Related papers: Recreating Neural Activity During Speech Productio…

Transformative innovations in model architectures have introduced hierarchical embedding augmentation as a means to redefine the representation of tokens through multi-level semantic structures, offering enhanced adaptability to complex…

Semantic sentence embedding models encode natural language sentences into vectors, such that closeness in embedding space indicates closeness in the semantics between the sentences. Bilingual data offers a useful signal for learning such…

Language models can be viewed as functions that embed text into Euclidean space, where the quality of the embedding vectors directly determines model performance, training such neural networks involves various uncertainties. This paper…

Speaker embeddings represent a means to extract representative vectorial representations from a speech signal such that the representation pertains to the speaker identity alone. The embeddings are commonly used to classify and discriminate…

The growing number of generative AI-based dialogue systems has made their evaluation a crucial challenge. This paper presents our contribution to this important problem through the Dialogue System Technology Challenge (DSTC-12, Track 1),…

Recurrent neural networks have been very successful at predicting sequences of words in tasks such as language modeling. However, all such models are based on the conventional classification framework, where the model is trained against…

Over the past few years, neural networks have re-emerged as powerful machine-learning models, yielding state-of-the-art results in fields such as image recognition and speech processing. More recently, neural network models started to be…

Recent research has delved into speech enhancement (SE) approaches that leverage audio embeddings from pre-trained models, diverging from time-frequency masking or signal prediction techniques. This paper introduces an efficient and…

Modern large language models (LLMs) excel at tasks that require storing and retrieving knowledge, such as factual recall and question answering. Transformers are central to this capability because they can encode information during training…

Token representation strategies within large-scale neural architectures often rely on contextually refined embeddings, yet conventional approaches seldom encode structured relationships explicitly within token interactions. Self-attention…

Natural and artificial audition can in principle acquire different solutions to a given problem. The constraints of the task, however, can nudge the cognitive science and engineering of audition to qualitatively converge, suggesting that a…

Predictive processing theories propose that the brain continuously anticipates upcoming input. However, direct neural evidence for predictive pre-activation during natural language comprehension remains limited and debated. Previous studies…

Word embeddings are a fixed, distributional representation of the context of words in a corpus learned from word co-occurrences. While word embeddings have proven to have many practical uses in natural language processing tasks, they…

Training large language models (LLMs) typically involves pre-training on massive corpora, only to restart the process entirely when new data becomes available. A more efficient and resource-conserving approach would be continual…

Pre-trained deep learning embeddings have consistently shown superior performance over handcrafted acoustic features in speech emotion recognition (SER). However, unlike acoustic features with clear physical meaning, these embeddings lack…

Representation learning plays a central role in structuring internal embeddings to capture the statistical properties of language, influencing the coherence and contextual consistency of generated text. Statistical Coherence Alignment is…

Pretrained language models (PLMs) are today the primary model for natural language processing. Despite their impressive downstream performance, it can be difficult to apply PLMs to new languages, a barrier to making their capabilities…

Large language models (LLMs) can sometimes report the strategies they actually use to solve tasks, yet at other times seem unable to recognize those strategies that govern their behavior. This suggests a limited degree of metacognition -…

Text generating capabilities have undergone a substantial transformation with the introduction of large language models (LLMs). Electroencephalography (EEG)-based text production is still difficult, though, because it requires a lot of data…

The human brain, among its several functions, analyzes the double articulation structure in spoken language, i.e., double articulation analysis (DAA). A hierarchical structure in which words are connected to form a sentence and words are…