Video wird geladen...
Video konnte nicht geladen werden
Discover how Google Research is working to extend speech, translation, and language processing technologies to the 1,000 most spoken languages in the world in this lightning talk hosted by Uche Okonkwo and Sandy Ritchie at Research@ NYC →
116,957 Aufrufe • vor 2 Jahren •via X (Twitter)
9 Kommentare
Google translate but live and has a voice
What's the point from all of this if you're keeping the assistant voice typing to Pixels only?! Moreover, your phones are not available in all countries! Please offer the robust voice typing dictation to other Androids especially those with flagship CPUs🙏
Did you know companies like @lumentechco target and fire pregnant employees?
Language like a form to transform societies.
Fix finnish language
I love this because I see light in the future of AI.
No coincidences I've called the 2020's the era of creative distinction using below quote as a point of reference, inspiration and direction. "ChatGPT uses natural language processing to create a humanlike conversational dialogue which then adds value at speed. In this era of creative distinction, as a leader, what language are you using that causes your conversations to become disruptive and value-driven, at speed?" ~ @Onyianyado777 #AI #ChatGPT #ArtificialIntelligence #Disruption #Leadership #GoogleAI
Hopefully better support and less neglection of African languages
@sundarpichai #GoogleAI is really NOT workg 2 Empower #PersonsWithDisabilities, ONLY Lip Service. NOT using AI to develop #AIpoweredSmartGlass 2 #AssistBlindsMobility #AIpoweredArtificialRetina for #BlindToSee @narendramodi @NamoApp #1/4thOfWorld'sBlindInIndia @AshwiniVaishnaw
![Google presents AudioPaLM: A Large Language Model That Can Speak and Listen paper page: introduce AudioPaLM, a large language model for speech understanding and generation. AudioPaLM fuses text-based and speech-based language models, PaLM-2 [Anil et al., 2023] and AudioLM [Borsos et al., 2022], into a unified multimodal architecture that can process and generate text and speech with applications including speech recognition and speech-to-speech translation. AudioPaLM inherits the capability to preserve paralinguistic information such as speaker identity and intonation from AudioLM and the linguistic knowledge present only in text large language models such as PaLM-2. We demonstrate that initializing AudioPaLM with the weights of a text-only large language model improves speech processing, successfully leveraging the larger quantity of text training data used in pretraining to assist with the speech tasks. The resulting model significantly outperforms existing systems for speech translation tasks and has the ability to perform zero-shot speech-to-text translation for many languages for which input/target language combinations were not seen in training. AudioPaLM also demonstrates features of audio language models, such as transferring a voice across languages based on a short spoken prompt.](https://image.24vids.com/tw-1672048076469698561/ext_tw_video_thumb/1672047839378300928/pu/img/MuoOBsAyUd-HAI7D.jpg)
