English
Related papers

Related papers: An investigation on selecting audio pre-trained mo…

200 papers

In the development of neural text-to-speech systems, model pre-training with a large amount of non-target speakers' data is a common approach. However, in terms of ultimately achieved system performance for target speaker(s), the actual…

Audio and Speech Processing · Electrical Eng. & Systems 2021-10-11 Guangyan Zhang , Yichong Leng , Daxin Tan , Ying Qin , Kaitao Song , Xu Tan , Sheng Zhao , Tan Lee

Automated audio captioning (AAC) has developed rapidly in recent years, involving acoustic signal processing and natural language processing to generate human-readable sentences for audio clips. The current models are generally based on the…

Sound · Computer Science 2021-10-13 Zhongjie Ye , Helin Wang , Dongchao Yang , Yuexian Zou

Automated audio captioning is a cross-modal translation task for describing the content of audio clips with natural language sentences. This task has attracted increasing attention and substantial progress has been made in recent years.…

Audio and Speech Processing · Electrical Eng. & Systems 2024-07-02 Xinhao Mei , Xubo Liu , Jianyuan Sun , Mark D. Plumbley , Wenwu Wang

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…

Sound · Computer Science 2020-07-10 Emre Çakır , Konstantinos Drossos , Tuomas Virtanen

Training data is at the core of any successful text-to-image models. The quality and descriptiveness of image text are crucial to a model's performance. Given the noisiness and inconsistency in web-scraped datasets, recent works shifted…

Computer Vision and Pattern Recognition · Computer Science 2025-06-23 Manuel Brack , Sudeep Katakol , Felix Friedrich , Patrick Schramowski , Hareesh Ravi , Kristian Kersting , Ajinkya Kale

Generative models have shown significant achievements in audio generation tasks. However, existing models struggle with complex and detailed prompts, leading to potential performance degradation. We hypothesize that this problem stems from…

Emotions lie on a continuum, but current models treat emotions as a finite valued discrete variable. This representation does not capture the diversity in the expression of emotion. To better represent emotions we propose the use of natural…

Sound · Computer Science 2023-12-08 Hira Dhamyal , Benjamin Elizalde , Soham Deshmukh , Huaming Wang , Bhiksha Raj , Rita Singh

The task of video captioning, that is, the automatic generation of sentences describing a sequence of actions in a video, has attracted an increasing attention recently. The complex and high-dimensional representation of video data makes it…

Computer Vision and Pattern Recognition · Computer Science 2020-10-13 Menatallh Hammad , May Hammad , Mohamed Elshenawy

Distributional shift is a central challenge in the deployment of machine learning models as they can be ill-equipped for real-world data. This is particularly evident in text-to-audio generation where the encoded representations are easily…

Audio captioning aims at using natural language to describe the content of an audio clip. Existing audio captioning systems are generally based on an encoder-decoder architecture, in which acoustic information is extracted by an audio…

Audio and Speech Processing · Electrical Eng. & Systems 2022-03-29 Xubo Liu , Xinhao Mei , Qiushi Huang , Jianyuan Sun , Jinzheng Zhao , Haohe Liu , Mark D. Plumbley , Volkan Kılıç , Wenwu Wang

Recent focus in video captioning has been on designing architectures that can consume both video and text modalities, and using large-scale video datasets with text transcripts for pre-training, such as HowTo100M. Though these approaches…

Computer Vision and Pattern Recognition · Computer Science 2023-06-23 Yuhan Shen , Linjie Yang , Longyin Wen , Haichao Yu , Ehsan Elhamifar , Heng Wang

Feature representations derived from models pre-trained on large-scale datasets have shown their generalizability on a variety of audio analysis tasks. Despite this generalizability, however, task-specific features can outperform if…

Audio and Speech Processing · Electrical Eng. & Systems 2022-06-13 Yun-Ning Hung , Alexander Lerch

Recent advancements in foundation models have sparked interest in respiratory audio foundation models. However, the effectiveness of applying conventional pre-training schemes to datasets that are small-sized and lack diversity has not been…

Audio and Speech Processing · Electrical Eng. & Systems 2025-05-22 Daisuke Niizumi , Daiki Takeuchi , Masahiro Yasuda , Binh Thien Nguyen , Yasunori Ohishi , Noboru Harada

We demonstrate that language models pre-trained on codified (discretely-encoded) music audio learn representations that are useful for downstream MIR tasks. Specifically, we explore representations from Jukebox (Dhariwal et al. 2020): a…

Sound · Computer Science 2021-07-14 Rodrigo Castellon , Chris Donahue , Percy Liang

Semantically-aligned $(speech, image)$ datasets can be used to explore "visually-grounded speech". In a majority of existing investigations, features of an image signal are extracted using neural networks "pre-trained" on other tasks (e.g.,…

Machine Learning · Computer Science 2020-10-30 Masood S. Mortazavi

We study the usability of pre-trained weakly supervised audio tagging (AT) models as feature extractors for general audio representations. We mainly analyze the feasibility of transferring those embeddings to other tasks within the speech…

Sound · Computer Science 2022-10-03 Heinrich Dinkel , Zhiyong Yan , Yongqing Wang , Junbo Zhang , Yujun Wang

Compared with ample visual-text pre-training research, few works explore audio-text pre-training, mostly due to the lack of sufficient parallel audio-text data. Most existing methods incorporate the visual modality as a pivot for audio-text…

Sound · Computer Science 2024-03-06 Xuenan Xu , Zhiling Zhang , Zelin Zhou , Pingyue Zhang , Zeyu Xie , Mengyue Wu , Kenny Q. Zhu

Lifelong audio feature extraction involves learning new sound classes incrementally, which is essential for adapting to new data distributions over time. However, optimizing the model only on new data can lead to catastrophic forgetting of…

Audio and Speech Processing · Electrical Eng. & Systems 2024-02-08 Xilin Jiang , Yinghao Aaron Li , Nima Mesgarani

We study the impact of visual assistance for automated audio captioning. Utilizing multi-encoder transformer architectures, which have previously been employed to introduce vision-related information in the context of sound event detection,…

Audio and Speech Processing · Electrical Eng. & Systems 2023-02-22 Wim Boes , Hugo Van hamme

Automated audio captioning (AAC) is the task of automatically creating textual descriptions (i.e. captions) for the contents of a general audio signal. Most AAC methods are using existing datasets to optimize and/or evaluate upon. Given the…

Sound · Computer Science 2021-07-19 Jan Berg , Konstantinos Drossos