Related papers: Multi-Level Transfer Learning from Near-Field to F…
In this paper, we describe our end-to-end multilingual speech translation system submitted to the IWSLT 2021 evaluation campaign on the Multilingual Speech Translation shared task. Our system is built by leveraging transfer learning across…
In this paper, we analyze the behavior and performance of speaker embeddings and the back-end scoring model under domain and language mismatch. We present our findings regarding ResNet-based speaker embedding architectures and show that…
Transfer learning approaches in reinforcement learning aim to assist agents in learning their target domains by leveraging the knowledge learned from other agents that have been trained on similar source domains. For example, recent…
We present a meta-learning approach for adaptive text-to-speech (TTS) with few data. During training, we learn a multi-speaker model using a shared conditional WaveNet core and independent learned embeddings for each speaker. The aim of…
Knowledge Distillation (KD) aims to transfer knowledge in a teacher-student framework, by providing the predictions of the teacher network to the student network in the training stage to help the student network generalize better. It can…
Supervised learning models are typically trained on a single dataset and the performance of these models rely heavily on the size of the dataset, i.e., amount of data available with the ground truth. Learning algorithms try to generalize…
Generalizing to out-of-distribution data while being aware of model fairness is a significant and challenging problem in meta-learning. The goal of this problem is to find a set of fairness-aware invariant parameters of classifier that is…
While few-shot classification has been widely explored with similarity based methods, few-shot sequence labeling poses a unique challenge as it also calls for modeling the label dependencies. To consider both the item similarity and label…
Previous transfer learning methods based on deep network assume the knowledge should be transferred between the same hidden layers of the source domain and the target domains. This assumption doesn't always hold true, especially when the…
This paper proposes a novel approach to address the challenge that pretrained VLA models often fail to effectively improve performance and reduce adaptation costs during standard supervised finetuning (SFT). Some advanced finetuning methods…
Deep learning has been applied to achieve significant progress in emotion recognition. Despite such substantial progress, existing approaches are still hindered by insufficient training data, and the resulting models do not generalize well…
We address the challenge of getting efficient yet accurate recognition systems with limited labels. While recognition models improve with model size and amount of data, many specialized applications of computer vision have severe resource…
Keyword Spotting plays a critical role in enabling hands-free interaction for battery-powered edge devices. Few-Shot Keyword Spotting (FS-KWS) addresses the scalability and adaptability challenges of traditional systems by enabling…
Transfer learning --- transferring learned knowledge --- has brought a paradigm shift in the way models are trained. The lucrative benefits of improved accuracy and reduced training time have shown promise in training models with…
Being expensive and time-consuming to collect massive COVID-19 image samples to train deep classification models, transfer learning is a promising approach by transferring knowledge from the abundant typical pneumonia datasets for COVID-19…
We introduce and analyze a novel approach to the problem of speaker identification in multi-party recorded meetings. Given a speech segment and a set of available candidate profiles, we propose a novel data-driven way to model the distance…
Task transfer, transferring knowledge contained in related tasks, holds the promise of reducing the quantity of labeled data required to fine-tune language models. Dialogue understanding encompasses many diverse tasks, yet task transfer has…
Transfer learning has become an essential technique to exploit information from the source domain to boost performance of the target task. Despite the prevalence in high-dimensional data, heterogeneity and heavy tails are insufficiently…
Deep learning models exhibit limited generalizability across different domains. Specifically, transferring knowledge from available entangled domain features(source/target domain) and categorical features to new unseen categorical features…
Automatic speech recognition (ASR) of single channel far-field recordings with an unknown number of speakers is traditionally tackled by cascaded modules. Recent research shows that end-to-end (E2E) multi-speaker ASR models can achieve…