# Analyzing the Quality and Stability of a Streaming End-to-End On-Device Speech Recognizer

arXiv: https://arxiv.org/abs/2006.01416 · HTML: https://mlsanity.com/paper/2006.01416/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Jun 2020.

## Built on by (most cited first, 7 of 7)

- [Dissecting User-Perceived Latency of On-Device E2E Speech Recognition](https://mlsanity.com/paper/2104.02207/) (2021)
- [Measuring the Accuracy of Automatic Speech Recognition Solutions](https://mlsanity.com/paper/2408.16287/) (2024)
- [Alignment Knowledge Distillation for Online Streaming Attention-based Speech Recognition](https://mlsanity.com/paper/2103.00422/) (2021)
- [DuplexCascade: Full-Duplex Speech-to-Speech Dialogue with VAD-Free Cascaded ASR-LLM-TTS Pipeline and Micro-Turn Optimization](https://mlsanity.com/paper/2603.09180/) (2026)
- [Flexi-Transducer: Optimizing Latency, Accuracy and Compute forMulti-Domain On-Device Scenarios](https://mlsanity.com/paper/2104.02232/) (2021)
- [Noisy Training Improves E2E ASR for the Edge](https://mlsanity.com/paper/2107.04677/) (2021)
- [Partial Rewriting for Multi-Stage ASR](https://mlsanity.com/paper/2312.09463/) (2023)

## Abstract (arXiv)

The demand for fast and accurate incremental speech recognition increases as the applications of automatic speech recognition (ASR) proliferate. Incremental speech recognizers output chunks of partially recognized words while the user is still talking. Partial results can be revised before the ASR finalizes its hypothesis, causing instability issues. We analyze the quality and stability of on-device streaming end-to-end (E2E) ASR models. We first introduce a novel set of metrics that quantify the instability at word and segment levels. We study the impact of several model training techniques that improve E2E model qualities but degrade model stability. We categorize the causes of instability and explore various solutions to mitigate them in a streaming E2E ASR system. Index Terms: ASR, stability, end-to-end, text normalization,on-device, RNN-T