# Predicting Multi-Codebook Vector Quantization Indexes for Knowledge Distillation

arXiv: https://arxiv.org/abs/2211.00508 · HTML: https://mlsanity.com/paper/2211.00508/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Speech and audio distillation, one of 12 directions in Knowledge distillation.
- Builds on 22 of its 34 references that are in the map.
- First posted on arXiv 31 Oct 2022.

## Placed in

- Knowledge distillation / [Speech and audio distillation](https://mlsanity.com/distill/speech-and-audio-distillation/)

## Builds on (most cited first, 22 of 22)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [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)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [MUSAN: A Music, Speech, and Noise Corpus](https://mlsanity.com/paper/1510.08484/) (2015)
- [vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations](https://mlsanity.com/paper/1910.05453/) (2019)
- [Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition](https://mlsanity.com/paper/2010.10504/) (2020)
- [Emotion Recognition from Speech Using Wav2vec 2.0 Embeddings](https://mlsanity.com/paper/2104.03502/) (2021)
- [Self-supervised Learning with Random-projection Quantizer for Speech Recognition](https://mlsanity.com/paper/2202.01855/) (2022)
- [A Fine-tuned Wav2vec 2.0/HuBERT Benchmark For Speech Emotion Recognition, Speaker Verification and Spoken Language Understanding](https://mlsanity.com/paper/2111.02735/) (2021)
- [Pruned RNN-T for fast, memory-efficient ASR training](https://mlsanity.com/paper/2206.13236/) (2022)
- [Unified Streaming and Non-streaming Two-pass End-to-end Model for Speech Recognition](https://mlsanity.com/paper/2012.05481/) (2020)
- [Efficient Knowledge Distillation for RNN-Transducer Models](https://mlsanity.com/paper/2011.06110/) (2020)
- [Domain Adaptation via Teacher-Student Learning for End-to-End Speech Recognition](https://mlsanity.com/paper/2001.01798/) (2020)
- [Improving Streaming Automatic Speech Recognition With Non-Streaming Model Distillation On Unsupervised Data](https://mlsanity.com/paper/2010.12096/) (2020)
- [Knowledge Distillation for Neural Transducers from Large Self-Supervised Pre-trained Models](https://mlsanity.com/paper/2110.03334/) (2021)
- [CoDERT: Distilling Encoder Representations with Co-learning for Transducer-based Speech Recognition](https://mlsanity.com/paper/2106.07734/) (2021)

## Built on by (most cited first, 6 of 6)

- [Knowledge Distillation from Multiple Foundation Models for End-to-End Speech Recognition](https://mlsanity.com/paper/2303.10917/) (2023)
- [Rate-Adaptive Quantization: A Multi-Rate Codebook Adaptation for Vector Quantization-based Generative Models](https://mlsanity.com/paper/2405.14222/) (2024)
- [DeCoR: Defy Knowledge Forgetting by Predicting Earlier Audio Codes](https://mlsanity.com/paper/2305.18441/) (2023)
- [Compact Speech Translation Models via Discrete Speech Units Pretraining](https://mlsanity.com/paper/2402.19333/) (2024)
- [Enhancing Fully Formatted End-to-End Speech Recognition with Knowledge Distillation via Multi-Codebook Vector Quantization](https://mlsanity.com/paper/2512.18967/) (2025)
- [LooC: Effective Low-Dimensional Codebook for Compositional Vector Quantization](https://mlsanity.com/paper/2601.00222/) (2026)

## Abstract (arXiv)

Knowledge distillation(KD) is a common approach to improve model performance in automatic speech recognition (ASR), where a student model is trained to imitate the output behaviour of a teacher model. However, traditional KD methods suffer from teacher label storage issue, especially when the training corpora are large. Although on-the-fly teacher label generation tackles this issue, the training speed is significantly slower as the teacher model has to be evaluated every batch. In this paper, we reformulate the generation of teacher label as a codec problem. We propose a novel Multi-codebook Vector Quantization (MVQ) approach that compresses teacher embeddings to codebook indexes (CI). Based on this, a KD training framework (MVQ-KD) is proposed where a student model predicts the CI generated from the embeddings of a self-supervised pre-trained teacher model. Experiments on the LibriSpeech clean-100 hour show that MVQ-KD framework achieves comparable performance as traditional KD methods (l1, l2), while requiring 256 times less storage. When the full LibriSpeech dataset is used, MVQ-KD framework results in 13.8% and 8.2% relative word error rate reductions (WERRs) for non -streaming transducer on test-clean and test-other and 4.0% and 4.9% for streaming transducer. The implementation of this work is already released as a part of the open-source project icefall.