Related papers: Effective Slogan Generation with Noise Perturbatio…

Noise-robust speech recognition systems require large amounts of training data including noisy speech data and corresponding transcripts to achieve state-of-the-art performances in face of various practical environments. However, such…

Generative models are now capable of synthesizing images, speeches, and videos that are hardly distinguishable from authentic contents. Such capabilities cause concerns such as malicious impersonation and IP theft. This paper investigates a…

Current state-of-the-art text generators build on powerful language models such as GPT-2, achieving impressive performance. However, to avoid degenerate text, they require sampling from a modified softmax, via temperature parameters or…

With the advances of deep learning techniques, text generation is attracting increasing interest in the artificial intelligence (AI) community, because of its wide applications and because it is an essential component of AI. Traditional…

We explore the task of improving persona consistency of dialogue agents. Recent models tackling consistency often train with additional Natural Language Inference (NLI) labels or attach trained extra modules to the generative agent for…

Generative Adversarial Networks (GANs) for text generation have recently received many criticisms, as they perform worse than their MLE counterparts. We suspect previous text GANs' inferior performance is due to the lack of a reliable…

Widely used evaluation metrics for text generation either do not work well with longer texts or fail to evaluate all aspects of text quality. In this paper, we introduce a new metric called SMART to mitigate such limitations. Specifically,…

Generative adversarial nets (GAN) has been successfully introduced for generating text to alleviate the exposure bias. However, discriminators in these models only evaluate the entire sequence, which causes feedback sparsity and mode…

Modeling and synthesizing real sRGB noise is crucial for various low-level vision tasks, such as building datasets for training image denoising systems. The distribution of real sRGB noise is highly complex and affected by a multitude of…

Generative spoken language models pretrained on large-scale raw audio can continue a speech prompt with appropriate content while preserving attributes like speaker and emotion, serving as foundation models for spoken dialogue. In prior…

Category text generation receives considerable attentions since it is beneficial for various natural language processing tasks. Recently, the generative adversarial network (GAN) has attained promising performance in text generation,…

The Generative Adversarial Network (GAN) has achieved great success in generating realistic (real-valued) synthetic data. However, convergence issues and difficulties dealing with discrete data hinder the applicability of GAN to text. We…

The Visual Dialogue task requires an agent to engage in a conversation about an image with a human. It represents an extension of the Visual Question Answering task in that the agent needs to answer a question about an image, but it needs…

In this paper, we propose the coarse-to-fine optimization for the task of speech enhancement. Cosine similarity loss [1] has proven to be an effective metric to measure similarity of speech signals. However, due to the large variance of the…

Most sentence embedding techniques heavily rely on expensive human-annotated sentence pairs as the supervised signals. Despite the use of large-scale unlabeled data, the performance of unsupervised methods typically lags far behind that of…

A major issue with using deep learning models in sensitive applications is that they provide no explanation for their output. To address this problem, unsupervised selective rationalization produces rationales alongside predictions by…

With the advancement of speech synthesis technology, users have higher expectations for the naturalness and expressiveness of synthesized speech. But previous research ignores the importance of prompt selection. This study proposes a…

Conventional Generative Adversarial Networks (GANs) for text generation tend to have issues of reward sparsity and mode collapse that affect the quality and diversity of generated samples. To address the issues, we propose a novel…

Learning with Noisy Labels (LNL) has become an appealing topic, as imperfectly annotated data are relatively cheaper to obtain. Recent state-of-the-art approaches employ specific selection mechanisms to separate clean and noisy samples and…

In task-oriented conversation systems, natural language generation systems that generate sentences with specific information related to conversation flow are useful. Our study focuses on language generation by considering various…