Related papers: A statistical model for word discovery in child di…
Word embedding methods revolve around learning continuous distributed vector representations of words with neural networks, which can capture semantic and/or syntactic cues, and in turn be used to induce similarity measures among words,…
Common language models typically predict the next word given the context. In this work, we propose a method that improves language modeling by learning to align the given context and the following phrase. The model does not require any…
Understanding how infants perceive speech sounds and language structures is still an open problem. Previous research in artificial neural networks has mainly focused on large dataset-dependent generative models, aiming to replicate…
Infants acquire words and phonemes from unsegmented speech signals using segmentation cues, such as distributional, prosodic, and co-occurrence cues. Many pre-existing computational models that represent the process tend to focus on…
Distributed word representations have been demonstrated to be effective in capturing semantic and syntactic regularities. Unsupervised representation learning from large unlabeled corpora can learn similar representations for those words…
Interactive spoken dialog provides many new challenges for spoken language systems. One of the most critical is the prevalence of speech repairs. This paper presents an algorithm that detects and corrects speech repairs based on finding the…
Speech signals are complex composites of various information, including phonetic content, speaker traits, channel effect, etc. Decomposing this complicated mixture into independent factors, i.e., speech factorization, is fundamentally…
We introduce machine unlearning for speech tasks, a novel and underexplored research problem that aims to efficiently and effectively remove the influence of specific data from trained speech models without full retraining. This has…
We present work-in-progress on the machine acquisition of a lexicon from sentences that are each an unsegmented phone sequence paired with a primitive representation of meaning. A simple exploratory algorithm is described, along with the…
Existing methods for CWS usually rely on a large number of labeled sentences to train word segmentation models, which are expensive and time-consuming to annotate. Luckily, the unlabeled data is usually easy to collect and many high-quality…
In what ways might statistical signals in linguistic input assist with the acquisition of syntax? Here we hypothesize a mechanism called collocational bootstrapping, in which regularities in word co-occurrence patterns can provide cues to…
Speech processing techniques are useful for analyzing speech and language development in children with Autism Spectrum Disorder (ASD), who are often varied and delayed in acquiring these skills. Early identification and intervention are…
Most language modeling methods rely on large-scale data to statistically learn the sequential patterns of words. In this paper, we argue that words are atomic language units but not necessarily atomic semantic units. Inspired by HowNet, we…
Speech separation with several speakers is a challenging task because of the non-stationarity of the speech and the strong signal similarity between interferent sources. Current state-of-the-art solutions can separate well the different…
Designing machine intelligence to converse with a human user necessarily requires an understanding of how humans participate in conversation, and thus conversation modeling is an important task in natural language processing. New…
Machine Learning produces efficient decision and prediction models based on input-output data only. Such models have the form of decision trees or neural nets and are far from transparent analytical models, based on mathematical formulas.…
In many real-world settings, machine learning models need to identify user inputs that are out-of-domain (OOD) so as to avoid performing wrong actions. This work focuses on a challenging case of OOD detection, where no labels for in-domain…
I present a computational-level model of semantic interference effects in word production. Word production is cast as a rate-distortion problem where an agent selects words to minimize a measure of cost while also minimizing the resources…
We study whether automatically-induced prompts that effectively extract information from a language model can also be used, out-of-the-box, to probe other language models for the same information. After confirming that discrete prompts…
Nous pr\'esentons dans cette contribution une approche \`a la fois symbolique et probabiliste permettant d'extraire l'information sur la segmentation du signal de parole \`a partir d'information prosodique. Nous utilisons pour ce faire des…