Not All Weights Are Created Equal: Enhancing Energy Efficiency in On-Device Streaming Speech Recognition
Power consumption plays an important role in on-device streaming speech recognition, as it
has a direct impact on the user experience. This study delves into how weight parameters in …
has a direct impact on the user experience. This study delves into how weight parameters in …
[HTML][HTML] A Simplified Query-Only Attention for Encoder-Based Transformer Models
Transformer models have revolutionized fields like Natural Language Processing (NLP) by
enabling machines to accurately understand and generate human language. However …
enabling machines to accurately understand and generate human language. However …
Deep Learning Models in Speech Recognition: Measuring GPU Energy Consumption, Impact of Noise and Model Quantization for Edge Deployment
A Chakravarty - arXiv preprint arXiv:2405.01004, 2024 - arxiv.org
Recent transformer-based ASR models have achieved word-error rates (WER) below 4%,
surpassing human annotator accuracy, yet they demand extensive server resources …
surpassing human annotator accuracy, yet they demand extensive server resources …