相关论文: CLAP-ART: Automated Audio Captioning with Semantic…

Audio captioning quality metrics which are typically borrowed from the machine translation and image captioning areas measure the degree of overlap between predicted tokens and gold reference tokens. In this work, we consider a metric…

The massive growth of self-supervised learning (SSL) has been witnessed in language, vision, speech, and audio domains over the past few years. While discrete label prediction is widely adopted for other modalities, the state-of-the-art…

Lexically constrained text generation aims to control the generated text by incorporating some pre-specified keywords into the output. Previous work injects lexical constraints into the output by controlling the decoding process or refining…

Contrastively pretrained audio-language models (e.g., CLAP) excel at clip-level understanding but struggle with frame-level tasks. Existing extensions fail to exploit the varying granularity of real-world audio-text data, where massive…

Supervised image captioning approaches have made great progress, but it is challenging to collect high-quality human-annotated image-text data. Recently, large-scale vision and language models (e.g., CLIP) and large-scale generative…

While existing speech audio codecs designed for compression exploit limited forms of temporal redundancy and allow for multi-scale representations, they tend to represent all features of audio in the same way. In contrast, generative voice…

Pre-trained vision-language models, e.g., CLIP, working with manually designed prompts have demonstrated great capacity of transfer learning. Recently, learnable prompts achieve state-of-the-art performance, which however are prone to…

Contrastive Language-Image Pre-training (CLIP) has significantly boosted the performance of various vision-language tasks by scaling up the dataset with image-text pairs collected from the web. However, the presence of intrinsic noise and…

In acoustic signal processing, the target signals usually carry semantic information, which is encoded in a hierarchal structure of short and long-term contexts. However, the background noise distorts these structures in a nonuniform way.…

In this paper we study a brand new topic of interactive image captioning with human in the loop. Different from automated image captioning where a given test image is the sole input in the inference stage, we have access to both the test…

Recent semantic communication methods explore effective ways to expand the communication paradigm and improve the system performance of the communication systems. Nonetheless, the common problem of these methods is that the essence of…

While Large Audio-Language Models (LALMs) have advanced audio captioning, robust evaluation remains difficult. Reference-based metrics are expensive and often fail to assess acoustic fidelity, while Contrastive Language-Audio Pretraining…

It is an open challenge to obtain high quality training data, especially captions, for text-to-audio models. Although prior methods have leveraged \textit{text-only language models} to augment and improve captions, such methods have…

We present LARP, a novel video tokenizer designed to overcome limitations in current video tokenization methods for autoregressive (AR) generative models. Unlike traditional patchwise tokenizers that directly encode local visual patches…

We propose a novel approach to semi-supervised automatic speech recognition (ASR). We first exploit a large amount of unlabeled audio data via representation learning, where we reconstruct a temporal slice of filterbank features from past…

Audio captioning aims to generate text descriptions from environmental sounds. One challenge of audio captioning is the difficulty of the generalization due to the lack of audio-text paired training data. In this work, we propose a simple…

Despite significant progress in image captioning, generating accurate and descriptive captions remains a long-standing challenge. In this study, we propose Attention-Guided Image Captioning (AGIC), which amplifies salient visual regions…

Animal vocalizations provide crucial insights for wildlife assessment, particularly in complex environments such as forests, aiding species identification and ecological monitoring. Recent advances in deep learning have enabled automatic…

Semantic communications has received growing interest since it can remarkably reduce the amount of data to be transmitted without missing critical information. Most existing works explore the semantic encoding and transmission for text and…

Modern image captioning models are usually trained with text similarity objectives. However, since reference captions in public datasets often describe the most salient common objects, models trained with text similarity objectives tend to…