Zobrazeno 21 - 30
of 79
pro vyhledávání: '"Liu, Haohe"'
Sounds carry an abundance of information about activities and events in our everyday environment, such as traffic noise, road works, music, or people talking. Recent machine learning methods, such as convolutional neural networks (CNNs), have been sh
Externí odkaz:
http://arxiv.org/abs/2305.18665
Autor:
Liang, Jinhua, Liu, Xubo, Liu, Haohe, Phan, Huy, Benetos, Emmanouil, Plumbley, Mark D., Wang, Wenwu
We presented the Treff adapter, a training-efficient adapter for CLAP, to boost zero-shot classification performance by making use of a small set of labelled data. Specifically, we designed CALM to retrieve the probability distribution of text-audio
Externí odkaz:
http://arxiv.org/abs/2305.17719
Foley sound presents the background sound for multimedia content and the generation of Foley sound involves computationally modelling sound effects with specialized techniques. In this work, we proposed a system for DCASE 2023 challenge task 7: Foley
Externí odkaz:
http://arxiv.org/abs/2305.15905
Autor:
Nolasco, Inês, Singh, Shubhr, Morfi, Veronica, Lostanlen, Vincent, Strandburg-Peshkin, Ariana, Vidaña-Vila, Ester, Gill, Lisa, Pamuła, Hanna, Whitehead, Helen, Kiskin, Ivan, Jensen, Frants H., Morford, Joe, Emmerson, Michael G., Versace, Elisabetta, Grout, Emily, Liu, Haohe, Stowell, Dan
Automatic detection and classification of animal sounds has many applications in biodiversity monitoring and animal behaviour. In the past twenty years, the volume of digitised wildlife sound available has massively increased, and automatic classific
Externí odkaz:
http://arxiv.org/abs/2305.13210
Autor:
Kong, Qiuqiang, Chen, Ke, Liu, Haohe, Du, Xingjian, Berg-Kirkpatrick, Taylor, Dubnov, Shlomo, Plumbley, Mark D.
Universal source separation (USS) is a fundamental research task for computational auditory scene analysis, which aims to separate mono recordings into individual source tracks. There are three potential challenges awaiting the solution to the audio
Externí odkaz:
http://arxiv.org/abs/2305.07447
Autor:
Mei, Xinhao, Meng, Chutong, Liu, Haohe, Kong, Qiuqiang, Ko, Tom, Zhao, Chengqi, Plumbley, Mark D., Zou, Yuexian, Wang, Wenwu
The advancement of audio-language (AL) multimodal learning tasks has been significant in recent years. However, researchers face challenges due to the costly and time-consuming collection process of existing audio-language datasets, which are limited
Externí odkaz:
http://arxiv.org/abs/2303.17395
Deep neural networks have recently achieved breakthroughs in sound generation. Despite the outstanding sample quality, current sound generation models face issues on small-scale datasets (e.g., overfitting), significantly limiting performance. In thi
Externí odkaz:
http://arxiv.org/abs/2303.03857
Autor:
Liu, Haohe, Chen, Zehua, Yuan, Yi, Mei, Xinhao, Liu, Xubo, Mandic, Danilo, Wang, Wenwu, Plumbley, Mark D.
Text-to-audio (TTA) system has recently gained attention for its ability to synthesize general audio based on text descriptions. However, previous studies in TTA have limited generation quality with high computational costs. In this study, we propose
Externí odkaz:
http://arxiv.org/abs/2301.12503
Autor:
Chen, Zehua, Wu, Yihan, Leng, Yichong, Chen, Jiawei, Liu, Haohe, Tan, Xu, Cui, Yang, Wang, Ke, He, Lei, Zhao, Sheng, Bian, Jiang, Mandic, Danilo
Denoising Diffusion Probabilistic Models (DDPMs) are emerging in text-to-speech (TTS) synthesis because of their strong capability of generating high-fidelity samples. However, their iterative refinement process in high-dimensional data space results
Externí odkaz:
http://arxiv.org/abs/2212.14518
Publikováno v:
Proc. Interspeech 2023
This study defines a new evaluation metric for audio tagging tasks to overcome the limitation of the conventional mean average precision (mAP) metric, which treats different kinds of sound as independent classes without considering their relations. A
Externí odkaz:
http://arxiv.org/abs/2211.12195