相关论文: Sequence-to-Sequence Multi-Modal Speech In-Paintin…

In a noisy environment, a lossy speech signal can be automatically restored by a listener if he/she knows the language well. That is, with the built-in knowledge of a "language model", a listener may effectively suppress noise interference…

We present an approach for unsupervised learning of speech representation disentangling contents and styles. Our model consists of: (1) a local encoder that captures per-frame information; (2) a global encoder that captures per-utterance…

In recent years, neural network based methods for multi-speaker text-to-speech synthesis (TTS) have made significant progress. However, the current speaker encoder models used in these methods still cannot capture enough speaker…

In this study, we propose a deep neural network for reconstructing intelligible speech from silent lip movement videos. We use auditory spectrogram as spectral representation of speech and its corresponding sound generation method resulting…

Visually grounded speech systems learn from paired images and their spoken captions. Recently, there have been attempts to utilize the visually grounded models trained from images and their corresponding text captions, such as CLIP, to…

We present a method for introducing a text encoder into pre-trained end-to-end speech translation systems. It enhances the ability of adapting one modality (i.e., source-language speech) to another (i.e., source-language text). Thus, the…

Speechreading or lipreading is the technique of understanding and getting phonetic features from a speaker's visual features such as movement of lips, face, teeth and tongue. It has a wide range of multimedia applications such as in…

We explore self-supervised models that can be potentially deployed on mobile devices to learn general purpose audio representations. Specifically, we propose methods that exploit the temporal context in the spectrogram domain. One method…

Recent advancements in diffusion models have introduced fast sampling methods that can effectively produce high-quality images in just one or a few denoising steps. Interestingly, when these are distilled from existing diffusion models,…

Building a single universal speech enhancement (SE) system that can handle arbitrary input is a demanded but underexplored research topic. Towards this ultimate goal, one direction is to build a single model that handles diverse audio…

We present a recurrent encoder-decoder deep neural network architecture that directly translates speech in one language into text in another. The model does not explicitly transcribe the speech into text in the source language, nor does it…

Vocoders received renewed attention as main components in statistical parametric text-to-speech (TTS) synthesis and speech transformation systems. Even though there are vocoding techniques give almost accepted synthesized speech, their high…

Video advertisement content structuring aims to segment a given video advertisement and label each segment on various dimensions, such as presentation form, scene, and style. Different from real-life videos, video advertisements contain…

We propose a new encoder-decoder approach to learn distributed sentence representations that are applicable to multiple purposes. The model is learned by using a convolutional neural network as an encoder to map an input sentence into a…

Image inpainting aims at restoring missing region of corrupted images, which has many applications such as image restoration and object removal. However, current GAN-based inpainting models fail to explicitly consider the semantic…

Sequence-to-sequence models provide a simple and elegant solution for building speech recognition systems by folding separate components of a typical system, namely acoustic (AM), pronunciation (PM) and language (LM) models into a single…

Probing is widely used to study which features can be decoded from language model representations. However, the common decoding probe approach has two limitations that we aim to solve with our new encoding probe approach: contributions of…

Lipreading is the task of decoding text from the movement of a speaker's mouth. Traditional approaches separated the problem into two stages: designing or learning visual features, and prediction. More recent deep lipreading approaches are…

Audio captioning is a multi-modal task, focusing on using natural language for describing the contents of general audio. Most audio captioning methods are based on deep neural networks, employing an encoder-decoder scheme and a dataset with…

In this work we propose a novel model-based deep convolutional autoencoder that addresses the highly challenging problem of reconstructing a 3D human face from a single in-the-wild color image. To this end, we combine a convolutional…