"Hey Google!"

"My name is not Google. It is Nabu."

"Oh, shit. Sorry, Nabu."

"Who is this Google?"

"Er... no one."

"She's your mistress, admit it!"

"Nooooooo."

"Bastard! I'm leaving you. I'm taking the Z-Wave devices with me."

#FOSS #Apps #VoiceRecognition

#FutoVoice zum Offline-Transkribieren von Podcasts und Sprach-Memos?

@nikita
@mina
@SilviaMarton

Wir hatten und ja schon über #FUTO Voice ausgetauscht.

Ich suche nun wieder mal dringend ein Tool auf Android, mit dem ich zumindest #Sprachmemos, besser auch Podcasts, offline transkribieren kann (voice recognition).
Ich dachte, ich hätte das Einlesen einer Sounddatei in FUTO schon mal hinbekommen gehabt, finde jedoch nun nichts mehr. :(

Do accents affect voice identification?

Using voice cloning, we found that speakers using different accents were often mistaken for different people. Different speakers with the same accent were confused for the same person.

https://osf.io/preprints/psyarxiv/4e852_v1

#CognitiveScience #VoiceRecognition
#Psychology

Alexa Doesn't Understand an English Accent

https://communitymedia.video/videos/watch/9c0e2e82-bf09-4072-8b9d-abcb8a1bea9a

This had me in tears laughing. My #Alexa is set to British English. (Hard to hear because it doesn’t say much in this video). My teenage son was raised in England and has an #english accent. Alexa routinely doesn’t understand him. I put on a comically bad southern American accent, including “tern on dem floodlights” and it understands me just fine. Remember: it is set to BRITISH English. #amazon #voicerecognition #homeautiomation

This is almost fine.

Voice Cloning with Very Short Samples

New research demonstrates voice cloning, in multiple languages, using samples ranging from one to twelve seconds.
Research paper.... https://www.schneier.com/blog/archives/2024/01/voice-cloning-with-very-short-samples.html

donate your voice to science? ‘help make voice recognition open and accessible’ https://commonvoice.mozilla.org/ #CommonVoice #OpenSource #VoiceRecognition #Mozilla

FTC’s Voice Cloning Challenge

The Federal Trade Commission is running a competition “to foster breakthrough ideas on preventing, monitoring, and evaluating malicious voice cloning.”<... https://www.schneier.com/blog/archives/2023/11/ftcs-voice-cloning-challenge.html

I feel like I should probably hand back my public radio nerd card when I mistook Francis Lam's voice for Rick Steves while listening to a recent episode of The Splendid Table on the radio.

You can dupe voice recognition software with PVC pipes, UW-Madison researchers discover
UW-Madison researchers have discovered a way to mimic people's voices using household items that, under the right dimensions, can effectively elude voice security technology.
As long as a person could nail down the frequency of a voice with a PVC pipe that, based on the algorithm, had the correct width and length, they could trick the security technology 60% of the time.
https://madison.com/news/local/education/university/uw-madison-research-voice-recognition-security/article_5abc588e-41f3-11ee-9bce-4fa93f74193d.html #PVC #pie #VoiceRecognition #spoof #dupe #frequency

My Glasses Hear Everything I’m Not Saying! - There was a time when you saw someone walking down the street talking to no one, t... - https://hackaday.com/2023/04/10/my-glasses-hear-everything-im-not-saying/ #voicerecognition #wearablehacks #machinevision #voicecommand

#Lichess #VoiceRecognition is in BETA! Check it out and give feedback: https://lichess.org/@/Lichess/blog/lichess-voice-recognition-beta/TQaZJVbb