# Layer Pruning on Demand with Intermediate CTC

arXiv: https://arxiv.org/abs/2106.09216 · HTML: https://mlsanity.com/paper/2106.09216/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 40 references that are in the map.
- First posted on arXiv 17 Jun 2021.

## Builds on (most cited first, 29 of 29)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [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)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [Deep Networks with Stochastic Depth](https://mlsanity.com/paper/1603.09382/) (2016)
- [ESPnet: End-to-End Speech Processing Toolkit](https://mlsanity.com/paper/1804.00015/) (2018)
- [Listen, Attend and Spell](https://mlsanity.com/paper/1508.01211/) (2015)
- [Reducing Transformer Depth on Demand with Structured Dropout](https://mlsanity.com/paper/1909.11556/) (2019)
- [Attention-Based Models for Speech Recognition](https://mlsanity.com/paper/1506.07503/) (2015)
- [AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline](https://mlsanity.com/paper/1709.05522/) (2017)
- [Slimmable Neural Networks](https://mlsanity.com/paper/1812.08928/) (2018)
- [Universally Slimmable Networks and Improved Training Techniques](https://mlsanity.com/paper/1903.05134/) (2019)
- [Recent Developments on ESPnet Toolkit Boosted by Conformer](https://mlsanity.com/paper/2010.13956/) (2020)
- [Intermediate Loss Regularization for CTC-based Speech Recognition](https://mlsanity.com/paper/2102.03216/) (2021)
- [QuartzNet: Deep Automatic Speech Recognition with 1D Time-Channel Separable Convolutions](https://mlsanity.com/paper/1910.10261/) (2019)
- [AI Benchmark: All About Deep Learning on Smartphones in 2019](https://mlsanity.com/paper/1910.06663/) (2019)
- [Mask CTC: Non-Autoregressive End-to-End ASR with CTC and Mask Predict](https://mlsanity.com/paper/2005.08700/) (2020)
- [Imputer: Sequence Modelling via Imputation and Dynamic Programming](https://mlsanity.com/paper/2002.08926/) (2020)
- [Very Deep Self-Attention Networks for End-to-End Speech Recognition](https://mlsanity.com/paper/1904.13377/) (2019)
- [Align-Refine: Non-Autoregressive Speech Recognition via Iterative Realignment](https://mlsanity.com/paper/2010.14233/) (2020)
- [On-Device Neural Net Inference with Mobile GPUs](https://mlsanity.com/paper/1907.01989/) (2019)
- [Domain Adaptation via Teacher-Student Learning for End-to-End Speech Recognition](https://mlsanity.com/paper/2001.01798/) (2020)
- [Joint Masked CPC and CTC Training for ASR](https://mlsanity.com/paper/2011.00093/) (2020)
- [Scaling Up Online Speech Recognition Using ConvNets](https://mlsanity.com/paper/2001.09727/) (2020)
- [Building competitive direct acoustics-to-word models for English conversational speech recognition](https://mlsanity.com/paper/1712.03133/) (2017)
- [Any-Width Networks](https://mlsanity.com/paper/2012.03153/) (2020)

## Built on by (most cited first, 13 of 13)

- [Hierarchical Conditional End-to-End ASR with CTC and Multi-Granular Subword Units](https://mlsanity.com/paper/2110.04109/) (2021)
- [HuBERT-EE: Early Exiting HuBERT for Efficient Speech Recognition](https://mlsanity.com/paper/2204.06328/) (2022)
- [BERT Meets CTC: New Formulation of End-to-End Speech Recognition with Pre-trained Masked Language Model](https://mlsanity.com/paper/2210.16663/) (2022)
- [I3D: Transformer architectures with input-dependent dynamic depth for speech recognition](https://mlsanity.com/paper/2303.07624/) (2023)
- [Dynamic Encoder Size Based on Data-Driven Layer-wise Pruning for Speech Recognition](https://mlsanity.com/paper/2407.18930/) (2024)
- [A CTC Alignment-based Non-autoregressive Transformer for End-to-end Automatic Speech Recognition](https://mlsanity.com/paper/2304.07611/) (2023)
- [Effective and Efficient Mixed Precision Quantization of Speech Foundation Models](https://mlsanity.com/paper/2501.03643/) (2025)
- [One-pass Multiple Conformer and Foundation Speech Systems Compression and Quantization Using An All-in-one Neural Model](https://mlsanity.com/paper/2406.10160/) (2024)
- [Guiding Frame-Level CTC Alignments Using Self-knowledge Distillation](https://mlsanity.com/paper/2406.07909/) (2024)
- [Efficient Supernet Training with Orthogonal Softmax for Scalable ASR Model Compression](https://mlsanity.com/paper/2501.18895/) (2025)
- [Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates](https://mlsanity.com/paper/2505.22608/) (2025)
- [Spiralformer: Low Latency Encoder for Streaming Speech Recognition with Circular Layer Skipping and Early Exiting](https://mlsanity.com/paper/2510.00982/) (2025)
- [Towards Data-free and Training-free Compression for Speech Foundation Models Using Parameter Clustering](https://mlsanity.com/paper/2606.11836/) (2026)

## Abstract (arXiv)

Deploying an end-to-end automatic speech recognition (ASR) model on mobile/embedded devices is a challenging task, since the device computational power and energy consumption requirements are dynamically changed in practice. To overcome the issue, we present a training and pruning method for ASR based on the connectionist temporal classification (CTC) which allows reduction of model depth at run-time without any extra fine-tuning. To achieve the goal, we adopt two regularization methods, intermediate CTC and stochastic depth, to train a model whose performance does not degrade much after pruning. We present an in-depth analysis of layer behaviors using singular vector canonical correlation analysis (SVCCA), and efficient strategies for finding layers which are safe to prune. Using the proposed method, we show that a Transformer-CTC model can be pruned in various depth on demand, improving real-time factor from 0.005 to 0.002 on GPU, while each pruned sub-model maintains the accuracy of individually trained model of the same depth.