Results 281 to 290 of about 2,183,275 (319)

Fast Timing-Conditioned Latent Audio Diffusion

International Conference on Machine Learning
Generating long-form 44.1kHz stereo audio from text prompts can be computationally demanding. Further, most previous works do not tackle that music and sound effects naturally vary in their duration.
Zach Evans, CJ Carr, Josiah Taylor, Scott H. Hawley, Jordi Pons   +4 more
semanticscholar   +1 more source

DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model With Self-Generated Cross-Modal Alignment

IEEE Transactions on Audio, Speech, and Language Processing
We introduce DeSTA2.5-Audio, a general-purpose Large Audio Language Model (LALM) designed for robust auditory perception and instruction-following. Recent LALMs augment Large Language Models (LLMs) with auditory capabilities by training on large-scale ...
Ke-Han Lu, Zhehuai Chen, Szu-Wei Fu, Chao-Han Huck Yang, Sung-Feng Huang, Chih-Kai Yang, Chee-En Yu, C. Chen, Wei-Chih Chen, Chien-yu Huang, Yi-Cheng Lin, Yu-Xiang Lin, C. Fu, Chun-Yi Kuan, Wenze Ren, Xuanjun Chen, Wei-Ping Huang, En-Pei Hu, Tzu-Quan Lin, Yuan-Kuei Wu, Kuan-Po Huang, Hsiao-Ying Huang, Huang-Cheng Chou, Kai-Wei Chang, Cheng-Han Chiang, Boris Ginsburg, Y. Wang, Hung-yi Lee   +27 more
semanticscholar   +1 more source

Lumina audio / Litora audio

2017
Rezension zu: Lumina audio. Von Ursula Blank-Sangmeister, Hubert Müller, Helmut Schlüter und Kurt Steinicke (ISBN 3-525-71045-3). Litora audio. Von Ursula Blank-Sangmeister und Hubert Müller (ISBN3-525- 7175-5). - Hör-CDs mit nach pronuntiatus restitutus gelesenen Lehrbuchtexten. Sprecher: Julia Hansen und Michael Jackenkroll.
openaire   +1 more source

Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities

International Conference on Machine Learning
Augmenting large language models (LLMs) to understand audio -- including non-speech sounds and non-verbal speech -- is critically important for diverse real-world applications of LLMs.
Zhifeng Kong, Arushi Goel, Rohan Badlani, Wei Ping, Rafael Valle, Bryan Catanzaro   +5 more
semanticscholar   +1 more source

GAMA: A Large Audio-Language Model with Advanced Audio Understanding and Complex Reasoning Abilities

Conference on Empirical Methods in Natural Language Processing
Perceiving and understanding non-speech sounds and non-verbal speech is essential to making decisions that help us interact with our surroundings. In this paper, we propose GAMA, a novel General-purpose Large Audio-Language Model (LALM) with Advanced ...
Sreyan Ghosh, Sonal Kumar, Ashish Seth, Chandra Kiran Reddy Evuru, Utkarsh Tyagi, S. Sakshi, Oriol Nieto, R. Duraiswami, Dinesh Manocha   +8 more
semanticscholar   +1 more source

audio

2020
  +10 more sources

MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis

Computer Vision and Pattern Recognition
We propose to synthesize high-quality and synchronized audio, given video and optional text conditions, using a novel multimodal joint training framework (MMAudio). In contrast to single-modality training conditioned on (limited) video data only, MMAudio
H. Cheng, Masato Ishii, Akio Hayakawa, Takashi Shibuya, Alexander G. Schwing, Yuki Mitsufuji   +5 more
semanticscholar   +1 more source

Loopy: Taming Audio-Driven Portrait Avatar with Long-Term Motion Dependency

International Conference on Learning Representations
With the introduction of diffusion-based video generation techniques, audio-conditioned human video generation has recently achieved significant breakthroughs in both the naturalness of motion and the synthesis of portrait details.
Jianwen Jiang, Chao Liang, Jiaqi Yang, Gaojie Lin, Tianyun Zhong, Yanbo Zheng   +5 more
semanticscholar   +1 more source

Audio Set: An ontology and human-labeled dataset for audio events

IEEE International Conference on Acoustics, Speech, and Signal Processing, 2017
J. Gemmeke, D. Ellis, Dylan Freedman, A. Jansen, W. Lawrence, R. C. Moore, M. Plakal, Marvin Ritter   +7 more
semanticscholar   +1 more source

audio

2021
  +7 more sources