# Partial Rewriting for Multi-Stage ASR

arXiv: https://arxiv.org/abs/2312.09463 · HTML: https://mlsanity.com/paper/2312.09463/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 27 references that are in the map.
- First posted on arXiv 8 Dec 2023.

## Builds on (most cited first, 11 of 11)

- [Streaming End-to-end Speech Recognition For Mobile Devices](https://mlsanity.com/paper/1811.06621/) (2018)
- [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)
- [Transformer-Transducer: End-to-End Speech Recognition with Self-Attention](https://mlsanity.com/paper/1910.12977/) (2019)
- [FastEmit: Low-latency Streaming ASR with Sequence-level Emission Regularization](https://mlsanity.com/paper/2010.11148/) (2020)
- [Improving RNN Transducer Modeling for End-to-End Speech Recognition](https://mlsanity.com/paper/1909.12415/) (2019)
- [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)
- [Streaming parallel transducer beam search with fast-slow cascaded encoders](https://mlsanity.com/paper/2203.15773/) (2022)
- [Analyzing the Quality and Stability of a Streaming End-to-End On-Device Speech Recognizer](https://mlsanity.com/paper/2006.01416/) (2020)
- [Improving Fast-slow Encoder based Transducer with Streaming Deliberation](https://mlsanity.com/paper/2212.07650/) (2022)

## Abstract (arXiv)

For many streaming automatic speech recognition tasks, it is important to provide timely intermediate streaming results, while refining a high quality final result. This can be done using a multi-stage architecture, where a small left-context only model creates streaming results and a larger left- and right-context model produces a final result at the end. While this significantly improves the quality of the final results without compromising the streaming emission latency of the system, streaming results do not benefit from the quality improvements. Here, we propose using a text manipulation algorithm that merges the streaming outputs of both models. We improve the quality of streaming results by around 10%, without altering the final results. Our approach introduces no additional latency and reduces flickering. It is also lightweight, does not require retraining the model, and it can be applied to a wide variety of multi-stage architectures.