# A Unified Cascaded Encoder ASR Model for Dynamic Model Sizes

arXiv: https://arxiv.org/abs/2204.06164 · HTML: https://mlsanity.com/paper/2204.06164/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 30 references that are in the map.
- First posted on arXiv 13 Apr 2022.

## Builds on (most cited first, 21 of 21)

- [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)
- [Attention-Based Models for Speech Recognition](https://mlsanity.com/paper/1506.07503/) (2015)
- [Deep Speech: Scaling up end-to-end speech recognition](https://mlsanity.com/paper/1412.5567/) (2014)
- [Joint CTC-Attention based End-to-End Speech Recognition using Multi-task Learning](https://mlsanity.com/paper/1609.06773/) (2016)
- [Streaming End-to-end Speech Recognition For Mobile Devices](https://mlsanity.com/paper/1811.06621/) (2018)
- [State-of-the-art Speech Recognition With Sequence-to-Sequence Models](https://mlsanity.com/paper/1712.01769/) (2017)
- [Funnel-Transformer: Filtering out Sequential Redundancy for Efficient Language Processing](https://mlsanity.com/paper/2006.03236/) (2020)
- [A Streaming On-Device End-to-End Model Surpassing Server-Side Conventional Model Quality and Latency](https://mlsanity.com/paper/2003.12710/) (2020)
- [Recognizing long-form speech using streaming end-to-end models](https://mlsanity.com/paper/1910.11455/) (2019)
- [Minimum Word Error Rate Training for Attention-based Sequence-to-Sequence Models](https://mlsanity.com/paper/1712.01818/) (2017)
- [Improving RNN Transducer Modeling for End-to-End Speech Recognition](https://mlsanity.com/paper/1909.12415/) (2019)
- [On the Comparison of Popular End-to-End Models for Large Scale Speech Recognition](https://mlsanity.com/paper/2005.14327/) (2020)
- [Cascaded encoders for unifying streaming and non-streaming ASR](https://mlsanity.com/paper/2010.14606/) (2020)
- [Tied & Reduced RNN-T Decoder](https://mlsanity.com/paper/2109.07513/) (2021)
- [A New Training Pipeline for an Improved Neural Transducer](https://mlsanity.com/paper/2005.09319/) (2020)
- [Dynamic Sparsity Neural Networks for Automatic Speech Recognition](https://mlsanity.com/paper/2005.10627/) (2020)
- [Omni-sparsity DNN: Fast Sparsity Optimization for On-Device Streaming E2E ASR via Supernet](https://mlsanity.com/paper/2110.08352/) (2021)
- [CoDERT: Distilling Encoder Representations with Co-learning for Transducer-based Speech Recognition](https://mlsanity.com/paper/2106.07734/) (2021)
- [Dynamic Encoder Transducer: A Flexible Solution For Trading Off Accuracy For Latency](https://mlsanity.com/paper/2104.02176/) (2021)
- [Collaborative Training of Acoustic Encoders for Speech Recognition](https://mlsanity.com/paper/2106.08960/) (2021)

## Built on by (most cited first, 11 of 11)

- [JEIT: Joint End-to-End Model and Internal Language Model Training for Speech Recognition](https://mlsanity.com/paper/2302.08583/) (2023)
- [Dynamic Encoder Size Based on Data-Driven Layer-wise Pruning for Speech Recognition](https://mlsanity.com/paper/2407.18930/) (2024)
- [Extreme Encoder Output Frame Rate Reduction: Improving Computational Latencies of Large End-to-End Models](https://mlsanity.com/paper/2402.17184/) (2024)
- [TODM: Train Once Deploy Many Efficient Supernet-Based RNN-T Compression For On-device ASR Models](https://mlsanity.com/paper/2309.01947/) (2023)
- [E2E Segmentation in a Two-Pass Cascaded Encoder ASR Model](https://mlsanity.com/paper/2211.15432/) (2022)
- [Semantic Segmentation with Bidirectional Language Models Improves Long-form ASR](https://mlsanity.com/paper/2305.18419/) (2023)
- [Knowledge Distillation from Non-streaming to Streaming ASR Encoder using Auxiliary Non-streaming Layer](https://mlsanity.com/paper/2308.16415/) (2023)
- [Efficient Supernet Training with Orthogonal Softmax for Scalable ASR Model Compression](https://mlsanity.com/paper/2501.18895/) (2025)
- [RAND: Robustness Aware Norm Decay For Quantized Seq2seq Models](https://mlsanity.com/paper/2305.15536/) (2023)
- [Joint Optimization of Streaming and Non-Streaming Automatic Speech Recognition with Multi-Decoder and Knowledge Distillation](https://mlsanity.com/paper/2405.13514/) (2024)
- [Federated Learning of Large ASR Models in the Real World](https://mlsanity.com/paper/2408.10443/) (2024)

## Abstract (arXiv)

In this paper, we propose a dynamic cascaded encoder Automatic Speech Recognition (ASR) model, which unifies models for different deployment scenarios. Moreover, the model can significantly reduce model size and power consumption without loss of quality. Namely, with the dynamic cascaded encoder model, we explore three techniques to maximally boost the performance of each model size: 1) Use separate decoders for each sub-model while sharing the encoders; 2) Use funnel-pooling to improve the encoder efficiency; 3) Balance the size of causal and non-causal encoders to improve quality and fit deployment constraints. Overall, the proposed large-medium model has 30% smaller size and reduces power consumption by 33%, compared to the baseline cascaded encoder model. The triple-size model that unifies the large, medium, and small models achieves 37% total size reduction with minimal quality loss, while substantially reducing the engineering efforts of having separate models.