Distilled Non-Semantic Speech Embeddings with Binary Neural Networks for Low-Resource Devices
Explore this paper's citation graph
- Type
- preprint
- Published
- 2022-07-12
- Cited by
- 4
- References
- 28
- Access
- Open access
- OpenAlex
- https://openalex.org/W4285483849
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:250478315
Keywords
Computer science, Latency (audio), Benchmark (surveying), Artificial neural network, Software deployment
References
- Distilling the Knowledge in a Neural Network
- BinaryConnect: Training Deep Neural Networks with binary weights during propagations
- CREMA-D: Crowd-sourced Emotional Multimodal Actors Dataset
- ESC: Dataset for Environmental Sound Classification
- MUSAN: A Music, Speech, and Noise Corpus
- Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition
- Distilled Binary Neural Network for Monaural Speech Separation
- Training binary neural networks with knowledge transfer
- Back to Simplicity: How to Train Accurate BNNs from Scratch?
- Libri-Light: A Benchmark for ASR with Limited or No Supervision
- Larq: An Open-Source Library for Training Binarized Neural Networks
- MeliusNet: Can Binary Neural Networks Achieve MobileNet-level Accuracy?
- Towards Learning a Universal Non-Semantic Representation of Speech
- Contrastive Learning of General-Purpose Audio Representations
- MeliusNet: An Improved Network Architecture for Binary Neural Networks
- Leveraging Recent Advances in Deep Learning for Audio-Visual Emotion Recognition
- Improving knowledge distillation using unified ensembles of specialized teachers
- FRILL: A Non-Semantic Speech Embedding for Mobile Devices
- BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition
- Universal Paralinguistic Speech Representations Using self-Supervised Conformers