SSI, a very interesting name for a company advancing AI! "Solid State Intelligence" or SSI was also the name of the malevolent entity described in the biography of John C. Lilly [0][1]. It was a network of "computers" (computation-capable solid state systems) that was first engineered by humans and then developed into something autonomous.
Your friend can take a look at solutions from Acapela [0], SpeakUnique [1] or VOCALiD [2]. Not sure whether they have a solution for Android though.
I recently saw a video from google about a custom voice they created for somebody with ALS but I can't seem to find it online (Does anybody have a link?). Creating custom voices is not yet available on Android though. The latest iOS release (iOS 17) does support creating personalized voices.
ModelTalker [3] is a long-term (research?) project to create custom voices for people with speech disabilities. Their TTS seem to support Android so that might be another option.
Hi and thanks for the suggestions. Looking through them, it looks like you need to do what they call "voice banking" before you lose your voice. Basically reading a script they provide.
Unfortunately my friend's voice is too far gone for that to be possible. Hoping for something where they can use old recordings to generate a voice.
From my tests I think Audiobox from Meta is the most promising (even better than Eleven Labs) - too bad it's closed source and they force you to read some randomly generated sentences (to prevent the case of someone generating a cloned voice without consent).
Right now Eleven Labs is your best bet.
xTTS is just not there quality wise. The version available in the studio is marginally better than the OSS version but it's still pretty far from being believable.
The non-nerfed version of Tortoise (the author decided to ruin their own project but forks exist) was decent at voice cloning but it takes a lot of tries.
I'm pretty sure we already have the technology to do what you want and help your friend, it's just a matter of time until it gets better and more software comes out.
Some of the recent transformer models can work with audio clips just a few seconds long. I'm sure the final output is less good, but perhaps your friend has audio clips that would work for that from e.g. home movies.
Nice work! Interesting idea to combine an app with “real” books!
One of your challenges for your business model might be to ensure long-term engagement. Parents might be very interested in your product but might lose interest after a while, leading to high churn rate after a few months. How are you dealing with this? Any tips for other startups who are also selling to parents?
Your app reminds me of Google’s Read Along [0], which is also a reading tutor for young children which one of Google’s offline speech recognition systems (it seems they are currently using an RNN-T encoder-decoder architecture with wordpieces as the base unit). Too bad this app was not marketed properly and translated in many languages, a missed opportunity it seems!
Soapbox Labs [1] is providing a speech recognition API (also offline) for reading tutors and other apps. It might be cheaper to integrate their technology? I believe their ASR technology used to be based (or still is?) on the Kaldi speech recognition toolkit, that might ring a bell ;-)
Thanks for the comment! We find that if a parent actually uses the product, and it changes their child's relationship with reading, Ello is quite sticky. Our biggest issues with churn are related to cost of the product and activation (people cancelling without ever using it). In terms of advice: 1) talk to parents about their pain points and iterate again and again, 2) be aware that a product that increases "work" rather than easing it, that causes a lot of resistance and friction.
We took a look at read along - it seems to have fallen off. I think the biggest issue with read along was the approach to supporting kids (it just gave the words rather than coaching the child through decoding them) and the quality of the "books" (the stories weren't that engaging and the illustrations were simple). The quality of the story matters a lot.
We looked at soapbox but for a number of reasons, we want to build our own speech recognition technology and have the team to do it! There are some issues with the time is takes for soapbox to run as well as the accuracy of the model. Thanks again!
SQLCipher [1] seems to be missing from the list. It is a SQLite extension that encrypts/decrypts a SQLite database on the fly. Works quite well in my experience.
Also SEE (SQLite Encryption Edition) from the SQLite developers - a flat fee for a perpetual license. I bought it 13 years ago for HashBackup, works great, never had a problem.
My oldest son (4y) has also a rare genetic disorder (18q12.3q21.1 deletion). Part of the chromosome that is missing is the SETBP1 gene [1] and this deletion can result in developmental delay, reduced speech and motor skills, intellectual disability and other issues such as autism. My son’s speech for example is limited to simple consonant-vowel syllables. Dr. Angela Morgan, who is mentioned on the IDefine website, is also conducting research on the SETBP1 gene [2]. You can take a look at the website of the SETBP1 Society [3] to get some additional inspiration for your foundation. They are also raising funds to promote basic research and awareness.
Community building will be an important part of your foundation and parents. In our case, we joined the SETBP1 support group on Facebook. It is always heartwarming and comforting to read other peoples and to know that you are not the only one that is in a similar situation. The Facebook group keeps us also updated on recent scientific progress and we were able to join a research study on SETBP1.
I know that having a kid that is unable to communicate is hard. Very hard. When our son was younger he was sometimes very frustated because he could not express himself. But communication is more than speech. Our son is now mainly expressing himself with key word signing (in our case the Dutch variant SMOG) and his speech is gradually improving (at a very slow pace). I hope your daughter will also find a way to properly express herself.
[2] Morgan A, Braden R, Wong MMK, Colin E, Amor D, Liégeois F, Srivastava S, Vogel A, Bizaoui V, Ranguin K, Fisher SE, van Bon BW. Speech and language deficits are central to SETBP1 haploinsufficiency disorder. Eur J Hum Genet. 2021 Aug;29(8):1216-1225.
Just chiming in as my son too has an 18q deletion, albeit further towards the distal arm. Just to bring to your attention, if you were not already aware, of https://www.chromosome18eur.org and its parent organisation https://www.chromosome18.org.
Some great resources and there'll be folks who have experienced similar issues to you and yours.
Thank you. I recently read a little about Dr. Morgan's research as well. I hope she would take on KS kids as well for research.
I think my daughter started to show some level of frustration as well, but currently, we are like what they call "helicopter parents", whatever she seems to want, it's done immediately. My understanding is we will start to see more of the frustration in the future.
[0] https://en.wikipedia.org/wiki/John_C._Lilly
[1] http://johnclilly.com/