Related papers: Structural Reductions and Stutter Sensitive Proper…

Verification of properties expressed as-regular languages such as LTL can benefit hugely from stutter-insensitivity, using a diverse set of reduction strategies. However properties that are not stutter-insensitive, for instance due to the…

For over a decade, researchers in formal methods tried to create formalisms that permit natural specification of systems and allow mathematical reasoning about their correctness. The availability of fully-automated reasoning tools enables…

Stuttering is a speech disorder where the natural flow of speech is interrupted by blocks, repetitions or prolongations of syllables, words and phrases. The majority of existing automatic speech recognition (ASR) interfaces perform poorly…

Computational efficiency has remained a critical consideration in scaling high-capacity language models, with inference latency and resource consumption presenting significant constraints on real-time applications. The study has introduced…

Humans can learn structural properties about a word from minimal experience, and deploy their learned syntactic representations uniformly in different grammatical contexts. We assess the ability of modern neural language models to reproduce…

Consumer speech recognition systems do not work as well for many people with speech diferences, such as stuttering, relative to the rest of the general population. However, what is not clear is the degree to which these systems do not work,…

Transformers achieve state-of-the-art accuracy and robustness across many tasks, but an understanding of their inductive biases and how those biases differ from other neural network architectures remains elusive. In this work, we identify…

In many current speech recognizers, a statistical language model is used to indicate how likely it is that a certain word will be spoken next, given the words recognized so far. How can statistical language models be improved so that more…

Stuttering is a speech impediment affecting tens of millions of people on an everyday basis. Even with its commonality, there is minimal data and research on the identification and classification of stuttered speech. This paper tackles the…

We present the first text-to-speech (TTS) system tailored to second language (L2) speakers. We use duration differences between American English tense (longer) and lax (shorter) vowels to create a "clarity mode" for Matcha-TTS. Our…

Large language models (LLMs) are known to exhibit brittle behavior under adversarial prompts and jailbreak attacks, even after extensive alignment and fine-tuning. This fragility reflects a broader challenge of modern neural language…

A specification given as a formula in linear temporal logic (LTL) defines a system by its set of traces. However, certain features such as information flow security constraints are rather modeled as so-called hyperproperties, which are sets…

Soft Prompt Tuning (SPT) is a parameter-efficient method for adapting pre-trained language models (PLMs) to specific tasks by inserting learnable embeddings, or soft prompts, at the input layer of the PLM, without modifying its parameters.…

Speech transcription, emotion recognition, and language identification are usually considered to be three different tasks. Each one requires a different model with a different architecture and training process. We propose using a recurrent…

We compare phone labels and articulatory features as input for cross-lingual transfer learning in text-to-speech (TTS) for low-resource languages (LRLs). Experiments with FastSpeech 2 and the LRL West Frisian show that using articulatory…

The idea of using phonological features instead of phonemes as input to sequence-to-sequence TTS has been recently proposed for zero-shot multilingual speech synthesis. This approach is useful for code-switching, as it facilitates the…

Stuttering is a varied speech disorder that harms an individual's communication ability. Persons who stutter (PWS) often use speech therapy to cope with their condition. Improving speech recognition systems for people with such non-typical…

Like many other machine learning applications, neural machine translation (NMT) benefits from over-parameterized deep neural models. However, these models have been observed to be brittle: NMT model predictions are sensitive to small input…

Current soft prompt methods yield limited performance when applied to small-sized models (fewer than a billion parameters). Deep prompt-tuning, which entails prepending parameters in each layer for enhanced efficacy, presents a solution for…

Language-independent tokenisation (LIT) methods that do not require labelled language resources or lexicons have recently gained popularity because of their applicability in resource-poor languages. Moreover, they compactly represent a…