mlsanityData to 7 Oct 2026

Breaking Down Power Barriers in On-Device Streaming ASR: Insights and Solutions

arXiv 2402.13076 ↗First posted 20 Feb 2024cs.SD cs.LG eess.AScited by 5

Not on the map. Why?

Abstract (arXiv)

Power consumption plays a crucial role in on-device streaming speech recognition, significantly influencing the user experience. This study explores how the configuration of weight parameters in speech recognition models affects their overall energy efficiency. We found that the influence of these parameters on power consumption varies depending on factors such as invocation frequency and memory allocation. Leveraging these insights, we propose design principles that enhance on-device speech recognition models by reducing power consumption with minimal impact on accuracy. Our approach, which adjusts model components based on their specific energy sensitivities, achieves up to 47% lower energy usage while preserving comparable model accuracy and improving real-time performance compared to leading methods.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 18 of its 33 references that are in the map. First posted on arXiv 20 Feb 2024.

Builds on

18 of 33 references.

References · 18

  1. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
  2. 2013Speech Recognition with Deep Recurrent Neural Networkscited by 666
  3. 2020Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Losscited by 232
  4. 2018Streaming End-to-end Speech Recognition For Mobile Devicescited by 230
  5. 2019A Comparative Study on Transformer vs RNN in Speech Applicationscited by 210
  6. 2023End-to-End Speech Recognition: A Surveycited by 127
  7. 2020Emformer: Efficient Memory Transformer Based Acoustic Model For Low Latency Streaming Speech Recognitioncited by 111
  8. 2019Transformer-based Acoustic Modeling for Hybrid Speech Recognitioncited by 86
  9. 2020Streaming automatic speech recognition with the transformer modelcited by 73
  10. 2019Transformer-Transducer: End-to-End Speech Recognition with Self-Attentioncited by 68
  11. 2020A Better and Faster End-to-End Model for Streaming ASRcited by 68
  12. 2021Tied & Reduced RNN-T Decodercited by 35
6 more
  1. 2019Optimizing Speech Recognition For The Edgecited by 32
  2. 2021Omni-sparsity DNN: Fast Sparsity Optimization for On-Device Streaming E2E ASR via Supernetcited by 12
  3. 2022ConvRNN-T: Convolutional Augmented Recurrent Neural Network Transducers for Streaming Speech Recognitioncited by 8
  4. 2021Memory-efficient Speech Recognition on Smart Devicescited by 7
  5. 2023Folding Attention: Memory and Power Optimization for On-Device Transformer-based Streaming Speech Recognitioncited by 7
  6. 2022Factorized Blank Thresholding for Improved Runtime Efficiency of Neural Transducerscited by 5

Built on by

Cited by year

Citing papers per year: 2024: 3; 2025: 2.

5 papers.

  1. 2024Deep Learning Models in Speech Recognition: Measuring GPU Energy Consumption, Impact of Noise and Model Quantization for Edge Deploymentcited by 1
  2. 2024Basis Selection: Low-Rank Decomposition of Pretrained Large Language Models for Target Applicationscited by 1
  3. 2025IMPACT: Importance-Aware Activation Space Reconstructioncited by 1
  4. 2024A light-weight and efficient punctuation and word casing prediction model for on-device streaming ASRcited by 0
  5. 2025Decomposed Trust: Privacy, Adversarial Robustness, Ethics, and Fairness in Low-Rank LLMscited by 0