Abstract Automatic Speech Recognition (ASR) systems can be trained to achieve
remarkable performance given large amounts of manually transcribed speech, but large …

Recent advancements in spoken dialogue models, exemplified by systems like GPT-4o,
have captured significant attention in the speech domain. Compared to traditional three-tier …

We investigate segmenting and clustering speech into low-bitrate phone-like sequences
without supervision. We specifically constrain pretrained self-supervised vector-quantized …

Computational models of child language development can help us understand the cognitive
underpinnings of the language learning process, which occurs along several linguistic …

In this paper, we propose an unsupervised kNN-based approach for word segmentation in
speech utterances. Our method relies on self-supervised pre-trained speech …

Computational models of child language development can help us understand the cognitive
underpinnings of the language learning process. One advantage of computational modeling …

Unsupervised PCFG induction models, which build syntactic structures from raw text, can be
used to evaluate the extent to which syntactic knowledge can be acquired from distributional …

Interpretability work on the convolutional layers of CNNs has primarily focused on computer
vision, but some studies also explore correspondences between the latent space and the …

It has been generally assumed in the automatic speech recognition (ASR) literature that it is
better for models to have access to wider context windows. Yet, many of the potential …

Abstract Linguistic bias in Deep Neural Network (DNN) based Natural Language Processing
(NLP) systems is a critical problem that needs attention. The problem further intensifies in …