At #ICASSP2025? Drop by the Google booth today at 11:15 AM when Subhashini Venugopalan will present "Unlock Better Speech Recognition with Project Euphonia" — adding disordered speech to ASR model training improves recognition of disordered speech for better personalized models.
@googleai
-
Google Remote Sensing Foundation Models Trusted Tester Program
By
–
Learn about Geospatial Reasoning: https://
goo.gle/42jJVKK
Interested in testing the new remote sensing foundation models? Express your interest in the trusted tester program: https://
goo.gle/4j9hkir -
AI Applications for Public Health Climate and Commercial Optimization
By
–
What can this help achieve? Real-world applications include: Public Health: Understanding disease spread/optimizing interventions. Climate Resilience: Risk modeling /planning adaptation. Commercial Apps: Enhancing logistics, site selection, demand forecasting.
-
Google Announces Geospatial Reasoning with Generative AI Gemini
By
–
We just announced Geospatial Reasoning, a new research effort that will use generative AI (#Gemini) to help unlock novel insights about our world. Imagine asking complex Qs about our planet & getting detailed answers w/ plans & visuals! https://
goo.gle/3XOO5sF -
Geospatial Foundation Models for Satellite Imagery Analysis
By
–
Crucially, this reasoning will be grounded in real-world data. This is powered by specialized AI like our geospatial foundation models, including a new remote sensing model, which can help analyze satellite and aerial imagery.
-
Gemini Geospatial Reasoning: Advanced Natural Language Analysis
By
–
How will Geospatial Reasoning work? It will use Gemini's advanced reasoning to understand natural language questions. Then, it will intelligently plan & orchestrate analysis across diverse data — maps, socioeconomics, satellite images, even your own datasets!
-
Gemma LLM Speech Recognition and Disordered Speech at ICASSP2025
By
–
Today at 3:30 PM, Subhashini Venugopalan will be at the #ICASSP2025 Google booth to discuss how to enable the open source Gemma LLM to recognize speech and to act as an ASR model. She'll also discuss how Gemma can be trained using RL to understand disordered speech.
-
Google Researcher Wins IEEE Speech Audio Processing Award
By
–
Congratulations to Google Visiting Faculty Researcher Shrikanth Narayana for winning the 2025 IEEE James L. Flanagan Speech and Audio Processing Award! This award recognizes contributions to speech communication science and technologies for inclusive human-centered engineering.
-
Audio Algorithms Implementation on Edge Devices
By
–
Stop by the #ICASSP2025 Google booth today at 11:30 AM IST where Arpit Jain will present "Considerations for the Implementation of Audio Algorithms on Edge Devices", covering algorithmic computational complexity, memory use, & DSP/NPU architecture for algorithm implementation.
-
Unlocking AI’s Full Potential to Improve Global Human Health
By
–
Find out how we’re unlocking the full potential of AI to improve human health for everyone, everywhere.