Related papers: Test-Time Training for Speech

Continual Test-Time Adaptation (CTTA) enables pre-trained models to adapt to continuously evolving domains. Existing methods have improved robustness but typically rely on fixed or batch-level thresholds, which cannot account for varying…

Text attribute transfer aims to automatically rewrite sentences such that they possess certain linguistic attributes, while simultaneously preserving their semantic content. This task remains challenging due to a lack of supervised parallel…

Fine-tuning language models in a downstream task is the standard approach for many state-of-the-art methodologies in the field of NLP. However, when the distribution between the source task and target task drifts, \textit{e.g.},…

In this paper, we study the problem of estimation and learning under temporal distribution shift. Consider an observation sequence of length $n$, which is a noisy realization of a time-varying groundtruth sequence. Our focus is to develop…

Scaling model parameters has become the de facto strategy for improving NLP systems, but it comes with substantial computational costs. Test-Time Scaling (TTS) offers an alternative by allocating more computation at inference: generating…

Text-based speech editing aims to modify specific segments while preserving speaker identity and acoustic context. Existing methods rely on task-specific training, which incurs high data costs and struggles with temporal fidelity in…

We formulate long-context language modeling as a problem in continual learning rather than architecture design. Under this formulation, we only use a standard architecture -- a Transformer with sliding-window attention. However, our model…

Recent work on speech representation models jointly pre-trained with text has demonstrated the potential of improving speech representations by encoding speech and text in a shared space. In this paper, we leverage such shared…

Across engineering and scientific domains, traditional deep learning (TDL) models perform well when training and test data share the same distribution. However, the dynamic nature of real-world data, broadly termed \textit{data shift},…

Transfer learning of diffusion models to smaller target domains is challenging, as naively fine-tuning the model often results in poor generalization. Test-time guidance methods help mitigate this by offering controllable improvements in…

Emotional state recognition through speech is being a very interesting research topic nowadays. Using subliminal information of speech, denominated as prosody, it is possible to recognize the emotional state of the person. One of the main…

Deep learning-based medical image segmentation models often face performance degradation when deployed across various medical centers, largely due to the discrepancies in data distribution. Test Time Adaptation (TTA) methods, which adapt…

Spatio-temporal forecasting is crucial in many domains, such as transportation, meteorology, and energy. However, real-world scenarios frequently present challenges such as signal anomalies, noise, and distributional shifts. Existing…

As the landscape of large language models expands, efficiently finetuning for specific tasks becomes increasingly crucial. At the same time, the landscape of parameter-efficient finetuning methods rapidly expands. Consequently,…

Meta-learning has emerged as a trending technique to tackle few-shot text classification and achieve state-of-the-art performance. However, the performance of existing approaches heavily depends on the inter-class variance of the support…

In deep learning, maintaining model robustness against distribution shifts is critical. This work explores a broad range of possibilities to adapt vision-language foundation models at test-time, with a particular emphasis on CLIP and its…

In deep learning, test-time adaptation has gained attention as a method for model fine-tuning without the need for labeled data. A prime exemplification is the recently proposed test-time prompt tuning for large-scale vision-language models…

The effects of language mismatch impact speech anti-spoofing systems, while investigations and quantification of these effects remain limited. Existing anti-spoofing datasets are mainly in English, and the high cost of acquiring…

Real-world NLP applications often deal with nonstandard text (e.g., dialectal, informal, or misspelled text). However, language models like BERT deteriorate in the face of dialect variation or noise. How do we push BERT's modeling…

Large-scale latent diffusion models (LDMs) excel in content generation across various modalities, but their reliance on phonemes and durations in text-to-speech (TTS) limits scalability and access from other fields. While recent studies…