# Dyn-ASR: Compact, Multilingual Speech Recognition via Spoken Language and Accent Identification

arXiv: https://arxiv.org/abs/2108.02034 · HTML: https://mlsanity.com/paper/2108.02034/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 21 references that are in the map.
- First posted on arXiv 4 Aug 2021.

## Builds on (most cited first, 7 of 7)

- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [Deep Speech: Scaling up end-to-end speech recognition](https://mlsanity.com/paper/1412.5567/) (2014)
- [Massively Multilingual ASR: 50 Languages, 1 Model, 1 Billion Parameters](https://mlsanity.com/paper/2007.03001/) (2020)
- [QuartzNet: Deep Automatic Speech Recognition with 1D Time-Channel Separable Convolutions](https://mlsanity.com/paper/1910.10261/) (2019)
- [Large-Scale Multilingual Speech Recognition with a Streaming End-to-End Model](https://mlsanity.com/paper/1909.05330/) (2019)
- [Universal Phone Recognition with a Multilingual Allophone System](https://mlsanity.com/paper/2002.11800/) (2020)
- [Streaming End-to-End Bilingual ASR Systems with Joint Language Identification](https://mlsanity.com/paper/2007.03900/) (2020)

## Abstract (arXiv)

Running automatic speech recognition (ASR) on edge devices is non-trivial due to resource constraints, especially in scenarios that require supporting multiple languages. We propose a new approach to enable multilingual speech recognition on edge devices. This approach uses both language identification and accent identification to select one of multiple monolingual ASR models on-the-fly, each fine-tuned for a particular accent. Initial results for both recognition performance and resource usage are promising with our approach using less than 1/12th of the memory consumed by other solutions.