Search Results - "Goldwater, Sharon"

A Bayesian framework for word segmentation: Exploring the effects of context by Goldwater, Sharon, Griffiths, Thomas L., Johnson, Mark

“…Since the experiments of Saffran et al. [Saffran, J., Aslin, R., & Newport, E. (1996). Statistical learning in 8-month-old infants. Science, 274, 1926–1928],…”
Get full text

Analyzing ASR Pretraining for Low-Resource Speech-to-Text Translation by Stoian, Mihaela C., Bansal, Sameer, Goldwater, Sharon

“…Previous work has shown that for low-resource source languages, automatic speech-to-text translation (AST) can be improved by pre-training an end-to-end model…”
Get full text

Unsupervised neural network based feature extraction using weak top-down constraints by Kamper, Herman, Elsner, Micha, Jansen, Aren, Goldwater, Sharon

“…Deep neural networks (DNNs) have become a standard component in supervised ASR, used in both data-driven feature extraction and acoustic modelling. Supervision…”
Get full text

A Role for the Developing Lexicon in Phonetic Category Acquisition by Feldman, Naomi H., Griffiths, Thomas L., Goldwater, Sharon, Morgan, James L.

“…Infants segment words from fluent speech during the same period when they are learning phonetic categories, yet accounts of phonetic category acquisition…”
Get full text

Talkers account for listener and channel characteristics to communicate efficiently by Pate, John K, Goldwater, Sharon

“…•We review the noisy channel theorem, distinguishing source and channel coding.•Our framing clarifies efficiency accounts of speech reduction and their…”
Get full text

A segmental framework for fully-unsupervised large-vocabulary speech recognition by Kamper, Herman, Jansen, Aren, Goldwater, Sharon

“…Zero-resource speech technology is a growing research area that aims to develop methods for speech processing in the absence of transcriptions, lexicons, or…”
Get full text

Multilingual and unsupervised subword modeling for zero-resource languages by Hermann, Enno, Kamper, Herman, Goldwater, Sharon

“…•VTLN is a useful preprocessing step for unsupervised speech processing systems.•Cross-lingual pre-training improves over target-language-only unsupervised…”
Get full text

Unsupervised Word Segmentation and Lexicon Discovery Using Acoustic Word Embeddings by Kamper, Herman, Jansen, Aren, Goldwater, Sharon

“…In settings where only unlabeled speech data is available, speech technology needs to be developed without transcriptions, pronunciation dictionaries, or…”
Get full text

Analyzing Acoustic Word Embeddings from Pre-Trained Self-Supervised Speech Models by Sanabria, Ramon, Tang, Hao, Goldwater, Sharon

“…Given the strong results of self-supervised models on various tasks, there have been surprisingly few studies exploring self-supervised representations for…”
Get full text

Improved Acoustic Word Embeddings for Zero-Resource Languages Using Multilingual Transfer by Kamper, Herman, Matusevych, Yevgen, Goldwater, Sharon

“…Acoustic word embeddings are fixed-dimensional representations of variable-length speech segments. Such embeddings can form the basis for speech search,…”
Get full text

Unsupervised lexical clustering of speech segments using fixed-dimensional acoustic embeddings by Kamper, Herman, Jansen, Aren, King, Simon, Goldwater, Sharon

“…Unsupervised speech processing methods are essential for applications ranging from zero-resource speech technology to modelling child language acquisition. One…”
Get full text

Multilingual Acoustic Word Embedding Models for Processing Zero-resource Languages by Kamper, Herman, Matusevych, Yevgen, Goldwater, Sharon

“…Acoustic word embeddings are fixed-dimensional representations of variable-length speech segments. In settings where unlabelled speech is the only available…”
Get full text

Which words are hard to recognize? Prosodic, lexical, and disfluency factors that increase speech recognition error rates by Goldwater, Sharon, Jurafsky, Dan, Manning, Christopher D.

“…Despite years of speech recognition research, little is known about which words tend to be misrecognized and why. Previous work has shown that errors increase…”
Get full text

Infant Phonetic Learning as Perceptual Space Learning: A Crosslinguistic Evaluation of Computational Models by Matusevych, Yevgen, Schatz, Thomas, Kamper, Herman, Feldman, Naomi H., Goldwater, Sharon

“…In the first year of life, infants' speech perception becomes attuned to the sounds of their native language. This process of early phonetic learning has…”
Get full text

Early phonetic learning without phonetic categories: Insights from large-scale simulations on realistic input by Schatz, Thomas, Feldman, Naomi H., Goldwater, Sharon, Cao, Xuan-Nga, Dupoux, Emmanuel

“…Before they even speak, infants become attuned to the sounds of the language(s) they hear, processing native phonetic contrasts more easily than nonnative…”
Get full text

Correction: Cross-linguistically consistent semantic and syntactic annotation of child-directed speech by Szubert, Ida, Abend, Omri, Schneider, Nathan, Gibbon, Samuel, Mahon, Louis, Goldwater, Sharon, Steedman, Mark

Get full text

Cross-linguistically consistent semantic and syntactic annotation of child-directed speech by Szubert, Ida, Abend, Omri, Schneider, Nathan, Gibbon, Samuel, Mahon, Louis, Goldwater, Sharon, Steedman, Mark

“…Abstract Corpora of child speech and child-directed speech (CDS) have enabled major contributions to the study of child language acquisition, yet semantic…”
Get full text

The Future of Speech Tech by Goldwater, Sharon, Cooper, Martin

Get full text

Do Infants Really Learn Phonetic Categories? by Feldman, Naomi H., Goldwater, Sharon, Dupoux, Emmanuel, Schatz, Thomas

“…Early changes in infants’ ability to perceive native and nonnative speech sound contrasts are typically attributed to their developing knowledge of phonetic…”
Get full text

Bootstrapping language acquisition by Abend, Omri, Kwiatkowski, Tom, Smith, Nathaniel J., Goldwater, Sharon, Steedman, Mark

“…•Computational implementation of the Semantic Bootstrapping Hypothesis.•Joint Bayesian modeling of the acquisition of word meanings and syntax.•The model…”
Get full text