Greta Tuckute
@gretatuckute.bsky.social
Studying language in biological brains and artificial ones at the Kempner Institute at Harvard University.
www.tuckute.com
www.tuckute.com
Reposted by Greta Tuckute
6/
We also wondered: if neuroscientists use functional localizers to map networks in the brain, could we do the same for MiCRo’s experts?
The answer: yes! The very same localizers successfully recovered the corresponding expert modules in our models!
We also wondered: if neuroscientists use functional localizers to map networks in the brain, could we do the same for MiCRo’s experts?
The answer: yes! The very same localizers successfully recovered the corresponding expert modules in our models!
October 20, 2025 at 12:10 PM
6/
We also wondered: if neuroscientists use functional localizers to map networks in the brain, could we do the same for MiCRo’s experts?
The answer: yes! The very same localizers successfully recovered the corresponding expert modules in our models!
We also wondered: if neuroscientists use functional localizers to map networks in the brain, could we do the same for MiCRo’s experts?
The answer: yes! The very same localizers successfully recovered the corresponding expert modules in our models!
We hope that AuriStream will serve as a task-performant model system for studying how language structure is learned from speech.
The Interspeech paper sets the stage—more work building on this idea coming soon! And as always, please feel free to get in touch with comments etc.!
The Interspeech paper sets the stage—more work building on this idea coming soon! And as always, please feel free to get in touch with comments etc.!
August 19, 2025 at 1:12 AM
We hope that AuriStream will serve as a task-performant model system for studying how language structure is learned from speech.
The Interspeech paper sets the stage—more work building on this idea coming soon! And as always, please feel free to get in touch with comments etc.!
The Interspeech paper sets the stage—more work building on this idea coming soon! And as always, please feel free to get in touch with comments etc.!
3️⃣ Temporally fine-grained → 5ms tokens preserve acoustic detail (e.g. speaker identity).
4️⃣ Unified → AuriStream learns strong speech representations and generates plausible continuations—bridging representation learning and sequence modeling in the audio domain.
4️⃣ Unified → AuriStream learns strong speech representations and generates plausible continuations—bridging representation learning and sequence modeling in the audio domain.
August 19, 2025 at 1:12 AM
3️⃣ Temporally fine-grained → 5ms tokens preserve acoustic detail (e.g. speaker identity).
4️⃣ Unified → AuriStream learns strong speech representations and generates plausible continuations—bridging representation learning and sequence modeling in the audio domain.
4️⃣ Unified → AuriStream learns strong speech representations and generates plausible continuations—bridging representation learning and sequence modeling in the audio domain.
4 key advantages of AuriStream:
1️⃣ Causal → allows the study of speech/language processing as it unfolds in real time.
2️⃣ Inspectable → predictions can naturally be decoded into the cochleagram/audio, enabling visualization and interpretation.
1️⃣ Causal → allows the study of speech/language processing as it unfolds in real time.
2️⃣ Inspectable → predictions can naturally be decoded into the cochleagram/audio, enabling visualization and interpretation.
August 19, 2025 at 1:12 AM
4 key advantages of AuriStream:
1️⃣ Causal → allows the study of speech/language processing as it unfolds in real time.
2️⃣ Inspectable → predictions can naturally be decoded into the cochleagram/audio, enabling visualization and interpretation.
1️⃣ Causal → allows the study of speech/language processing as it unfolds in real time.
2️⃣ Inspectable → predictions can naturally be decoded into the cochleagram/audio, enabling visualization and interpretation.