Related papers: TADA: Task-Agnostic Dialect Adapters for English
Existing large language models (LLMs) that mainly focus on Standard American English (SAE) often lead to significantly worse performance when being applied to other English dialects. While existing mitigations tackle discrepancies for…
Intermediate training of pre-trained transformer-based language models on domain-specific data leads to substantial gains for downstream tasks. To increase efficiency and prevent catastrophic forgetting alleviated from full domain-adaptive…
Test-time domain adaptation (TTDA) is an excellent method which helps generalize models across domains, tasks, and distributions without the use of labeled datasets. Thus, TTDA is very useful in natural language processing (NLP) in the…
Large Language Models (LLMs) are trained on corpora disproportionally weighted in favor of Standard American English. As a result, speakers of other dialects experience significantly more failures when interacting with these technologies.…
Unsupervised Domain Adaptation (UDA) aims to bridge the gap between a source domain, where labelled data are available, and a target domain only represented with unlabelled data. If domain invariant representations have dramatically…
While Large language models (LLMs) have demonstrated considerable capabilities across various natural language tasks, they often fall short of the performance achieved by domain-specific state-of-the-art models. One potential approach to…
Neural Network Language Models (NNLMs) for Virtual Assistants (VAs) are generally language-, region-, and in some cases, device-dependent, which increases the effort to scale and maintain them. Combining NNLMs for one or more of the…
Test-time adaptation with pre-trained vision-language models (VLMs) has attracted increasing attention for tackling the issue of distribution shift during the test phase. While prior methods have shown effectiveness in addressing…
Spoken Language Models (SLMs) are increasingly central to modern speech-driven applications, but performance degrades under acoustic shift - real-world noise, reverberation, and microphone variation. Prior solutions rely on offline domain…
More than 80% of the 1.6B English speakers do not use Standard American English (SAE), yet LLMs often fail to correctly identify non-SAE dialects and generate stereotyped responses for their speakers. We introduce DialectLLM, the first…
Temporal Action Localization (TAL) is a complex task that poses relevant challenges, particularly when attempting to generalize on new -- unseen -- domains in real-world applications. These scenarios, despite realistic, are often neglected…
We propose TANDA, an effective technique for fine-tuning pre-trained Transformer models for natural language tasks. Specifically, we first transfer a pre-trained model into a model for a general task by fine-tuning it with a large and…
Speaker verification systems often degrade significantly when there is a language mismatch between training and testing data. Being able to improve cross-lingual speaker verification system using unlabeled data can greatly increase the…
Operator learning for time-dependent partial differential equations (PDEs) has seen rapid progress in recent years, enabling efficient approximation of complex spatiotemporal dynamics. However, most existing methods rely on fixed time step…
Speaker adaptive training (SAT) of neural network acoustic models learns models in a way that makes them more suitable for adaptation to test conditions. Conventionally, model-based speaker adaptive training is performed by having a set of…
Domain adaptation is a potential method to train a powerful deep neural network, which can handle the absence of labeled data. More precisely, domain adaptation solving the limitation called dataset bias or domain shift when the training…
We propose three regularization-based speaker adaptation approaches to adapt the attention-based encoder-decoder (AED) model with very limited adaptation data from target speakers for end-to-end automatic speech recognition. The first…
The end-to-end ASR model is often desired in the streaming multilingual scenario since it is easier to deploy and can benefit from pre-trained speech models such as powerful foundation models. Meanwhile, the heterogeneous nature and…
We propose two methods to make unsupervised domain adaptation (UDA) more parameter efficient using adapters, small bottleneck layers interspersed with every layer of the large-scale pre-trained language model (PLM). The first method…
Test-time adaptation with pre-trained vision-language models has attracted increasing attention for tackling distribution shifts during the test time. Though prior studies have achieved very promising performance, they involve intensive…