Search Results for author:
Found 55 papers, 13 papers with code
Minimally-Supervised Morphological Segmentation using Adaptor Grammars
This paper explores the use of Adaptor Grammars, a nonparametric Bayesian modelling framework, for minimally supervised morphological segmentation.
Unsupervised Dependency Parsing with Acoustic Cues
Unsupervised parsing is a difficult task that infants readily perform.
Unsupervised word segmentation and lexicon discovery using acoustic word embeddings
In settings where only unlabelled speech data is available, speech technology needs to be developed without transcriptions, pronunciation dictionaries, or language modelling text.
A segmental framework for fully-unsupervised large-vocabulary speech recognition
We also show that the discovered clusters can be made less speaker- and gender-specific by using an unsupervised autoencoder-like feature extractor to learn better frame-level features (prior to embedding).
Weakly supervised spoken term discovery using cross-lingual side information
Recent work on unsupervised term discovery (UTD) aims to identify and cluster repeated word-like units from audio alone.
Towards speech-to-text translation without speech recognition
We explore the problem of translating speech to text in low-resource scenarios where neither automatic speech recognition (ASR) nor machine translation (MT) are available, but we have training data in the form of audio paired with text translations.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
An embedded segmental K-means model for unsupervised segmentation and clustering of speech
Unsupervised segmentation and clustering of unlabelled speech are core problems in zero-resource speech processing.
From Segmentation to Analyses: a Probabilistic Model for Unsupervised Morphology Induction
A major motivation for unsupervised morphological analysis is to reduce the sparse data problem in under-resourced languages.
Aye or naw, whit dae ye hink? Scottish independence and linguistic identity on social media
Political surveys have indicated a relationship between a sense of Scottish identity and voting decisions in the 2014 Scottish Independence Referendum.
Topic and audience effects on distinctively Scottish vocabulary usage in Twitter data
Sociolinguistic research suggests that speakers modulate their language style in response to their audience.
Spoken Term Discovery for Language Documentation using Translations
Vast amounts of speech data collected for language documentation and research remain untranscribed and unsearchable, but often a small amount of speech may have text translations available.
Multilingual bottleneck features for subword modeling in zero-resource languages
How can we effectively develop speech technology for languages where no transcribed data is available?
Low-Resource Speech-to-Text Translation
We explore models trained on between 20 and 160 hours of data, and find that although models trained on less data have considerably lower BLEU scores, they can still predict words with relatively high precision and recall---around 50% for a model trained on 50 hours of data, versus around 60% for the full 160 hour model.
Evaluating historical text normalization systems: How well do they generalize?
We highlight several issues in the evaluation of historical text normalization systems that make it hard to tell how well these systems would actually work in practice---i. e., for new datasets or languages; in comparison to more na\"ive systems; or as a preprocessing step for downstream NLP tools.
Context Sensitive Neural Lemmatization with Lematus
The main motivation for developing contextsensitive lemmatizers is to improve performance on unseen and ambiguous words.
Pre-training on high-resource speech recognition improves low-resource speech-to-text translation
Finally, we show that the approach improves performance on a true low-resource task: pre-training on a combination of English ASR and French ASR improves Mboshi-French ST, where only 4 hours of data are available, from 3. 5 to 7. 1
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Inducing a lexicon of sociolinguistic variables from code-mixed text
Sociolinguistics is often concerned with how variants of a linguistic item (e. g., \textit{nothing} vs. \textit{nothin{'}}) are used by different groups or in different situations.
Multilingual and Unsupervised Subword Modeling for Zero-Resource Languages
Here we directly compare multiple methods, including some that use only target language speech data and some that use transcribed speech from other (non-target) languages, and we evaluate using two intrinsic measures as well as on a downstream unsupervised word segmentation and clustering task.
Training Data Augmentation for Context-Sensitive Neural Lemmatization Using Inflection Tables and Raw Text
Lemmatization aims to reduce the sparse data problem by relating the inflected forms of a word to its dictionary form.
Training Data Augmentation for Context-Sensitive Neural Lemmatizer Using Inflection Tables and Raw Text
Lemmatization aims to reduce the sparse data problem by relating the inflected forms of a word to its dictionary form.
Are we there yet? Encoder-decoder neural networks as cognitive models of English past tense inflection
The cognitive mechanisms needed to account for the English past tense have long been a subject of debate in linguistics and cognitive science.
Cross-lingual topic prediction for speech using translations
Given a large amount of unannotated speech in a low-resource language, can we classify the speech utterances by topic?
Analyzing ASR pretraining for low-resource speech-to-text translation
Previous work has shown that for low-resource source languages, automatic speech-to-text translation (AST) can be improved by pretraining an end-to-end model on automatic speech recognition (ASR) data from a high-resource language.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Multilingual acoustic word embedding models for processing zero-resource languages
Acoustic word embeddings are fixed-dimensional representations of variable-length speech segments.
Analyzing autoencoder-based acoustic word embeddings
To better understand the applications of AWEs in various downstream tasks and in cognitive modeling, we need to analyze the representation spaces of AWEs.
The role of context in neural pitch accent detection in English
We find that these innovations lead to an improvement from 87. 5% to 88. 7% accuracy on pitch accent detection on American English speech in the Boston University Radio News Corpus, a state-of-the-art result.
Inflecting when there's no majority: Limitations of encoder-decoder neural networks as cognitive models for German plurals
Encoder-decoder models do generalize the most frequently produced plural class, but do not show human-like variability or 'regular' extension of these other plural markers.
Improved acoustic word embeddings for zero-resource languages using multilingual transfer
We consider three multilingual recurrent neural network (RNN) models: a classifier trained on the joint vocabularies of all training languages; a Siamese RNN trained to discriminate between same and different words from multiple languages; and a correspondence autoencoder (CAE) RNN trained to reconstruct word pairs.
Evaluating computational models of infant phonetic learning across languages
In the first year of life, infants' speech perception becomes attuned to the sounds of their native language.
LemMED: Fast and Effective Neural Morphological Analysis with Short Context Windows
We present LemMED, a character-level encoder-decoder for contextual morphological analysis (combined lemmatization and tagging).
A phonetic model of non-native spoken word processing
We then test the model on a spoken word processing task, showing that phonology may not be necessary to explain some of the word processing effects observed in non-native speakers.
Identity Signals in Emoji Do not Influence Perception of Factual Truth on Twitter
Prior work has shown that Twitter users use skin-toned emoji as an act of self-representation to express their racial/ethnic identity.
Black or White but never neutral: How readers perceive identity from yellow or skin-toned emoji
Research in sociology and linguistics shows that people use language not only to express their own identity but to understand the identity of others.
Prosodic segmentation for parsing spoken dialogue
We investigate how prosody affects a parser that receives an entire dialogue turn as input (a turn-based model), instead of gold standard pre-segmented SUs (an SU-based model).
On the Difficulty of Segmenting Words with Attention
Word segmentation, the problem of finding word boundaries in speech, is of interest for a range of tasks.
Cross-linguistically Consistent Semantic and Syntactic Annotation of Child-directed Speech
We then demonstrate the utility of the compiled corpora through (1) a longitudinal corpus study of the prevalence of different syntactic and semantic phenomena in the CDS, and (2) applying an existing computational model of language acquisition to the two corpora and briefly comparing the results across languages.
Analyzing Acoustic Word Embeddings from Pre-trained Self-supervised Speech Models
Given the strong results of self-supervised models on various tasks, there have been surprisingly few studies exploring self-supervised representations for acoustic word embeddings (AWE), fixed-dimensional vectors representing variable-length spoken word segments.
Prosodic features improve sentence segmentation and parsing
Parsing spoken dialogue presents challenges that parsing text does not, including a lack of clear sentence boundaries.
Self-supervised Predictive Coding Models Encode Speaker and Phonetic Information in Orthogonal Subspaces
Self-supervised speech representations are known to encode both speaker and phonetic information, but how they are distributed in the high-dimensional space remains largely unexplored.
Acoustic Word Embeddings for Untranscribed Target Languages with Continued Pretraining and Learned Pooling
Acoustic word embeddings are typically created by training a pooling function using pairs of word-like units.
ALDi: Quantifying the Arabic Level of Dialectness of Text
Transcribed speech and user-generated text in Arabic typically contain a mixture of Modern Standard Arabic (MSA), the standardized language taught in schools, and Dialectal Arabic (DA), used in daily communications.
Adaptor Grammars for Unsupervised Paradigm Clustering
This work describes the Edinburgh submission to the SIGMORPHON 2021 Shared Task 2 on unsupervised morphological paradigm clustering.
Conditioning, but on Which Distribution? Grammatical Gender in German Plural Inflection
Grammatical gender is a consistent and informative cue to the plural class of German nouns.
