# Efficient Speech Representation Learning with Low-Bit Quantization

arXiv: https://arxiv.org/abs/2301.00652 · HTML: https://mlsanity.com/paper/2301.00652/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 23 references that are in the map.
- First posted on arXiv 14 Dec 2022.

## Builds on (most cited first, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [fairseq: A Fast, Extensible Toolkit for Sequence Modeling](https://mlsanity.com/paper/1904.01038/) (2019)
- [XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks](https://mlsanity.com/paper/1603.05279/) (2016)
- [SUPERB: Speech processing Universal PERformance Benchmark](https://mlsanity.com/paper/2105.01051/) (2021)
- [Pruning and Quantization for Deep Neural Network Acceleration: A Survey](https://mlsanity.com/paper/2101.09671/) (2021)
- [Training with Quantization Noise for Extreme Model Compression](https://mlsanity.com/paper/2004.07320/) (2020)
- [DistilHuBERT: Speech Representation Learning by Layer-wise Distillation of Hidden-unit BERT](https://mlsanity.com/paper/2110.01900/) (2021)
- [TorchAudio: Building Blocks for Audio and Speech Processing](https://mlsanity.com/paper/2110.15018/) (2021)
- [Performance-Efficiency Trade-offs in Unsupervised Pre-training for Speech Recognition](https://mlsanity.com/paper/2109.06870/) (2021)
- [BiT: Robustly Binarized Multi-distilled Transformer](https://mlsanity.com/paper/2205.13016/) (2022)
- [QKD: Quantization-aware Knowledge Distillation](https://mlsanity.com/paper/1911.12491/) (2019)
- [QuaRL: Quantization for Fast and Environmentally Sustainable Reinforcement Learning](https://mlsanity.com/paper/1910.01055/) (2019)

## Built on by (most cited first, 5 of 5)

- [OWSM-CTC: An Open Encoder-Only Speech Foundation Model for Speech Recognition, Translation, and Language Identification](https://mlsanity.com/paper/2402.12654/) (2024)
- [Fine-tuning Strategies for Faster Inference using Speech Self-Supervised Models: A Comparative Study](https://mlsanity.com/paper/2303.06740/) (2023)
- [CoLLD: Contrastive Layer-to-layer Distillation for Compressing Multilingual Pre-trained Speech Encoders](https://mlsanity.com/paper/2309.07707/) (2023)
- [Outlier Reduction with Gated Attention for Improved Post-training Quantization in Large Sequence-to-sequence Speech Foundation Models](https://mlsanity.com/paper/2406.11022/) (2024)
- [Attention or Convolution: Transformer Encoders in Audio Language Models for Inference Efficiency](https://mlsanity.com/paper/2311.02772/) (2023)

## Abstract (arXiv)

With the development of hardware for machine learning, newer models often come at the cost of both increased sizes and computational complexity. In effort to improve the efficiency for these models, we apply and investigate recent quantization techniques on speech representation learning models. The quantization techniques were evaluated on the SUPERB benchmark. On the ASR task, with aggressive quantization to 1 bit, we achieved 86.32% storage reduction (184.42 -> 25.23), 88% estimated runtime reduction (1.00 -> 0.12) with increased word error rate (7.06 -> 15.96). In comparison with DistillHuBERT which also aims for model compression, the 2-bit configuration yielded slightly smaller storage (35.84 vs. 46.98), better word error rate (12.68 vs. 13.37) and more efficient estimated runtime (0.15 vs. 0.73).