# Blank Collapse: Compressing CTC emission for the faster decoding

arXiv: https://arxiv.org/abs/2210.17017 · HTML: https://mlsanity.com/paper/2210.17017/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 31 references that are in the map.
- First posted on arXiv 31 Oct 2022.

## Builds on (most cited first, 17 of 17)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [Listen, Attend and Spell](https://mlsanity.com/paper/1508.01211/) (2015)
- [Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss](https://mlsanity.com/paper/2002.02562/) (2020)
- [Beam Search Strategies for Neural Machine Translation](https://mlsanity.com/paper/1702.01806/) (2017)
- [End-to-end ASR: from Supervised to Semi-Supervised Learning with Modern Architectures](https://mlsanity.com/paper/1911.08460/) (2019)
- [TorchAudio: Building Blocks for Audio and Speech Processing](https://mlsanity.com/paper/2110.15018/) (2021)
- [CTC-Segmentation of Large Corpora for German End-to-end Speech Recognition](https://mlsanity.com/paper/2007.09127/) (2020)
- [EESEN: End-to-End Speech Recognition using Deep RNN Models and WFST-based Decoding](https://mlsanity.com/paper/1507.08240/) (2015)
- [First-Pass Large Vocabulary Continuous Speech Recognition using Bi-Directional Recurrent DNNs](https://mlsanity.com/paper/1408.2873/) (2014)
- [Flashlight: Enabling Innovation in Tools for Machine Learning](https://mlsanity.com/paper/2201.12465/) (2022)
- [RNN-T For Latency Controlled ASR With Improved Beam Search](https://mlsanity.com/paper/1911.01629/) (2019)
- [Tiny Transducer: A Highly-efficient Speech Recognition Model on Edge Devices](https://mlsanity.com/paper/2101.06856/) (2021)
- [CTC Variations Through New WFST Topologies](https://mlsanity.com/paper/2110.03098/) (2021)
- [Accelerating RNN-T Training and Inference Using CTC guidance](https://mlsanity.com/paper/2210.16481/) (2022)
- [A GPU-based WFST Decoder with Exact Lattice Generation](https://mlsanity.com/paper/1804.03243/) (2018)

## Built on by (most cited first, 3 of 3)

- [Unveiling the Potential of LLM-Based ASR on Chinese Open-Source Datasets](https://mlsanity.com/paper/2405.02132/) (2024)
- [Guiding Frame-Level CTC Alignments Using Self-knowledge Distillation](https://mlsanity.com/paper/2406.07909/) (2024)
- [TASU2: Controllable CTC Simulation for Alignment and Low-Resource Adaptation of Speech LLMs](https://mlsanity.com/paper/2604.08384/) (2026)

## Abstract (arXiv)

Connectionist Temporal Classification (CTC) model is a very efficient method for modeling sequences, especially for speech data. In order to use CTC model as an Automatic Speech Recognition (ASR) task, the beam search decoding with an external language model like n-gram LM is necessary to obtain reasonable results. In this paper we analyze the blank label in CTC beam search deeply and propose a very simple method to reduce the amount of calculation resulting in faster beam search decoding speed. With this method, we can get up to 78% faster decoding speed than ordinary beam search decoding with a very small loss of accuracy in LibriSpeech datasets. We prove this method is effective not only practically by experiments but also theoretically by mathematical reasoning. We also observe that this reduction is more obvious if the accuracy of the model is higher.