Google WaveNet: Neural Network-generated Text-2-Speech

Gepostet vor 7 Monaten, 14 Tagen in #Tech #AI #AlgoCulture #Language

Share: Twitter Facebook Mail


Google hat seine Neural Networks auf Stimmerzeugung trainiert und ein neues Verfahren zur Synthetisierung von Sprache erfunden. Die Ergebnisse sind deutlich besser, als das, was man bisher von Text-2-Speech-Synthesis so kennt:

Die füttern ihr WaveNet mit Lautsprache, bis zu einer „echten“ Text-2-Speech-Anwendung fehlt also noch ein kleines Stück (und das Teil ist ohnehin eher… langsam: „it takes 90 minutes to synthesize one second of audio.“)

Interessant: Da die Algorithmen aber auch auf Audio-Samples trainiert sind, können sie auch einfach losreden ohne Text-Input und die Ergebnisse hier beinhalten dann auch „menschliche Spuren“ in der Kunst-Stimme, also Atmen, Lispeln und subtile Schmatzer:

Discover Mag: Google DeepMind’s WaveNet AI Sounds Human, Rocks the Piano
Technology Review: Face of a Robot, Voice of an Angel? – DeepMind’s use of neural networks to synthesize speech could finally make computers sound more human.

generating speech with computers — a process usually referred to as speech synthesis or text-to-speech (TTS) — is still largely based on so-called concatenative TTS, where a very large database of short speech fragments are recorded from a single speaker and then recombined to form complete utterances. This makes it difficult to modify the voice (for example switching to a different speaker, or altering the emphasis or emotion of their speech) without recording a whole new database.

This has led to a great demand for parametric TTS, where all the information required to generate the data is stored in the parameters of the model, and the contents and characteristics of the speech can be controlled via the inputs to the model. So far, however, parametric TTS has tended to sound less natural than concatenative, at least for syllabic languages such as English. Existing parametric models typically generate audio signals by passing their outputs through signal processing algorithms known as vocoders.

WaveNet changes this paradigm by directly modelling the raw waveform of the audio signal, one sample at a time. As well as yielding more natural-sounding speech, using raw waveforms means that WaveNet can model any kind of audio, including music. […]

Here are some samples from all three systems so you can listen and compare yourself:

[…] If we train the network without the text sequence, it still generates speech, but now it has to make up what to say. As you can hear from the samples below, this results in a kind of babbling, where real words are interspersed with made-up word-like sounds:

[…] By changing the speaker identity, we can use WaveNet to say the same thing in different voices:

[…] Since WaveNets can be used to model any audio signal, we thought it would also be fun to try to generate music. Unlike the TTS experiments, we didn’t condition the networks on an input sequence telling it what to play (such as a musical score); instead, we simply let it generate whatever it wanted to. When we trained it on a dataset of classical piano music, it produced fascinating samples like the ones below:

Neural Network cooks with Cthulhu

Janelle Shane spielt mit Neural Networks rum und hat eins davon auf Lovecraft trainiert. Dann hat sie das Neural Network…

Rogue Apostrophe Vigilante

Wie die Graffiti Grammar Police aus Ecuador, nur mit Deppen-Apostroph in Bristol. (via Martin)

Next Level, photorealistic Style-Transfer

In ihrem neuen Paper stellen Fujun Luan, Sylvain Paris, Eli Shechtman und Kavita Bala eine neue Style-Transfer-Methode vor: Figure 1:…

Blacked Out Censorship-Poetry Generator

Schöne Spielerei von Max Kreminski, ein JS-Droplet, das Websites in Blacked Out Poetry verwandelt, basierend auf Liza Dalys █ Blackout…

This Bot kills Fascists

So-So-Working-Object-Detection-Algorithm + Woodie Guthrie = Fascists.exe | „This bot kills fascists“.

„Alexa? Are you connected to the CIA?“

„I always try to tell the truth.“ This reminds me of those Guilty-Dog-Videos:

Palm Generator

Es sollte mehr entspannte Algorithmen mit Urlaubs-Attitüde geben wie den hier: „The Palm Generator is a Three.js module to create…

AI Brainscans

Graphcore aus Bristol visualisieren künstliche Intelligenzen und Neural Networks: Inside an AI 'brain' - What does machine learning look like?…

A Banana Keytar and more from Stupid Hackathon: Inverted Eyetracker-Pong, Robot Porn Addict or the Shitty Sharpie Tattoo Gun)

Ein weiterer Fav vom Stupid Hackathon NYC 2017, die Banana-Keytar von Amanda Lange. Auch geil: der Twitter-Bot Robot Porn Addiction,…

Fotorealistische Pics aus der Gameboy-Camera

Roland Meertens generiert fotorealistische Farbbilder aus den Pics der Gameboy-Camera: Creating photorealistic images with neural networks and a Gameboy Camera.…

The best Anagramm

Mark Dominus hat das beste Anagramm der englischen Sprache ausgerechnet. Dazu hat er die komplette Liste der Anagramme (der englischen…