Related papers: PolyMorph: Increasing P300 Spelling Efficiency by …
Self-supervised speech representation learning (S3RL) is revolutionizing the way we leverage the ever-growing availability of data. While S3RL related studies typically use large models, we employ light-weight networks to comply with tight…
The majority of research in computational psycholinguistics has concentrated on the processing of words. This study introduces innovative methods for computing sentence-level metrics using multilingual large language models. The metrics…
Intuitively, human readers cope easily with errors in text; typos, misspelling, word substitutions, etc. do not unduly disrupt natural reading. Previous work indicates that letter transpositions result in increased reading times, but it is…
We describe a new framework for distilling information from word lattices to improve the accuracy of speech recognition and obtain a more perspicuous representation of a set of alternative hypotheses. In the standard MAP decoding approach…
State-of-the-art speech-to-text models typically employ Transformer-based encoders that model token dependencies via self-attention mechanisms. However, the quadratic complexity of self-attention in both memory and computation imposes…
Emotion plays a fundamental role in human interaction, and therefore systems capable of identifying emotions in speech are crucial in the context of human-computer interaction. Speech emotion recognition (SER) is a challenging problem,…
For reasons such as privacy, there are use cases for language models at the edge. This has given rise to small language models targeted for deployment in resource-constrained devices where energy efficiency is critical. Spiking neural…
Although diffusion models in text-to-speech have become a popular choice due to their strong generative ability, the intrinsic complexity of sampling from diffusion models harms their efficiency. Alternatively, we propose VoiceFlow, an…
Children efficiently acquire language not just by listening, but by interacting with others in their social environment. Conversely, large language models are typically trained with next-word prediction on massive amounts of text. Motivated…
Brain-computer interfaces have many algorithms based on the P300 component of ERP. Modern industry has started to produce consumer grade EEG equipment which is handy and not too expensive. This gives us an opportunity to use BCI in everyday…
Speeding up the spelling in event-related potentials (ERP) based Brain-Computer Interfaces (BCI) requires eliciting strong brain responses in a short span of time, as much as the accurate classification of such evoked potentials remains…
Metaphors play a significant role in our everyday communication, yet detecting them presents a challenge. Traditional methods often struggle with improper application of language rules and a tendency to overlook data sparsity. To address…
The ability to dynamically adjust the computational load of neural models during inference in a resource aware manner is crucial for on-device processing scenarios, characterised by limited and time-varying computational resources.…
In automatic speech recognition (ASR) rescoring, the hypothesis with the fewest errors should be selected from the n-best list using a language model (LM). However, LMs are usually trained to maximize the likelihood of correct word…
The rapid evolution of lightweight consumer augmented reality (AR) smart glasses (a.k.a. optical see-through head-mounted displays) offers novel opportunities for learning, particularly through their unique capability to deliver multimodal…
Speech production is a complex phenomenon, wherein the brain orchestrates a sequence of processes involving thought processing, motor planning, and the execution of articulatory movements. However, this intricate execution of various…
The linear programming decoder will occasionally output fractional-valued sequences that do not correspond to binary codewords - such outputs are termed nontrivial pseudocodewords. Feldman et al. have demonstrated that it is precisely the…
Mental manipulation, the strategic use of language to covertly influence or exploit others, is a newly emerging task in computational social reasoning. Prior work has focused exclusively on textual conversations, overlooking how…
Within the area of speech enhancement, there is an ongoing interest in the creation of neural systems which explicitly aim to improve the perceptual quality of the processed audio. In concert with this is the topic of non-intrusive (i.e.…
Many deep learning synthetic speech generation tools are readily available. The use of synthetic speech has caused financial fraud, impersonation of people, and misinformation to spread. For this reason forensic methods that can detect…