相关论文: Geometric Analysis of Speech Representation Spaces…

Speech signals encode emotional, linguistic, and pathological information within a shared acoustic channel; however, disentanglement is typically assessed indirectly through downstream task performance. We introduce an information-theoretic…

Speech intelligibility assessment plays an important role in the therapy of patients suffering from pathological speech disorders. Automatic and objective measures are desirable to assist therapists in their traditionally subjective and…

Neural speech models build deeply entangled internal representations, which capture a variety of features (e.g., fundamental frequency, loudness, syntactic category, or semantic content of a word) in a distributed encoding. This complexity…

We introduce a multi-level analysis framework for examining semantic geometry in multilingual embeddings, implemented through Semanscope (a visualization tool that applies PHATE manifold learning across four linguistic levels). Analysis of…

We previously introduced a training-free method for dysarthria severity assessment based on d-prime separability of phonological feature subspaces in frozen self-supervised speech representations, validated on 890 speakers across 5…

Large-scale end-to-end models such as Whisper have shown strong performance on diverse speech tasks, but their internal behavior on pathological speech remains poorly understood. Understanding how dysarthric speech is represented across…

Understanding the representations of different languages in multilingual language models is essential for comprehending their cross-lingual properties, predicting their performance on downstream tasks, and identifying any biases across…

The detection of pathologies from speech features is usually defined as a binary classification task with one class representing a specific pathology and the other class representing healthy speech. In this work, we train neural networks,…

We developed two machine learning frameworks that could assist in automated litho-stratigraphic interpretation of seismic volumes without any manual hand labeling from an experienced seismic interpreter. The first framework is an…

Dysarthric speech severity assessment typically requires trained clinicians or supervised models built from labelled pathological speech, limiting scalability across languages and clinical settings. We present a training-free method that…

We assess how multilingual language models maintain a shared multilingual representation space while still encoding language-sensitive information in each language. Using XLM-R as a case study, we show that languages occupy similar linear…

Speech and language technologies offer valuable opportunities for supporting mental health assessment through objective and interpretable cues. We present a systematic feature-based analysis framework leveraging perceptually grounded…

Disentangled representation learning in speech processing has lagged behind other domains, largely due to the lack of datasets with annotated generative factors for robust evaluation. To address this, we propose SynSpeech, a novel…

Dysarthria is a motor speech disorder that results in slow and often incomprehensible speech. Speech intelligibility significantly impacts communication, leading to barriers in social interactions. Dysarthria is often a characteristic of…

Disentangling uncorrelated information in speech utterances is a crucial research topic within speech community. Different speech-related tasks focus on extracting distinct speech representations while minimizing the affects of other…

Traditional screening practices for anxiety and depression pose an impediment to monitoring and treating these conditions effectively. However, recent advances in NLP and speech modelling allow textual, acoustic, and hand-crafted…

We describe a PubMed scale retrieval framework that separates semantic interpretation from metric geometry. A large language model expands a natural language query into concise biomedical phrases; retrieval then operates in a fixed, mean…

Word embeddings represent language vocabularies as clouds of $d$-dimensional points. We investigate how information is conveyed by the general shape of these clouds, instead of representing the semantic meaning of each token. Specifically,…

Investigating linguistic relationships on a global scale requires analyzing diverse features such as syntax, phonology and prosody, which evolve at varying rates influenced by internal diversification, language contact, and sociolinguistic…

Patient education materials for solid-organ transplantation vary substantially across U.S. centers, yet no systematic method exists to quantify this heterogeneity at scale. We introduce a framework that grounds the same patient questions in…