相关论文: Fact sheet: Automatic Self-Reported Personality Re…
As equality issues in the use of face recognition have garnered a lot of attention lately, greater efforts have been made to debiased deep learning models to improve fairness to minorities. However, there is still no clear definition nor…
In recent years, numerous studies have been published dealing with the effect of individual characteristics of pedestrians on the fundamental diagram. These studies compared cumulative data on individuals in a group homogeneous in terms of…
Training data are critical in face recognition systems. However, labeling a large scale face data for a particular domain is very tedious. In this paper, we propose a method to automatically and incrementally construct datasets from massive…
The diagnosis and treatment of individuals with communication disorders offers many opportunities for the application of speech technology, but research so far has not adequately considered: the diversity of conditions, the role of…
Deep learning technologies have brought us many models that outperform human beings on a few benchmarks. An interesting question is: can these models well solve real-world problems with similar settings (e.g., identical input/output) to the…
Pretrained multilingual contextual representations have shown great success, but due to the limits of their pretraining data, their benefits do not apply equally to all language varieties. This presents a challenge for language varieties…
Few-shot classification refers to learning a classifier for new classes given only a few examples. While a plethora of models have emerged to tackle it, we find the procedure and datasets that are used to assess their progress lacking. To…
Synthetic data becomes crucial for large language model training, but its effectiveness is highly inconsistent. We provide an information-theoretic account of this inconsistency: synthetic data improves a model only when the…
Personality traits have long been studied as predictors of human behavior. Recent advances in Large Language Models (LLMs) suggest similar patterns may emerge in artificial systems, with advanced LLMs displaying consistent behavioral…
Auditory and visual signals usually present together and correlate with each other, not only in natural environments but also in clinical settings. However, the audio-visual modelling in the latter case can be more challenging, due to the…
Spoken language understanding (SLU) tasks involve mapping from speech audio signals to semantic labels. Given the complexity of such tasks, good performance might be expected to require large labeled datasets, which are difficult to collect…
Synthetic personas are widely used to condition large language models (LLMs) for social simulation, yet most personas are still constructed from coarse sociodemographic attributes or summaries. We revisit persona creation by introducing…
Evidence-based fact checking aims to verify the truthfulness of a claim against evidence extracted from textual sources. Learning a representation that effectively captures relations between a claim and evidence can be challenging. Recent…
In this work, we define barge-in verification as a supervised learning task where audio-only information is used to classify user spoken dialogue into true and false barge-ins. Following the success of pre-trained models, we use low-level…
We present a novel approach to multilingual audio-visual speech recognition tasks by introducing a single model on a multilingual dataset. Motivated by a human cognitive system where humans can intuitively distinguish different languages…
In this position paper, we argue that human baselines in foundation model evaluations must be more rigorous and more transparent to enable meaningful comparisons of human vs. AI performance, and we provide recommendations and a reporting…
Person re-identification has achieved great progress with deep convolutional neural networks. However, most previous methods focus on learning individual appearance feature embedding, and it is hard for the models to handle difficult…
This study employs deep learning techniques to explore four speaker profiling tasks on the TIMIT dataset, namely gender classification, accent classification, age estimation, and speaker identification, highlighting the potential and…
It has been postulated that a good representation is one that disentangles the underlying explanatory factors of variation. However, it remains an open question what kind of training framework could potentially achieve that. Whereas most…
Self-report questionnaires have long been used to assess LLM personality traits, yet they fail to capture behavioral nuances due to biases and meta-knowledge contamination. This paper proposes a novel multi-observer framework for…