Related papers: Using Speech Technology for Quantifying Behavioral…

We propose supervised systems for speech activity detection (SAD) and speaker identification (SID) tasks in Fearless Steps Challenge Phase-2. The proposed systems for both the tasks share a common convolutional neural network (CNN)…

Pre-trained language models (PLM) have demonstrated their effectiveness for a broad range of information retrieval and natural language processing tasks. As the core part of PLM, multi-head self-attention is appealing for its ability to…

Self-attention has been a huge success for many downstream tasks in NLP, which led to exploration of applying self-attention to speech problems as well. The efficacy of self-attention in speech applications, however, seems not fully blown…

Compared to large speech foundation models, small distilled models exhibit degraded noise robustness. The student's robustness can be improved by introducing noise at the inputs during pre-training. Despite this, using the standard…

Longitudinal passive sensing enables continuous health prediction, yet models often fail under cross-dataset distribution shifts. Traditional ML overfits cohort-specific artifacts, while Large Language Models (LLMs) struggle to reason…

Knowledge distillation is a key technique for transferring the capabilities of large language models (LLMs) into smaller, more efficient student models. Existing distillation approaches often overlook two critical factors: the learning…

Large Language Models (LLMs) can be adapted to extend their text capabilities to speech inputs. However, these speech-adapted LLMs consistently underperform their text-based counterparts--and even cascaded pipelines--on language…

Early diagnosis of Alzheimer's disease (AD) is crucial in facilitating preventive care and to delay further progression. Speech based automatic AD screening systems provide a non-intrusive and more scalable alternative to other clinical…

Post-Traumatic Stress Disorder (PTSD) remains underdiagnosed in clinical settings, presenting opportunities for automated detection to identify patients. This study evaluates natural language processing approaches for detecting PTSD from…

Speech intelligibility can be affected by multiple factors, such as noisy environments, channel distortions or physiological issues. In this work, we deal with the problem of automatic prediction of the speech intelligibility level in this…

Recent diffusion-based text-to-speech (TTS) models achieve high naturalness and expressiveness, yet often suffer from speaker drift, a subtle, gradual shift in perceived speaker identity within a single utterance. This underexplored…

MTL is a learning paradigm that effectively leverages both task-specific and shared information to address multiple related tasks simultaneously. In contrast to STL, MTL offers a suite of benefits that enhance both the training process and…

Recent work has shown that augmenting environments with language descriptions improves policy learning. However, for environments with complex language abstractions, learning how to ground language to observations is difficult due to…

The escalating scale and cost of Large Language Models (LLMs) training necessitate accurate pre-training prediction of downstream task performance for comprehensive understanding of scaling properties. This is challenged by: 1) the…

Signal Temporal Logic (STL) is a formalism used to rigorously specify requirements of cyberphysical systems (CPS), i.e., systems mixing digital or discrete components in interaction with a continuous environment or analog com- ponents. STL…

The intrinsic dynamics and event-driven nature of spiking neural networks (SNNs) make them excel in processing temporal information by naturally utilizing embedded time sequences as time steps. Recent studies adopting this approach have…

Speech Activity Detection (SAD), locating speech segments within an audio recording, is a main part of most speech technology applications. Robust SAD is usually more difficult in noisy conditions with varying signal-to-noise ratios (SNR).…

Low latency speech human-machine communication is becoming increasingly necessary as speech technology advances quickly in the last decade. One of the primary factors behind the advancement of speech technology is self-supervised learning.…

Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide range of instruction-following tasks, yet their grasp of nuanced social science concepts remains underexplored. This paper examines whether LLMs can…

Social Event Detection (SED) aims to identify significant events from social streams, and has a wide application ranging from public opinion analysis to risk management. In recent years, Graph Neural Network (GNN) based solutions have…