Zobrazeno 1 - 10
of 155
pro vyhledávání: '"Wu, Mengyue"'
Zero-shot audio classification aims to recognize and classify a sound class that the model has never seen during training. This paper presents a novel approach for zero-shot audio classification using automatically generated sound attribute descripti
Externí odkaz:
http://arxiv.org/abs/2407.14355
Significant improvement has been achieved in automated audio captioning (AAC) with recent models. However, these models have become increasingly large as their performance is enhanced. In this work, we propose a knowledge distillation (KD) framework
Externí odkaz:
http://arxiv.org/abs/2407.14329
Audio generation has attracted significant attention. Despite remarkable enhancement in audio quality, existing models overlook diversity evaluation. This is partially due to the lack of a systematic sound class diversity framework and a matching dat
Externí odkaz:
http://arxiv.org/abs/2407.13198
Recently, audio generation tasks have attracted considerable research interests. Precise temporal controllability is essential to integrate audio generation with real applications. In this work, we propose a temporal controlled audio generation frame
Externí odkaz:
http://arxiv.org/abs/2407.02869
Recent advancements in audio generation have enabled the creation of high-fidelity audio clips from free-form textual descriptions. However, temporal relationships, a critical feature for audio content, are currently underrepresented in mainstream mo
Externí odkaz:
http://arxiv.org/abs/2407.02857
With the advancement of audio generation, generative models can produce highly realistic audios. However, the proliferation of deepfake general audio can pose negative consequences. Therefore, we propose a new task, deepfake general audio detection,
Externí odkaz:
http://arxiv.org/abs/2406.08052
Autor:
Wang, Yufei, Wu, Mengyue
Emotion semantic inconsistency is an ubiquitous challenge in multi-modal sentiment analysis (MSA). MSA involves analyzing sentiment expressed across various modalities like text, audio, and videos. Each modality may convey distinct aspects of sentime
Externí odkaz:
http://arxiv.org/abs/2406.03004
Large language models (LLMs) have significantly advanced audio processing through audio codecs that convert audio into discrete tokens, enabling the application of language modelling techniques to audio data. However, traditional codecs often operate
Externí odkaz:
http://arxiv.org/abs/2405.00233
Chatbots can serve as a viable tool for preliminary depression diagnosis via interactive conversations with potential patients. Nevertheless, the blend of task-oriented and chit-chat in diagnosis-related dialogues necessitates professional expertise
Externí odkaz:
http://arxiv.org/abs/2404.05012
Recently, there has been an increasing focus on audio-text cross-modal learning. However, most of the existing audio-text datasets contain only simple descriptions of sound events. Compared with classification labels, the advantages of such descripti
Externí odkaz:
http://arxiv.org/abs/2403.04594