Digital sound-alikes - Revision history

Juho Kunsola: linking to the Stop-Synthetic-Filth.org for most recent information

2021-02-02T17:17:56Z

linking to the Stop-Synthetic-Filth.org for most recent information

← Older revision		Revision as of 17:17, 2 February 2021
Line 1:		Line 1:
			<center><big>Latest version of this article can be found in [https://stop-synthetic-filth.org/wiki/Synthetic_human-like_fakes#Digital_sound-alikes '''Synthetic human-like fakes''' § '''Digital sound-alikes''' at the stop-synthetic-filth.org wiki]</big></center>

	When it cannot be determined by human testing whether some fake voice is a synthetic fake of some person's voice, or is it an actual recording made of that person's actual real voice, it is a '''digital sound-alike'''.		When it cannot be determined by human testing whether some fake voice is a synthetic fake of some person's voice, or is it an actual recording made of that person's actual real voice, it is a '''digital sound-alike'''.

Juho Kunsola: work on the formulation of the definition

2019-11-26T18:17:22Z

work on the formulation of the definition

← Older revision		Revision as of 18:17, 26 November 2019
Line 1:		Line 1:
	When it cannot be determined by human testing, is ~~some synthesized recording~~ a ~~simulation~~ of some person's ~~speech~~, or is it a recording made of that person's actual real voice, it is a '''digital sound-alike'''.		When it cannot be determined by human testing whether some fake voice is a synthetic fake of some person's voice, or is it an actual recording made of that person's actual real voice, it is a '''digital sound-alike'''.

Juho Kunsola: /* Timeline of digital sound-alikes */ + In 2018 Conference on Neural Information Processing Systems the work 'Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis'

2019-11-26T14:14:21Z

Timeline of digital sound-alikes: + In 2018 Conference on Neural Information Processing Systems the work 'Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis'

← Older revision		Revision as of 14:14, 26 November 2019
Line 8:		Line 8:
	== Timeline of digital sound-alikes ==		== Timeline of digital sound-alikes ==
	* In '''2016''' [[w:Adobe Inc.]]'s [[w:Adobe Voco\|Voco]], an unreleased prototype, was publicly demonstrated in 2016. ([https://www.youtube.com/watch?v=I3l4XLZ59iw&t=5s View and listen to Adobe MAX 2016 presentation of Voco])		* In '''2016''' [[w:Adobe Inc.]]'s [[w:Adobe Voco\|Voco]], an unreleased prototype, was publicly demonstrated in 2016. ([https://www.youtube.com/watch?v=I3l4XLZ59iw&t=5s View and listen to Adobe MAX 2016 presentation of Voco])

	* In '''2016''' [[w:DeepMind]]'s [[w:WaveNet]] owned by [[w:Google]] also demonstrated ability to steal people's voices		* In '''2016''' [[w:DeepMind]]'s [[w:WaveNet]] owned by [[w:Google]] also demonstrated ability to steal people's voices

			* In '''2018''' [[w:Conference on Neural Information Processing Systems\|Conference on Neural Information Processing Systems]] the work [http://papers.nips.cc/paper/7700-transfer-learning-from-speaker-verification-to-multispeaker-text-to-speech-synthesis 'Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis'] ([https://arxiv.org/abs/1806.04558 at arXiv.org]) was presented. The pre-trained model is able to steal voices from a sample of only '''5 seconds''' with almost convincing results
			** Listen [https://google.github.io/tacotron/publications/speaker_adaptation/ 'Audio samples from "Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis"']
			** View [https://www.youtube.com/watch?v=0sR1rU3gLzQ Video summary of the work at YouTube: 'This AI Clones Your Voice After Listening for 5 Seconds']

	* As of '''2019''' Symantec research knows of 3 cases where digital sound-alike technology '''has been used for crimes'''.<ref name="WaPo2019">		* As of '''2019''' Symantec research knows of 3 cases where digital sound-alike technology '''has been used for crimes'''.<ref name="WaPo2019">
	https://www.washingtonpost.com/technology/2019/09/04/an-artificial-intelligence-first-voice-mimicking-software-reportedly-used-major-theft/</ref>		https://www.washingtonpost.com/technology/2019/09/04/an-artificial-intelligence-first-voice-mimicking-software-reportedly-used-major-theft/</ref>

Juho Kunsola: starting on == Timeline of digital sound-alikes ==

2019-11-26T14:05:46Z

starting on == Timeline of digital sound-alikes ==

← Older revision		Revision as of 14:05, 26 November 2019
Line 1:		Line 1:
	When it cannot be determined by human testing, is some synthesized recording a simulation of some person's speech, or is it a recording made of that person's actual real voice, it is a '''digital sound-alike'''.		When it cannot be determined by human testing, is some synthesized recording a simulation of some person's speech, or is it a recording made of that person's actual real voice, it is a '''digital sound-alike'''.

	~~As of '''2019''' Symantec research knows of 3 cases where digital sound-alike technology '''has been used for crimes'''.<ref name="WaPo2019">~~
	~~https://www.washingtonpost.com/technology/2019/09/04/an-artificial-intelligence-first-voice-mimicking-software-reportedly-used-major-theft/</ref>~~

	Living people can defend¹ themselves against digital sound-alike by denying the things the digital sound-alike says if they are presented to the target, but dead people cannot. Digital sound-alikes offer criminals new disinformation attack vectors and wreak havoc on provability.		Living people can defend¹ themselves against digital sound-alike by denying the things the digital sound-alike says if they are presented to the target, but dead people cannot. Digital sound-alikes offer criminals new disinformation attack vectors and wreak havoc on provability.
Line 8:		Line 6:
	[[File:Spectrogram-19thC.png\|thumb\|right\|640px\|A [[w:spectrogram\|spectrogram]] of a male voice saying 'nineteenth century']]		[[File:Spectrogram-19thC.png\|thumb\|right\|640px\|A [[w:spectrogram\|spectrogram]] of a male voice saying 'nineteenth century']]
	----		----
			== Timeline of digital sound-alikes ==
			* In '''2016''' [[w:Adobe Inc.]]'s [[w:Adobe Voco\|Voco]], an unreleased prototype, was publicly demonstrated in 2016. ([https://www.youtube.com/watch?v=I3l4XLZ59iw&t=5s View and listen to Adobe MAX 2016 presentation of Voco])
			* In '''2016''' [[w:DeepMind]]'s [[w:WaveNet]] owned by [[w:Google]] also demonstrated ability to steal people's voices
			* As of '''2019''' Symantec research knows of 3 cases where digital sound-alike technology '''has been used for crimes'''.<ref name="WaPo2019">
			https://www.washingtonpost.com/technology/2019/09/04/an-artificial-intelligence-first-voice-mimicking-software-reportedly-used-major-theft/</ref>

	~~== Examples of speech synthesis software capable to make a digital sound~~-~~alikes ==~~		----
	* [[w:Adobe Inc.]]'s [[w:Adobe Voco\|Voco]] unreleased prototype publicly demonstrated in 2016. ([https://www.youtube.com/watch?v=I3l4XLZ59iw&t=5s View and listen to Adobe MAX 2016 presentation of Voco)]
	* [[w:DeepMind]]'s [[w:WaveNet]] that was acquired by [[w:Google]] in 2014

	~~Neither of these software are available to the masses at large according to the "official truth", but as is known software has a high tendency to get pirated very quickly.~~

	~~----~~
	== Examples of speech synthesis software not quite able to fool a human yet ==		== Examples of speech synthesis software not quite able to fool a human yet ==
	Some other contenders to create digital sound-alikes are though, as of 2019, their speech synthesis in most use scenarios does not yet fool a human because the results contain tell tale signs that give it away as a speech synthesizer.		Some other contenders to create digital sound-alikes are though, as of 2019, their speech synthesis in most use scenarios does not yet fool a human because the results contain tell tale signs that give it away as a speech synthesizer.

Juho Kunsola: + A picture of a w:spectrogram| of a male voice saying 'nineteenth century'

2019-11-21T17:05:46Z

+ A picture of a w:spectrogram of a male voice saying 'nineteenth century'

← Older revision		Revision as of 17:05, 21 November 2019
Line 6:		Line 6:
	Living people can defend¹ themselves against digital sound-alike by denying the things the digital sound-alike says if they are presented to the target, but dead people cannot. Digital sound-alikes offer criminals new disinformation attack vectors and wreak havoc on provability.		Living people can defend¹ themselves against digital sound-alike by denying the things the digital sound-alike says if they are presented to the target, but dead people cannot. Digital sound-alikes offer criminals new disinformation attack vectors and wreak havoc on provability.

			[[File:Spectrogram-19thC.png\|thumb\|right\|640px\|A [[w:spectrogram\|spectrogram]] of a male voice saying 'nineteenth century']]
	----		----

Juho Kunsola: move the actually realized crimes up

2019-11-21T15:44:11Z

move the actually realized crimes up

← Older revision		Revision as of 15:44, 21 November 2019
Line 21:		Line 21:
	* '''[https://candyvoice.com/ CandyVoice.com]''' [https://candyvoice.com/demos/voice-conversion (test with your choice of text)]		* '''[https://candyvoice.com/ CandyVoice.com]''' [https://candyvoice.com/demos/voice-conversion (test with your choice of text)]
	* '''[https://cstr-edinburgh.github.io/merlin/ Merlin]''', a [[w:neural network]] based speech synthesis system by the Centre for Speech Technology Research at the [[w:University of Edinburgh]]		* '''[https://cstr-edinburgh.github.io/merlin/ Merlin]''', a [[w:neural network]] based speech synthesis system by the Centre for Speech Technology Research at the [[w:University of Edinburgh]]


			== Documented digital sound-alike attacks ==
			* [https://www.washingtonpost.com/technology/2019/09/04/an-artificial-intelligence-first-voice-mimicking-software-reportedly-used-major-theft/?noredirect=on 'An artificial-intelligence first: Voice-mimicking software reportedly used in a major theft'], a 2019 Washington Post article

			----

	== Example of a hypothetical digital sound-alike attack ==		== Example of a hypothetical digital sound-alike attack ==
Line 33:		Line 39:

	Thus it is high time to act and to '''[[Law proposals to ban covert modeling\|criminalize the covert modeling of human appearance and voice!]]'''		Thus it is high time to act and to '''[[Law proposals to ban covert modeling\|criminalize the covert modeling of human appearance and voice!]]'''
	~~----~~

	~~== Documented digital sound-alike attacks ==~~
	* [https://www.washingtonpost.com/technology/2019/09/04/an-artificial-intelligence-first-voice-mimicking-software-reportedly-used-major-theft/?noredirect=on 'An artificial-intelligence first: Voice-mimicking software reportedly used in a major theft'], a 2019 Washington Post article

	----		----

Juho Kunsola: Changed a heading to == Example of a hypothetical digital sound-alike attack ==

2019-10-13T13:45:57Z

Changed a heading to == Example of a hypothetical digital sound-alike attack ==

← Older revision		Revision as of 13:45, 13 October 2019
Line 22:		Line 22:
	* '''[https://cstr-edinburgh.github.io/merlin/ Merlin]''', a [[w:neural network]] based speech synthesis system by the Centre for Speech Technology Research at the [[w:University of Edinburgh]]		* '''[https://cstr-edinburgh.github.io/merlin/ Merlin]''', a [[w:neural network]] based speech synthesis system by the Centre for Speech Technology Research at the [[w:University of Edinburgh]]

	== Example of a digital sound-alike attack ==		== Example of a hypothetical digital sound-alike attack ==
	A very simple example of a digital sound-alike attack is as follows:		A very simple example of a digital sound-alike attack is as follows:

Juho Kunsola: just the URL in ref

2019-09-09T15:37:10Z

just the URL in ref

← Older revision		Revision as of 15:37, 9 September 2019
Line 2:		Line 2:

	As of '''2019''' Symantec research knows of 3 cases where digital sound-alike technology '''has been used for crimes'''.<ref name="WaPo2019">		As of '''2019''' Symantec research knows of 3 cases where digital sound-alike technology '''has been used for crimes'''.<ref name="WaPo2019">
	~~{{cite web~~		https://www.washingtonpost.com/technology/2019/09/04/an-artificial-intelligence-first-voice-mimicking-software-reportedly-used-major-theft/</ref>
	~~\|url=~~ https://www.washingtonpost.com/technology/2019/09/04/an-artificial-intelligence-first-voice-mimicking-software-reportedly-used-major-theft/
	~~\|title= An artificial-intelligence first: Voice-mimicking software reportedly used in a major theft~~
	~~\|last= Drew~~
	~~\|first= Harwell~~
	~~\|date= 2019-09-04~~
	~~\|website=~~
	~~\|publisher=~~
	~~\|access-date= 2019-09-089~~
	~~\|quote= }}~~
	</ref>

	Living people can defend¹ themselves against digital sound-alike by denying the things the digital sound-alike says if they are presented to the target, but dead people cannot. Digital sound-alikes offer criminals new disinformation attack vectors and wreak havoc on provability.		Living people can defend¹ themselves against digital sound-alike by denying the things the digital sound-alike says if they are presented to the target, but dead people cannot. Digital sound-alikes offer criminals new disinformation attack vectors and wreak havoc on provability.

Juho Kunsola: + As of 2019 Symantec research knows of 3 cases where digital sound-alike technology has been used for crimes +

2019-09-09T15:28:42Z

+ As of 2019 Symantec research knows of 3 cases where digital sound-alike technology has been used for crimes + <ref name="WaPo2019">

← Older revision		Revision as of 15:28, 9 September 2019
Line 1:		Line 1:
	When it cannot be determined by human testing, is some synthesized recording a simulation of some person's speech, or is it a recording made of that person's actual real voice, it is a '''digital sound-alike'''.		When it cannot be determined by human testing, is some synthesized recording a simulation of some person's speech, or is it a recording made of that person's actual real voice, it is a '''digital sound-alike'''.

			As of '''2019''' Symantec research knows of 3 cases where digital sound-alike technology '''has been used for crimes'''.<ref name="WaPo2019">
			{{cite web
			\|url= https://www.washingtonpost.com/technology/2019/09/04/an-artificial-intelligence-first-voice-mimicking-software-reportedly-used-major-theft/
			\|title= An artificial-intelligence first: Voice-mimicking software reportedly used in a major theft
			\|last= Drew
			\|first= Harwell
			\|date= 2019-09-04
			\|website=
			\|publisher=
			\|access-date= 2019-09-089
			\|quote= }}
			</ref>

	Living people can defend¹ themselves against digital sound-alike by denying the things the digital sound-alike says if they are presented to the target, but dead people cannot. Digital sound-alikes offer criminals new disinformation attack vectors and wreak havoc on provability.		Living people can defend¹ themselves against digital sound-alike by denying the things the digital sound-alike says if they are presented to the target, but dead people cannot. Digital sound-alikes offer criminals new disinformation attack vectors and wreak havoc on provability.

Juho Kunsola: + == Documented digital sound-alike attacks == + 'An artificial-intelligence first: Voice-mimicking software reportedly used in a major theft', a 2019 Washington Post article

2019-09-05T07:10:21Z

+ == Documented digital sound-alike attacks == + 'An artificial-intelligence first: Voice-mimicking software reportedly used in a major theft', a 2019 Washington Post article

← Older revision		Revision as of 07:10, 5 September 2019
Line 30:		Line 30:

	Thus it is high time to act and to '''[[Law proposals to ban covert modeling\|criminalize the covert modeling of human appearance and voice!]]'''		Thus it is high time to act and to '''[[Law proposals to ban covert modeling\|criminalize the covert modeling of human appearance and voice!]]'''
			----

			== Documented digital sound-alike attacks ==
			* [https://www.washingtonpost.com/technology/2019/09/04/an-artificial-intelligence-first-voice-mimicking-software-reportedly-used-major-theft/?noredirect=on 'An artificial-intelligence first: Voice-mimicking software reportedly used in a major theft'], a 2019 Washington Post article

	----		----