. Do the preparation as much as you can, as long as your wife also wants this.
You said there is a small chance, so I really wish you and your wife the best of luck that she and her voice will be fine after the surgery.
Re: Ask HN: My wife might lose the ability to speak in 3 weeks – how to prepare?
#169Earlier quoted context omitted.
I work in pathological speech processing/synthesis so I'm unfortunately familiar with your father's position. It really sucks that these people didn't know that archiving their voice would've been useful. I hear snippets that people manage to glean from family videos right after listening to their current voices and it makes me really sad. On the upside, your father can choose any celebrity he wants to voice him! Ton…
Are there any simple howtos anywhere which describes the process in as simple terms as possible? Without knowing the cool toolkits du jour. Something like: - Download these texts - Record in WAV at least 48 kHz - Record each line in a separate file. - Do 3 takes of each line: flat, happy, despair Maybe even a minimal set and a full set depending on how much effort you are willing to put in. A plain description on how…
Not really, this is the only thing I know of in terms of collection: https://www.isca-speech.org/archive/Interspeech_2018/pdfs/24... Usually you're basing your recipe off of those for existing datasets (TIMIT, WSJ, LibriSpeech, etc).
Re: Ask HN: My wife might lose the ability to speak in 3 weeks – how to prepare?
#170You need to do voice banking. It is imperative that you do so, so that your wife keeps her identity no matter what.
What you need to do is spend the entire next 3 weeks doing voice banking. This will give your wife a text-to-speech voice (SAPI 5 voice, or others, for example). You record phrases that the voice banking service wants you to speak, with a high quality headset (best if wired) in a quiet setting.
The more sentences (samples) you have, the better the voice will be, obviously. But, there are services out there that will update the recordings, as the technology gets better, and that is the way to go, in terms of choosing the "best service".
The voice banking services that people typically use are here: https://www.mndassociation.org/professionals/management-of-m...
I would say that Acapela my-own-voice is currently the best technology. Obviously there are open source technologies, but you do not have the luxury of time to figure all of that out. However, you should do your own voice banking for later post-processing on your own with open source stuff.
There is also a free version of voice banking available, but I would only recommend it as a secondary tool: https://www.modeltalker.org/
This app (iOS and Android) for example, allows you to use your personal voice banked text-to-speech voice, to talk: https://therapy-box.co.uk/predictable
This is another great app that allows you to use your personal voice banked text-to-speech voice: https://www.assistiveware.com/products/proloquo4text
Source: Disabled engineering student, who is extremely interested in assistive technology. I would love to be a rehabilitation engineer.