#wavenet

[technologictr]

'İnsan sesinin gerçekçi taklidi korkunç ve yanlış'

Google, geliştirdiği yapay zekalı sohbet programı Duplex’in iletişime geçeceği kullanıcıların, karşılarındakinin insan değil yapay zeka programı olduğu konusunda uyarılacağını açıkladı.

Duplex’in konuşma yetenekleri bu hafta Google I/O geliştirici konferansında sergilenmiş, görüşmede bir kullanıcının berberden randevu alması sağlanmıştı.

Duplex konuşma sırasında insanları yaptığı gibi duraksıyor,…

View On WordPress

[bytetrending]

WaveNet for EEG Analysis

Image request: A split image: one side shows an overwhelmed neurologist surrounded by stacks of paper EEGs, the other side showcases a sleek visualization of a WaveNet neural network processing EEG data in real-time. Style: futuristic, clean, emphasizing contrast between old and new methods. Color palette: cool blues and greens against warm yellows/oranges to highlight the shift. Imagine spending…

WaveNet for EEG Analysis

[ajhalthor]

Tacotron 2 - THE BEST TEXT TO SPEECH AI YET!

[suprimatec]

Conheça as pessoas que foram feitas por inteligência artificial

Conheça as pessoas que foram feitas por inteligência artificial

EM RESUMO: A fabricante de chips NVIDIA desenvolveu uma inteligência artificial que produz imagens altamente detalhadas de rostos de aparência humana, mas as pessoas retratadas aqui na verdade não existem. O sistema é o último exemplo de como a IA está desfocando a linha entre o “real” e o fabricado.

Melhor do que Doodles do Google

De volta em junho, um gerador de imagens que poderia transformar…

View On WordPress

[chatbotsworld]

WaveNet: A Generative Model for Raw Audio | DeepMind

This post presents WaveNet, a deep generative model of raw audio waveforms. We show that WaveNets are able to generate speech which mimics any human voice and which sounds more natural than the best existing Text-to-Speech systems, reducing the gap with human performance by over 50%. We also demonstrate that the same network can be used to synthesize other audio signals such as music, and present some striking samples of automatically generated piano pieces.

“WaveNets are able to generate speech which mimics any human voice and which sounds more natural than the best existing Text-to-Speech systems, reducing the gap with human performance by over 50%.”

Pretty scary, pretty exciting... it’s always a bit half and half or conflicting, when it comes to AI in its early days.

[kreuzaderny]

A machine learning system was tasked with learning what makes a person's voice unique, then generating audio of that quality.

[letgodbeyourgardener]

using artificial neural nets to analyze and model raw sound

The deep mind team have been working on something called WaveNet, and published their results about a month ago. It’s a new method for using convolutional neural networks to model raw audio, sample by sample. It’s pretty crazy to me that it’s possible to get that granular and still walk away with meaningful data, but convolutional neural networks are also used to analyze and model the deep mind pictures pixel by pixel.

https://deepmind.com/blog/wavenet-generative-model-raw-audio/

I think I’m having trouble breaking out of this algorithmic way of thinking. When you get so granular that you’re looking at individual samples in a waveform or individual pixels and color channels in an image, it seems intuitively impossible to get back to any kind of meaningful big picture. It seems like a contradiction to me but that basic idea is the foundation of how these convolutional networks work.

They have maybe 10 or 20 layers of neurons, and slowly build in abstraction as they go along. The first layer deals with regions around individual samples or individual color channels on pixels, basically the most granular and raw interpretation of the data. Then those neurons are pooled together and the next layer deals with the maximal elements of those pools, then those neurons are pooled, and so on until we reach a high level of abstraction. Each successive layer takes the most significant features of the previous layer and builds further connections, which is what allows the model to go from looking at contrast in small regions of pixels to identifying lines, then from identifying lines to detecting outlines and closed regions, and so on until a meaningful concept of what a feature actually is emerges on the other side.

I have no real way of visualizing this or wrapping my head around this concept. I’d like to write a convolutional network myself so I can peel it apart layer by layer and figure out what’s going on, but that feels a little inaccessible to me right now. Networks like this could probably write some interesting music with the right training. There’s a small sample of that toward the end of their blog post.

[geratura]

“Remember, these are evolutionary amoebas, toddlers just learning to babble. The amazing thing is that without being given any syntax rules, they are speaking, generating a kind of prototypical glossolalia poem, character by character. Note: models are like wines, idiosyncratic reservoirs, the output of each has a distinct taste, — some have mastered open lines, others mutter densely, many mangle words to make neologisms  — each has obsessions. The Wavenet algorithm is analogous to a winery: its processes ensure that all of the models are similar. Tensorflow is the local region; recursive neural nets form the ecosystem. The corpus is the grapes.“