# Back from the future: bidirectional CTC decoding using future information in speech recognition

arXiv: https://arxiv.org/abs/2110.03326 · HTML: https://mlsanity.com/paper/2110.03326/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 26 references that are in the map.
- First posted on arXiv 7 Oct 2021.

## Builds on (most cited first, 15 of 15)

- [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 Speech 2: End-to-End Speech Recognition in English and Mandarin](https://mlsanity.com/paper/1512.02595/) (2015)
- [Regularizing and Optimizing LSTM Language Models](https://mlsanity.com/paper/1708.02182/) (2017)
- [State-of-the-art Speech Recognition With Sequence-to-Sequence Models](https://mlsanity.com/paper/1712.01769/) (2017)
- [End-to-End Attention-based Large Vocabulary Speech Recognition](https://mlsanity.com/paper/1508.04395/) (2015)
- [Long Short-Term Memory Based Recurrent Neural Network Architectures for Large Vocabulary Speech Recognition](https://mlsanity.com/paper/1402.1128/) (2014)
- [Exploring Architectures, Data and Units For Streaming End-to-End Speech Recognition with RNN-Transducer](https://mlsanity.com/paper/1801.00841/) (2018)
- [First-Pass Large Vocabulary Continuous Speech Recognition using Bi-Directional Recurrent DNNs](https://mlsanity.com/paper/1408.2873/) (2014)
- [Improving RNN Transducer Based ASR with Auxiliary Tasks](https://mlsanity.com/paper/2011.03109/) (2020)
- [Librispeech Transducer Model with Internal Language Model Prior Correction](https://mlsanity.com/paper/2104.03006/) (2021)
- [Asynchronous Bidirectional Decoding for Neural Machine Translation](https://mlsanity.com/paper/1801.05122/) (2018)
- [Fully Convolutional Speech Recognition](https://mlsanity.com/paper/1812.06864/) (2018)
- [Improved training of neural trans-dimensional random field language models with dynamic noise-contrastive estimation](https://mlsanity.com/paper/1807.00993/) (2018)
- [Future Word Contexts in Neural Network Language Models](https://mlsanity.com/paper/1708.05592/) (2017)

## Built on by (most cited first, 2 of 2)

- [Iterative Shallow Fusion of Backward Language Model for End-to-End Speech Recognition](https://mlsanity.com/paper/2310.11010/) (2023)
- [Korean Tokenization for Beam Search Rescoring in Speech Recognition](https://mlsanity.com/paper/2203.03583/) (2022)

## Abstract (arXiv)

In this paper, we propose a simple but effective method to decode the output of Connectionist Temporal Classifier (CTC) model using a bi-directional neural language model. The bidirectional language model uses the future as well as the past information in order to predict the next output in the sequence. The proposed method based on bi-directional beam search takes advantage of the CTC greedy decoding output to represent the noisy future information. Experiments on the Librispeechdataset demonstrate the superiority of our proposed method compared to baselines using unidirectional decoding. In particular, the boost inaccuracy is most apparent at the start of a sequence which is the most erroneous part for existing systems based on unidirectional decoding.