research
∙
06/30/2023
Dataset balancing can hurt model performance
Machine learning from training data with a skewed distribution of exampl...
share
research
∙
05/11/2023
V2Meow: Meowing to the Visual Beat via Music Generation
Generating high quality music that complements the visual content of a v...
research
∙
01/26/2023
MusicLM: Generating Music From Text
We introduce MusicLM, a model generating high-fidelity music from text d...
research
∙
01/09/2023
MAQA: A Multimodal QA Benchmark for Negation
Multimodal learning can benefit from the representation power of pretrai...
research
∙
08/26/2022
MuLan: A Joint Embedding of Music Audio and Natural Language
Music tagging and content-based retrieval systems have traditionally bee...
research
∙
04/12/2022
Text-Driven Separation of Arbitrary Sounds
We propose a method of separating a desired sound source from a single-c...
research
∙
10/09/2021
Universal Paralinguistic Speech Representations Using Self-Supervised Conformers
Many speech applications require understanding aspects beyond the words ...
research
∙
09/27/2021
BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition
We summarize the results of a host of efforts using giant automatic spee...
research
∙
06/30/2021
Attention Bottlenecks for Multimodal Fusion
Humans perceive the world by concurrently processing and fusing high-dim...
research
∙
06/01/2021
Sparse, Efficient, and Semantic Mixture Invariant Training: Taming In-the-Wild Unsupervised Sound Separation
Supervised neural network training has led to significant progress on si...
research
∙
05/14/2021
The Benefit Of Temporally-Strong Labels In Audio Event Classification
To reveal the importance of temporal precision in ground truth audio eve...
research
∙
05/05/2021
Self-Supervised Learning from Automatically Separated Sound Scenes
Real-world sound scenes consist of time-varying collections of sound sou...
research
∙
11/02/2020
Into the Wild with AudioScope: Unsupervised Audio-Visual Separation of On-Screen Sounds
Recent progress in deep learning has enabled many advances in sound sepa...
research
∙
05/02/2020
Addressing Missing Labels in Large-scale Sound Event Recognition using a Teacher-student Framework with Loss Masking
The study of label noise in sound event recognition has recently gained ...
research
∙
02/25/2020
Towards Learning a Universal Non-Semantic Representation of Speech
The ultimate goal of transfer learning is to reduce labeled data require...
research
∙
11/18/2019
Improving Universal Sound Separation Using Sound Classification
Deep learning approaches have recently achieved impressive performance o...
research
∙
11/14/2019
Coincidence, Categorization, and Consolidation: Learning to Recognize Sounds with Minimal Supervision
Humans do not acquire perceptual abilities in the way we train machines....
research
∙
11/06/2017
Unsupervised Learning of Semantic Audio Representations
Even in the absence of any explicit semantic annotation, vast collection...
research
∙
09/29/2016
CNN Architectures for Large-Scale Audio Classification
Convolutional Neural Networks (CNNs) have proven very effective in image...
research
∙
06/22/2016
A segmental framework for fully-unsupervised large-vocabulary speech recognition
Zero-resource speech technology is a growing research area that aims to ...
research
∙
03/09/2016
Unsupervised word segmentation and lexicon discovery using acoustic word embeddings
In settings where only unlabelled speech data is available, speech techn...
research
∙
08/18/2015