Cognitive science in the era of artificial intelligence: A roadmap for reverse-engineering the infant language-learner
E Dupoux - Cognition, 2018 - Elsevier
Spectacular progress in the information processing sciences (machine learning, wearable
sensors) promises to revolutionize the study of cognitive development. Here, we analyse the …
sensors) promises to revolutionize the study of cognitive development. Here, we analyse the …
Computational modeling of phonetic and lexical learning in early language acquisition: Existing models and future directions
O Räsänen - Speech Communication, 2012 - Elsevier
This work reviews a number of existing computational studies concentrated on the question
of how spoken language can be learned from continuous speech in the absence of …
of how spoken language can be learned from continuous speech in the absence of …
Efficient spoken term discovery using randomized algorithms
A Jansen, B Van Durme - 2011 IEEE Workshop on Automatic …, 2011 - ieeexplore.ieee.org
Spoken term discovery is the task of automatically identifying words and phrases in speech
data by searching for long repeated acoustic patterns. Initial solutions relied on exhaustive …
data by searching for long repeated acoustic patterns. Initial solutions relied on exhaustive …
What do self-supervised speech models know about words?
Many self-supervised speech models (S3Ms) have been introduced over the last few years,
improving performance and data efficiency on various speech tasks. However, these …
improving performance and data efficiency on various speech tasks. However, these …
What do self-supervised speech models know about words?
Many self-supervised speech models (S3Ms) have been introduced over the last few years,
producing performance and data efficiency improvements for a variety of speech tasks …
producing performance and data efficiency improvements for a variety of speech tasks …
Unsupervised word segmentation and lexicon discovery using acoustic word embeddings
In settings where only unlabeled speech data is available, speech technology needs to be
developed without transcriptions, pronunciation dictionaries, or language modelling text. A …
developed without transcriptions, pronunciation dictionaries, or language modelling text. A …
[PDF][PDF] Rapid evaluation of speech representations for spoken term discovery
Acoustic front-ends are typically developed for supervised learning tasks and are thus
optimized to minimize word error rate, phone error rate, etc. However, in recent efforts to …
optimized to minimize word error rate, phone error rate, etc. However, in recent efforts to …
Semantic speech retrieval with a visually grounded model of untranscribed speech
H Kamper, G Shakhnarovich… - Proceedings of the …, 2018 - openaccess.thecvf.com
There is growing interest in speech models that can learn from unlabelled speech paired
with visual context. Here we study how a visually grounded speech model, trained on …
with visual context. Here we study how a visually grounded speech model, trained on …
Unsupervised discovery of recurring speech patterns using probabilistic adaptive metrics
O Räsänen, MAC Blandón - arXiv preprint arXiv:2008.00731, 2020 - arxiv.org
Unsupervised spoken term discovery (UTD) aims at finding recurring segments of speech
from a corpus of acoustic speech data. One potential approach to this problem is to use …
from a corpus of acoustic speech data. One potential approach to this problem is to use …
Weak top-down constraints for unsupervised acoustic model training
Typical supervised acoustic model training relies on strong top-down constraints provided
by dynamic programming alignment of the input observations to phonetic sequences …
by dynamic programming alignment of the input observations to phonetic sequences …