Related papers: Robust Dialogue State Tracking with Weak Supervisi…

Neural abstractive summarization methods often require large quantities of labeled training data. However, labeling large amounts of summarization data is often prohibitive due to time, financial, and expertise constraints, which has…

Over the last few years, deep learning has grown in popularity for speaker verification, identification, and diarization. Inarguably, a significant part of this success is due to the demonstrated effectiveness of their speaker…

We address the problem of detecting speech directed to a device that does not contain a specific wake-word. Specifically, we focus on audio coming from a touch-based invocation. Mitigating virtual assistants (VAs) activation due to…

Active learning is an iterative labeling process that is used to obtain a small labeled subset, despite the absence of labeled data, thereby enabling to train a model for supervised tasks such as text classification. While active learning…

High accuracy speech recognition requires a large amount of transcribed data for supervised training. In the absence of such data, domain adaptation of a well-trained acoustic model can be performed, but even here, high accuracy usually…

Multiple instance learning (MIL) has become the standard learning paradigm for distantly supervised relation extraction (DSRE). However, due to relation extraction being performed at bag level, MIL has significant hardware requirements for…

In recent years, text summarization methods have attracted much attention again thanks to the researches on neural network models. Most of the current text summarization methods based on neural network models are supervised methods which…

Detecting medical conditions from speech acoustics is fundamentally a weakly-supervised learning problem: a single, often noisy, session-level label must be linked to nuanced patterns within a long, complex audio recording. This task is…

Unsupervised online 3D instance segmentation is a fundamental yet challenging task, as it requires maintaining consistent object identities across LiDAR scans without relying on annotated training data. Existing methods, such as UNIT, have…

We propose an unsupervised adaptation framework, Self-TAught Recognizer (STAR), which leverages unlabeled data to enhance the robustness of automatic speech recognition (ASR) systems in diverse target domains, such as noise and accents.…

Pre-trained vision-language models learn massive data to model unified representations of images and natural languages, which can be widely applied to downstream machine learning tasks. In addition to zero-shot inference, in order to better…

Recent efforts in Spoken Dialogue Modeling aim to synthesize spoken dialogue without the need for direct transcription, thereby preserving the wealth of non-textual information inherent in speech. However, this approach faces a challenge…

Diffusion models have gained attention for their ability to represent complex distributions and incorporate uncertainty, making them ideal for robust predictions in the presence of noisy or incomplete data. In this study, we develop and…

Sparsity is a desirable attribute. It can lead to more efficient and more effective representations compared to the dense model. Meanwhile, learning sparse latent representations has been a challenging problem in the field of computer…

Training deep neural networks (DNNs) with limited supervision has been a popular research topic as it can significantly alleviate the annotation burden. Self-training has been successfully applied in semi-supervised learning tasks, but one…

Dialogue State Tracking (DST) is an essential element of conversational AI with the objective of deeply understanding the conversation context and leading it toward answering user requests. Due to high demands for open-domain and multi-turn…

For training a few-shot keyword spotting (FS-KWS) model, a large labeled dataset containing massive target keywords has known to be essential to generalize to arbitrary target keywords with only a few enrollment samples. To alleviate the…

State-of-the-art speaker verification systems are inherently dependent on some kind of human supervision as they are trained on massive amounts of labeled data. However, manually annotating utterances is slow, expensive and not scalable to…

Considering the abundance of unlabeled speech data and the high labeling costs, unsupervised learning methods can be essential for better system development. One of the most successful methods is contrastive self-supervised methods, which…

Self-training has been shown to be helpful in addressing data scarcity for many domains, including vision, speech, and language. Specifically, self-training, or pseudo-labeling, labels unsupervised data and adds that to the training pool.…