mlsanityData to 7 Oct 2026

A Model for Every User and Budget: Label-Free and Personalized Mixed-Precision Quantization

arXiv 2307.12659 ↗First posted 24 Jul 2023cs.SD cs.CL eess.AScited by 7

Not on the map. Why?

Abstract (arXiv)

Recent advancement in Automatic Speech Recognition (ASR) has produced large AI models, which become impractical for deployment in mobile devices. Model quantization is effective to produce compressed general-purpose models, however such models may only be deployed to a restricted sub-domain of interest. We show that ASR models can be personalized during quantization while relying on just a small set of unlabelled samples from the target domain. To this end, we propose myQASR, a mixed-precision quantization method that generates tailored quantization schemes for diverse users under any memory requirement with no fine-tuning. myQASR automatically evaluates the quantization sensitivity of network layers by analysing the full-precision activation values. We are then able to generate a personalised mixed-precision quantization scheme for any pre-determined memory budget. Results for large-scale ASR models show how myQASR improves performance for specific genders, languages, and speakers.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 30 of its 44 references that are in the map. First posted on arXiv 24 Jul 2023.

Builds on

30 of 44 references.

References · 30

  1. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  2. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
  3. 2020Knowledge Distillation: A Surveycited by 1,578
  4. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 798
  5. 2018Speech Commands: A Dataset for Limited-Vocabulary Speech Recognitioncited by 741
  6. 2020Up or Down? Adaptive Rounding for Post-Training Quantizationcited by 600
  7. 2022ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformerscited by 517
  8. 2022FLEURS: Few-shot Learning Evaluation of Universal Representations of Speechcited by 458
  9. 2019HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precisioncited by 387
  10. 2019Data-Free Quantization Through Weight Equalization and Bias Correctioncited by 328
  11. 2021Post-Training Quantization for Vision Transformercited by 274
  12. 2020ZeroQ: A Novel Zero Shot Quantization Frameworkcited by 265
18 more
  1. 2021Pruning and Quantization for Deep Neural Network Acceleration: A Surveycited by 259
  2. 2019HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networkscited by 250
  3. 2020fairseq S2T: Fast Speech-to-Text Modeling with fairseqcited by 174
  4. 2021PTQ4ViT: Post-training quantization for vision transformers with twin uniform quantizationcited by 173
  5. 2021FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformercited by 148
  6. 2022Q-ViT: Accurate and Fully Quantized Low-bit Vision Transformercited by 106
  7. 2022I-ViT: Integer-only Quantization for Efficient Vision Transformer Inferencecited by 93
  8. 2021Diversifying Sample Generation for Accurate Data-Free Quantizationcited by 63
  9. 2020EasyQuant: Post-training Quantization via Scale Optimizationcited by 57
  10. 2021Towards Mixed-Precision Quantization of Neural Networks via Constrained Optimizationcited by 57
  11. 2021Qimera: Data-free Quantization with Synthetic Boundary Supporting Samplescited by 39
  12. 20224-bit Conformer with Native Quantization Aware Training for Speech Recognitioncited by 22
  13. 2021Integer-only Zero-shot Quantization for Efficient Speech Recognitioncited by 19
  14. 2021Automatic Mixed-Precision Quantization Search of BERTcited by 16
  15. 2021KDLSQ-BERT: A Quantized Bert Combining Knowledge Distillation with Learned Step Size Quantizationcited by 14
  16. 2019A Simplified Fully Quantized Transformer for End-to-end Speech Recognitioncited by 11
  17. 2022Sub-8-Bit Quantization Aware Training for 8-Bit Neural Network Accelerator with On-Device Speech Recognitioncited by 4
  18. 2022Accelerating Inference and Language Model Fusion of Recurrent Neural Network Transducers via End-to-End 4-bit Quantizationcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 2; 2026: 3.

7 papers.

  1. 2025Effective and Efficient Mixed Precision Quantization of Speech Foundation Modelscited by 5
  2. 2024One-pass Multiple Conformer and Foundation Speech Systems Compression and Quantization Using An All-in-one Neural Modelcited by 4
  3. 2025Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gatescited by 1
  4. 2024Constraint Guided Model Quantization of Neural Networkscited by 0
  5. 2026Diagnostic-Driven Layer-Wise Compensation for Post-Training Quantization of Encoder-Decoder ASR Modelscited by 0
  6. 2026Towards Data-free and Training-free Compression for Speech Foundation Models Using Parameter Clusteringcited by 0
  7. 2026Efficiency-Performance Trade-offs in Neural Speaker Diarization via Structured Pruning and Low-Bit Quantizationcited by 0