Related papers: Word stress in self-supervised speech models: A cr…

A range of studies have concluded that neural word prediction models can distinguish grammatical from ungrammatical sentences with high accuracy. However, these studies are based primarily on monolingual evidence from English. To…

Speech and language models trained through self-supervised learning (SSL) demonstrate strong alignment with brain activity during speech and language perception. However, given their distinct training modalities, it remains unclear whether…

Multilingual speech recognition with supervised learning has achieved great results as reflected in recent research. With the development of pretraining methods on audio and text data, it is imperative to transfer the knowledge from…

Self-supervised speech models (S3Ms) are known to encode rich phonetic information, yet how this information is structured remains underexplored. We conduct a comprehensive study across 96 languages to analyze the underlying structure of…

Cross-lingual word embeddings are vector representations of words in different languages where words with similar meaning are represented by similar vectors, regardless of the language. Recent developments which construct these embeddings…

The success of pretrained word embeddings has motivated their use in the biomedical domain, with contextualized embeddings yielding remarkable results in several biomedical NLP tasks. However, there is a lack of research on quantifying…

Spoken Dialogue Models (SDMs) have recently attracted significant attention for their ability to generate voice responses directly to users' spoken queries. Despite their increasing popularity, there exists a gap in research focused on…

Acoustic word embeddings are fixed-dimensional representations of variable-length speech segments. In settings where unlabelled speech is the only available resource, such embeddings can be used in "zero-resource" speech search, indexing…

Detecting psychological stress from speech is critical in high-pressure settings. While prior work has leveraged acoustic features for stress detection, most treat stress as a static label. In this work, we model stress as a temporally…

Recent research has adopted a new experimental field centered around the concept of text perturbations which has revealed that shuffled word order has little to no impact on the downstream performance of Transformer-based language models…

As a neurophysiological response to threat or adverse conditions, stress can affect cognition, emotion and behaviour with potentially detrimental effects on health in the case of sustained exposure. Since the affective content of speech is…

Self-supervised models for speech processing form representational spaces without using any external labels. Increasingly, they appear to be a feasible way of at least partially eliminating costly manual annotations, a problem of particular…

Utilizing Self-Supervised Learning (SSL) models for Speech Emotion Recognition (SER) has proven effective, yet limited research has explored cross-lingual scenarios. This study presents a comparative analysis between human performance and…

We propose an unsupervised method to obtain cross-lingual embeddings without any parallel data or pre-trained word embeddings. The proposed model, which we call multilingual neural language models, takes sentences of multiple languages as…

Recently proposed self-supervised learning approaches have been successful for pre-training speech representation models. The utility of these learned representations has been observed empirically, but not much has been studied about the…

Recent models such as XLS-R and Whisper have made multilingual speech technologies more accessible by pre-training on audio from around 100 spoken languages each. However, there are thousands of spoken languages worldwide, and adapting to…

Speech representations from self-supervised speech models (S3Ms) are known to be sensitive to phonemic contrasts, but their sensitivity to prosodic contrasts has not been directly measured. The ABX discrimination task has been used to…

Large Language Models (LLMs) exhibit strong linguistic capabilities, but little is known about how they encode psycholinguistic knowledge across languages. We investigate whether and how LLMs exhibit human-like psycholinguistic responses…

Depression, a prevalent mental health disorder impacting millions globally, demands reliable assessment systems. Unlike previous studies that focus solely on either detecting depression or predicting its severity, our work identifies…

Child speech recognition is still an underdeveloped area of research due to the lack of data (especially on non-English languages) and the specific difficulties of this task. Having explored various architectures for child speech…