Audio Embeddings are dense vector representations of audio signals learned by neural networks to encode semantic, acoustic, or temporal information in a continuous, fixed-dimensional space. They serve as foundational representations for tasks including audio classification, acoustic scene recognition, sound event detection, and audio-language retrieval. Research challenges include learning embeddings that generalize across noise conditions, recording environments, and domains, and aligning audio representations with other modalities such as text for cross-modal applications.
Mix-CLAP from NEC Laboratories America delivers near-Transformer accuracy for sound event classification at a fraction of the compute cost, using dual lightweight encoders and adaptive, noise-aware inference for real-world edge deployment.
Princeton Office
4 Independence Way, Suite 200
Princeton, NJ 08540
+1 609-520-1555
San Jose Office
2033 Gateway Place, Suite 200
San Jose, CA 95110
+1 408-863-6007
NEC Laboratories America, Inc. (NEC Labs) is the US-based center for NEC Corporation’s global network of corporate research laboratories. Our diverse research groups collaborate with industry, academia and governments to provide disruptive solutions to complex problems. A leader in the integration of IT and network technologies with more than 100 years of expertise, NEC provides a combination of products and solutions that cross-utilize the company’s experience and global resources to meet the complex and ever-changing needs of its customers.