Related papers: Using Mimicry to Learn about Mental Representation…

Emotion and expressivity in music have been topics of considerable interest in the field of music information retrieval. In recent years, mid-level perceptual features have been suggested as means to explain computational predictions of…

Prior research indicates that LID model performance significantly declines on accented speech; however, the specific causes, extent, and characterization of these errors remain under-explored. (i) We identify a common failure mode on…

Whether a word was bawled, whispered, or yelped, captions will typically represent it in the same way. If they are your only way to access what is being said, subjective nuances expressed in the voice will be lost. Since so much of…

Recent dialogue coherence models use the coherence features designed for monologue texts, e.g. nominal entities, to represent utterances and then explicitly augment them with dialogue-relevant features, e.g., dialogue act labels. It…

Ideological attitudes and stance are often expressed through subtle meanings of words and phrases. Understanding these connotations is critical to recognizing the cultural and emotional perspectives of the speaker. In this paper, we use…

This article contains a proposal to add coinduction to the computational apparatus of natural language understanding. This, we argue, will provide a basis for more realistic, computationally sound, and scalable models of natural language…

Discrete speech representation learning has recently attracted increasing interest in both acoustic and semantic modeling. Existing approaches typically encode 16 kHz waveforms into discrete tokens at a rate of 25 or 50 tokens per second.…

Recent progress in Spoken Language Modeling has shown that learning language directly from speech is feasible. Generating speech through a pipeline that operates at the text level typically loses nuances, intonations, and non-verbal…

In the highly constrained context of low-resource language studies, we explore vector representations of speech from a pretrained model to determine their level of abstraction with regard to the audio signal. We propose a new unsupervised…

Audio events are quite often overlapping in nature, and more prone to noise than visual signals. There has been increasing evidence for the superior performance of representations learned using sparse dictionaries for applications like…

Human infants face a formidable challenge in speech acquisition: mapping extremely variable acoustic inputs into appropriate articulatory movements without explicit instruction. We present a computational model that addresses the…

While a large body of literature suggests that large language models (LLMs) acquire rich linguistic representations, little is known about whether they adapt to linguistic biases in a human-like way. The present study probes this question…

Fonts are ubiquitous across documents and come in a variety of styles. They are either represented in a native vector format or rasterized to produce fixed resolution images. In the first case, the non-standard representation prevents…

Sentence representation models trained only on language could potentially suffer from the grounding problem. Recent work has shown promising results in improving the qualities of sentence representations by jointly training them with…

Machine learning techniques are an active area of research for speech enhancement for hearing aids, with one particular focus on improving the intelligibility of a noisy speech signal. Recent work has shown that feature encodings from…

Large speech models-derived features have recently shown increased performance over signal-based features across multiple downstream tasks, even when the networks are not finetuned towards the target task. In this paper we show the results…

Prosody plays a vital role in verbal communication. Acoustic cues of prosody have been examined extensively. However, prosodic characteristics are not only perceived auditorily, but also visually based on head and facial movements. The…

Compositionality, the phenomenon where the meaning of a phrase can be derived from its constituent parts, is a hallmark of human language. At the same time, many phrases are non-compositional, carrying a meaning beyond that of each part in…

A neural language model trained on a text corpus can be used to induce distributed representations of words, such that similar words end up with similar representations. If the corpus is multilingual, the same model can be used to learn…

The neural mechanisms underlying the comprehension of meaningful sounds are yet to be fully understood. While previous research has shown that the auditory cortex can classify auditory stimuli into distinct semantic categories, the specific…