Related papers: Evaluating Logit-Based GOP Scores for Mispronuncia…

Semantic plausibility (e.g. knowing that "the actor won the award" is more likely than "the actor won the battle") serves as an effective proxy for general world knowledge. Language models (LMs) capture vast amounts of world knowledge by…

How predictable a word is can be quantified in two ways: using human responses to the cloze task or using probabilities from language models (LMs).When used as predictors of processing effort, LM probabilities outperform probabilities…

Recently, denoising diffusion probabilistic models and generative score matching have shown high potential in modelling complex data distributions while stochastic calculus has provided a unified point of view on these techniques allowing…

Many mispronunciation detection and diagnosis (MD&D) research approaches try to exploit both the acoustic and linguistic features as input. Yet the improvement of the performance is limited, partially due to the shortage of large amount…

This paper explores the relationship between accent strength and articulatory features inferred from acoustic speech. To quantify accent strength, we compare phonetic transcriptions with transcriptions based on dictionary-based references,…

Unsupervised speech representation learning has shown remarkable success at finding representations that correlate with phonetic structures and improve downstream speech recognition performance. However, most research has been focused on…

The pre-trained multi-lingual XLSR model generalizes well for language identification after fine-tuning on unseen languages. However, the performance significantly degrades when the languages are not very distinct from each other, for…

Out-of-distribution (OOD) detection is critical for ensuring the reliability of deep learning models in open-world applications. While post-hoc methods are favored for their efficiency and ease of deployment, existing approaches often…

Grammaticality and likelihood are distinct notions in human language. Pretrained language models (LMs), which are probabilistic models of language fitted to maximize corpus likelihood, generate grammatically well-formed text and…

With an evergrowing number of LLMs reporting superlative performance for English, their ability to perform equitably for different dialects of English ($\textit{i.e.}$, dialect robustness) needs to be ascertained. Specifically, we use…

Grammar Detection, also referred to as Parts of Speech Tagging of raw text, is considered an underlying building block of the various Natural Language Processing pipelines like named entity recognition, question answering, and sentiment…

Reinforcement learning enhances the reasoning capabilities of large language models but often involves high computational costs due to rollout-intensive optimization. Online prompt selection presents a plausible solution by prioritizing…

The ability to reliably distinguish human-written text from that generated by large language models is of profound societal importance. The dominant approach to this problem exploits the likelihood hypothesis: that machine-generated text…

Pronunciation is one of the fundamentals of language learning, and it is considered a primary factor of spoken language when it comes to an understanding and being understood by others. The persistent presence of high error rates in speech…

Confidence calibration is an emerging challenge in real-world decision systems based on foundations models when used for downstream vision classification tasks. Due to various reasons exposed, logit scores on the CLIP head remain large…

Wide usage of ChatGPT has highlighted the potential of reinforcement learning from human feedback. However, its training pipeline relies on manual ranking, a resource-intensive process. To reduce labor costs, we propose a self-supervised…

In this paper, we initiate our discussion by demonstrating how Large Language Models (LLMs), when tasked with responding to queries, display a more even probability distribution in their answers if they are more adept, as opposed to their…

Prompt-based classifiers are an attractive approach for zero-shot classification. However, the precise choice of the prompt template and label words can largely influence performance, with semantically equivalent settings often showing…

Traditionally, the performance of non-native mispronunciation verification systems relied on effective phone-level labelling of non-native corpora. In this study, a multi-view approach is proposed to incorporate discriminative feature…

We apply rule induction, classifier combination and meta-learning (stacked classifiers) to the problem of bootstrapping high accuracy automatic annotation of corpora with pronunciation information. The task we address in this paper consists…