Related papers: Domain-aware Neural Language Models for Speech Rec…

In task-oriented dialogue systems the dialogue state tracker (DST) component is responsible for predicting the state of the dialogue based on the dialogue history. Current DST approaches rely on a predefined domain ontology, a fact that…

Unsupervised sim-to-real domain adaptation (UDA) for semantic segmentation aims to improve the real-world test performance of a model trained on simulated data. It can save the cost of manually labeling data in real-world applications such…

Domain adaptation becomes more challenging with increasing gaps between source and target domains. Motivated from an empirical analysis on the reliability of labeled source data for the use of distancing target domains, we propose…

Domain adaptive semantic segmentation is the task of generating precise and dense predictions for an unlabeled target domain using a model trained on a labeled source domain. While significant efforts have been devoted to improving…

Mainstream state-of-the-art domain generalization algorithms tend to prioritize the assumption on semantic invariance across domains. Meanwhile, the inherent intra-domain style invariance is usually underappreciated and put on the shelf. In…

Domain adaptation is an important but challenging task. Most of the existing domain adaptation methods struggle to extract the domain-invariant representation on the feature space with entangling domain information and semantic information.…

Deep domain adaptation models learn a neural network in an unlabeled target domain by leveraging the knowledge from a labeled source domain. This can be achieved by learning a domain-invariant feature space. Though the learned…

Speech recognition systems have improved dramatically over the last few years, however, their performance is significantly degraded for the cases of accented or impaired speech. This work explores domain adversarial neural networks (DANN)…

Unsupervised Domain Adaptation (UDA) refers to the method that utilizes annotated source domain data and unlabeled target domain data to train a model capable of generalizing to the target domain data. Domain discrepancy leads to a…

Fast contextual adaptation has shown to be effective in improving Automatic Speech Recognition (ASR) of rare words and when combined with an on-device personalized training, it can yield an even better recognition result. However, the…

The use of low-rank adaptation (LoRA) with frozen pretrained language models (PLMs) has become increasing popular as a mainstream, resource-efficient modeling approach for memory-constrained hardware. In this study, we first explore how to…

Building an automatic speech recognition (ASR) system from scratch requires a large amount of annotated speech data, which is difficult to collect in many languages. However, there are cases where the low-resource language shares a common…

We study the problem of unsupervised domain adaption in the universal scenario, in which only some of the classes are shared between the source and target domains. We present a scoring scheme that is effective in identifying the samples of…

Foundation models (FMs), that are trained on broad data at scale and are adaptable to a wide range of downstream tasks, have brought large interest in the research community. Benefiting from the diverse data sources such as different…

Neural sequence-to-sequence systems deliver state-of-the-art performance for automatic speech recognition. When using appropriate modeling units, e.g., byte-pair encoding, these systems are in principle open vocabulary systems. In practice,…

Voice assistants increasingly use on-device Automatic Speech Recognition (ASR) to ensure speed and privacy. However, due to resource constraints on the device, queries pertaining to complex information domains often require further…

Contextual embedding-based language models trained on large data sets, such as BERT and RoBERTa, provide strong performance across a wide range of tasks and are ubiquitous in modern NLP. It has been observed that fine-tuning these models on…

We present a Lipreading system, i.e. a speech recognition system using only visual features, which uses domain-adversarial training for speaker independence. Domain-adversarial training is integrated into the optimization of a lipreader…

Word embeddings are traditionally trained on a large corpus in an unsupervised setting, with no specific design for incorporating domain knowledge. This can lead to unsatisfactory performances when training data originate from heterogeneous…

It has been previously noted that neural machine translation (NMT) is very sensitive to domain shift. In this paper, we argue that this is a dual effect of the highly lexicalized nature of NMT, resulting in failure for sentences with large…