# Adding Connectionist Temporal Summarization into Conformer to Improve Its Decoder Efficiency For Speech Recognition

arXiv: https://arxiv.org/abs/2204.03889 · HTML: https://mlsanity.com/paper/2204.03889/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 17 references that are in the map.
- First posted on arXiv 8 Apr 2022.

## Builds on (most cited first, 9 of 9)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [Speech Recognition with Deep Recurrent Neural Networks](https://mlsanity.com/paper/1303.5778/) (2013)
- [Listen, Attend and Spell](https://mlsanity.com/paper/1508.01211/) (2015)
- [Speech2Vec: A Sequence-to-Sequence Framework for Learning Word Embeddings from Speech](https://mlsanity.com/paper/1803.08976/) (2018)
- [Leveraging Unpaired Text Data for Training End-to-End Speech-to-Intent Systems](https://mlsanity.com/paper/2010.04284/) (2020)
- [Audio Word2Vec: Unsupervised Learning of Audio Segment Representations using Sequence-to-sequence Autoencoder](https://mlsanity.com/paper/1603.00982/) (2016)
- [Segmental Audio Word2Vec: Representing Utterances as Sequences of Vectors with Applications in Spoken Term Detection](https://mlsanity.com/paper/1808.02228/) (2018)
- [Almost-unsupervised Speech Recognition with Close-to-zero Resource Based on Phonetic Structures Learned from Very Small Unpaired Speech and Text Data](https://mlsanity.com/paper/1810.12566/) (2018)

## Abstract (arXiv)

The Conformer model is an excellent architecture for speech recognition modeling that effectively utilizes the hybrid losses of connectionist temporal classification (CTC) and attention to train model parameters. To improve the decoding efficiency of Conformer, we propose a novel connectionist temporal summarization (CTS) method that reduces the number of frames required for the attention decoder fed from the acoustic sequences generated by the encoder, thus reducing operations. However, to achieve such decoding improvements, we must fine-tune model parameters, as cross-attention observations are changed and thus require corresponding refinements. Our final experiments show that, with a beamwidth of 4, the LibriSpeech's decoding budget can be reduced by up to 20% and for FluentSpeech data it can be reduced by 11%, without losing ASR accuracy. An improvement in accuracy is even found for the LibriSpeech "test-other" set. The word error rate (WER) is reduced by 6% relative at the beam width of 1 and by 3% relative at the beam width of 4.