# ASAPP-ASR: Multistream CNN and Self-Attentive SRU for SOTA Speech Recognition

arXiv: https://arxiv.org/abs/2005.10469 · HTML: https://mlsanity.com/paper/2005.10469/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 May 2020.

## Built on by (most cited first, 10 of 10)

- [Squeezeformer: An Efficient Transformer for Automatic Speech Recognition](https://mlsanity.com/paper/2206.00888/) (2022)
- [TC-SKNet with GridMask for Low-complexity Classification of Acoustic scene](https://mlsanity.com/paper/2210.02287/) (2022)
- [Understanding Medical Conversations: Rich Transcription, Confidence Scores & Information Extraction](https://mlsanity.com/paper/2104.02219/) (2021)
- [MSTRE-Net: Multistreaming Acoustic Modeling for Automatic Lyrics Transcription](https://mlsanity.com/paper/2108.02625/) (2021)
- [Revisiting ASR Error Correction with Specialized Models](https://mlsanity.com/paper/2405.15216/) (2024)
- [Word-level confidence estimation for RNN transducers](https://mlsanity.com/paper/2110.15222/) (2021)
- [Channel-Aware Domain-Adaptive Generative Adversarial Network for Robust Speech Recognition](https://mlsanity.com/paper/2409.12386/) (2024)
- [A Comparison of Semi-Supervised Learning Techniques for Streaming ASR at Scale](https://mlsanity.com/paper/2304.11053/) (2023)
- [SW-ASR: A Context-Aware Hybrid ASR Pipeline for Robust Single Word Speech Recognition](https://mlsanity.com/paper/2601.20890/) (2026)
- [Universal Robust Speech Adaptation for Cross-Domain Speech Recognition and Enhancement](https://mlsanity.com/paper/2602.04307/) (2026)

## Abstract (arXiv)

In this paper we present state-of-the-art (SOTA) performance on the LibriSpeech corpus with two novel neural network architectures, a multistream CNN for acoustic modeling and a self-attentive simple recurrent unit (SRU) for language modeling. In the hybrid ASR framework, the multistream CNN acoustic model processes an input of speech frames in multiple parallel pipelines where each stream has a unique dilation rate for diversity. Trained with the SpecAugment data augmentation method, it achieves relative word error rate (WER) improvements of 4% on test-clean and 14% on test-other. We further improve the performance via N-best rescoring using a 24-layer self-attentive SRU language model, achieving WERs of 1.75% on test-clean and 4.46% on test-other.