Maureen de Seyssel
@maureendeseyssel.bsky.social
machine learning researcher @Apple | PhD from @CoML_ENS | speech, ml and cognition.
⚠️ Correction: The tutorial is on August 17th (not September 21)
May 28, 2025 at 8:45 AM
⚠️ Correction: The tutorial is on August 17th (not September 21)
We’ll show how bridging speech processing and psycholinguistics benefits both fields, and why speech researchers (you!) should care.
Collab. between ENS/Meta (Emmanuel Dupoux), Tampere University (Okko Räsänen) and Apple (me).
Hope to see many of you on September 21!
(2/2)
Collab. between ENS/Meta (Emmanuel Dupoux), Tampere University (Okko Räsänen) and Apple (me).
Hope to see many of you on September 21!
(2/2)
May 27, 2025 at 4:14 PM
We’ll show how bridging speech processing and psycholinguistics benefits both fields, and why speech researchers (you!) should care.
Collab. between ENS/Meta (Emmanuel Dupoux), Tampere University (Okko Räsänen) and Apple (me).
Hope to see many of you on September 21!
(2/2)
Collab. between ENS/Meta (Emmanuel Dupoux), Tampere University (Okko Räsänen) and Apple (me).
Hope to see many of you on September 21!
(2/2)
In this work, we investigate whether learning statistical regularities in speech supports word learning, and find that while people can detect these regularities, they rarely remember the words; suggesting a dissociation between pattern learning and memory. 🧠
Check it out!
Check it out!
April 22, 2025 at 5:31 PM
In this work, we investigate whether learning statistical regularities in speech supports word learning, and find that while people can detect these regularities, they rarely remember the words; suggesting a dissociation between pattern learning and memory. 🧠
Check it out!
Check it out!
This work was primarily carried out by
Ansgar Endress, who also gave me my first taste of research, of cognition, and even introduced me to programming. Couldn't have asked for a better introduction!
Ansgar Endress, who also gave me my first taste of research, of cognition, and even introduced me to programming. Couldn't have asked for a better introduction!
April 22, 2025 at 5:31 PM
This work was primarily carried out by
Ansgar Endress, who also gave me my first taste of research, of cognition, and even introduced me to programming. Couldn't have asked for a better introduction!
Ansgar Endress, who also gave me my first taste of research, of cognition, and even introduced me to programming. Couldn't have asked for a better introduction!
🥳 A huge thank you to all of our co-authors @hadware.bsky.social, @acristia.bsky.social, @hbredin.bsky.social, Guillaume Wisnewski & Emmanuel Dupoux, and of course to a larger extent to everyone in the CoML team!
🧵7/7
🧵7/7
January 8, 2025 at 4:47 PM
🥳 A huge thank you to all of our co-authors @hadware.bsky.social, @acristia.bsky.social, @hbredin.bsky.social, Guillaume Wisnewski & Emmanuel Dupoux, and of course to a larger extent to everyone in the CoML team!
🧵7/7
🧵7/7
💡 Finally, we aim to illustrate with this research how advanced computational models can simulate broad and realistic language learning, and as such help advance psycholinguistic research.
For a theoretical take, check our other paper ⬇
📄 www.cambridge.org/core/journal...
🧵6/7
For a theoretical take, check our other paper ⬇
📄 www.cambridge.org/core/journal...
🧵6/7
Realistic and broad-scope learning simulations: first results and challenges | Journal of Child Language | Cambridge Core
Realistic and broad-scope learning simulations: first results and challenges - Volume 50 Issue 6
www.cambridge.org
January 8, 2025 at 4:47 PM
💡 Finally, we aim to illustrate with this research how advanced computational models can simulate broad and realistic language learning, and as such help advance psycholinguistic research.
For a theoretical take, check our other paper ⬇
📄 www.cambridge.org/core/journal...
🧵6/7
For a theoretical take, check our other paper ⬇
📄 www.cambridge.org/core/journal...
🧵6/7
📚 We also analyse STELA's representations and find they don't match traditional linguistic categories like phonemes or words.
📈This indicates that early phonetic and word learning can occur without these categories, which may develop later in life.
🧵5/7
📈This indicates that early phonetic and word learning can occur without these categories, which may develop later in life.
🧵5/7
January 8, 2025 at 4:47 PM
📚 We also analyse STELA's representations and find they don't match traditional linguistic categories like phonemes or words.
📈This indicates that early phonetic and word learning can occur without these categories, which may develop later in life.
🧵5/7
📈This indicates that early phonetic and word learning can occur without these categories, which may develop later in life.
🧵5/7
🔬After training, we evaluate STELA on a phone discrimination and a word recognition task.
📊 We find the model replicates the *gradual* and *simultaneous* learning patters found in infants, suggesting statistical learning can alone bootstrap early language patterns.
🧵4/7
📊 We find the model replicates the *gradual* and *simultaneous* learning patters found in infants, suggesting statistical learning can alone bootstrap early language patterns.
🧵4/7
January 8, 2025 at 4:47 PM
🔬After training, we evaluate STELA on a phone discrimination and a word recognition task.
📊 We find the model replicates the *gradual* and *simultaneous* learning patters found in infants, suggesting statistical learning can alone bootstrap early language patterns.
🧵4/7
📊 We find the model replicates the *gradual* and *simultaneous* learning patters found in infants, suggesting statistical learning can alone bootstrap early language patterns.
🧵4/7
🤖 Here, we isolate statistical learning by developing STELA, a computational model that learns by predicting the near future of speech utterances.
🗣️ STELA is trained on raw speech only, with gradually increasing quantities, equivalent to those an infant would hear.
🧵3/7
🗣️ STELA is trained on raw speech only, with gradually increasing quantities, equivalent to those an infant would hear.
🧵3/7
January 8, 2025 at 4:47 PM
🤖 Here, we isolate statistical learning by developing STELA, a computational model that learns by predicting the near future of speech utterances.
🗣️ STELA is trained on raw speech only, with gradually increasing quantities, equivalent to those an infant would hear.
🧵3/7
🗣️ STELA is trained on raw speech only, with gradually increasing quantities, equivalent to those an infant would hear.
🧵3/7
👶 We know that infants learn multiple aspects of language - like distinguishing native sounds and recognising words - *gradually* and *simultaneously*.
Yet, it is still difficult to pinpoint which mechanisms are responsible for which aspect of language development.
🧵2/7
Yet, it is still difficult to pinpoint which mechanisms are responsible for which aspect of language development.
🧵2/7
January 8, 2025 at 4:47 PM
👶 We know that infants learn multiple aspects of language - like distinguishing native sounds and recognising words - *gradually* and *simultaneously*.
Yet, it is still difficult to pinpoint which mechanisms are responsible for which aspect of language development.
🧵2/7
Yet, it is still difficult to pinpoint which mechanisms are responsible for which aspect of language development.
🧵2/7