SpurAudio benchmark shows state-of-the-art few-shot audio classifiers suffer large performance drops when background correlations are disrupted, even in large pretrained models.
hub
preprint arXiv:1904.05862 , year=
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
hub tools
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 10roles
background 1polarities
background 1representative citing papers
Unimodal model representations converge to a relational structure captured by the Indra representation via V-enriched Yoneda embedding, which is unique and structure-preserving and improves cross-model and cross-modal robustness when instantiated with angular distance.
Spoof-SUPERB benchmark shows large-scale discriminative SSL models such as XLS-R, UniSpeech-SAT, and WavLM Large outperform others in audio deepfake detection and maintain robustness under acoustic degradations.
The paper introduces phoneme recognition using articulatory features as a proxy metric for evaluating articulatory speech synthesis quality from phonetic sequences.
LetsTalk combines a multimodal diffusion transformer, noise-regularized memory bank, deep compression autoencoder, and symbiotic/direct fusion schemes to achieve state-of-the-art quality and efficiency in long-duration talking video generation.
Adding register tokens to Vision Transformers eliminates high-norm background artifacts and raises state-of-the-art performance on dense visual prediction tasks.
HighSync is a diffusion-based lip synchronization system that operates natively at 512x512 resolution by eliminating data leakage to enforce genuine audio dependence and reports state-of-the-art results on quality and sync metrics.
An adaptive cross-modal gating network improves depression detection from speech by selectively weighting sparse relevant segments across acoustic and textual modalities.
EGI integrates four existing AI components for real-time multimodal emotion monitoring and feedback in simulated agile meetings, reporting 10% WER and improved self-awareness for Scrum Masters.
A survey provides a task-based formalization of meta-learning and meta-RL while chronicling algorithms that lead to DeepMind's Adaptive Agent.
citing papers explorer
-
SpurAudio: A Benchmark for Studying Shortcut Learning in Few-Shot Audio Classification
SpurAudio benchmark shows state-of-the-art few-shot audio classifiers suffer large performance drops when background correlations are disrupted, even in large pretrained models.
-
The Indra Representation Hypothesis for Multimodal Alignment
Unimodal model representations converge to a relational structure captured by the Indra representation via V-enriched Yoneda embedding, which is unique and structure-preserving and improves cross-model and cross-modal robustness when instantiated with angular distance.
-
A SUPERB-Style Benchmark of Self-Supervised Speech Models for Audio Deepfake Detection
Spoof-SUPERB benchmark shows large-scale discriminative SSL models such as XLS-R, UniSpeech-SAT, and WavLM Large outperform others in audio deepfake detection and maintain robustness under acoustic degradations.
-
Evaluating Speech Articulation Synthesis with Articulatory Phoneme Recognition
The paper introduces phoneme recognition using articulatory features as a proxy metric for evaluating articulatory speech synthesis quality from phonetic sequences.
-
Multimodal Diffusion Transformer with Memory Bank for Scalable Long-Duration Talking Video Generation
LetsTalk combines a multimodal diffusion transformer, noise-regularized memory bank, deep compression autoencoder, and symbiotic/direct fusion schemes to achieve state-of-the-art quality and efficiency in long-duration talking video generation.
-
Vision Transformers Need Registers
Adding register tokens to Vision Transformers eliminates high-norm background artifacts and raises state-of-the-art performance on dense visual prediction tasks.
-
HighSync: High-Quality Lip Synchronization via Latent Diffusion Models
HighSync is a diffusion-based lip synchronization system that operates natively at 512x512 resolution by eliminating data leakage to enforce genuine audio dependence and reports state-of-the-art results on quality and sync metrics.
-
Learning to Attend to Depression-Related Patterns: An Adaptive Cross-Modal Gating Network for Depression Detection
An adaptive cross-modal gating network improves depression detection from speech by selectively weighting sparse relevant segments across acoustic and textual modalities.
-
EGI: A Multimodal Emotional AI Framework for Enhancing Scrum Master Real-time Self-Awareness
EGI integrates four existing AI components for real-time multimodal emotion monitoring and feedback in simulated agile meetings, reporting 10% WER and improved self-awareness for Scrum Masters.
-
Meta-Learning and Meta-Reinforcement Learning -- Tracing the Path towards DeepMind's Adaptive Agent
A survey provides a task-based formalization of meta-learning and meta-RL while chronicling algorithms that lead to DeepMind's Adaptive Agent.