Massively Multilingual ASR on 70 Languages: Tokenization, Architecture, and Generalization Capabilities

11/10/2022
by   Andros Tjandra, et al.
0

End-to-end multilingual ASR has become more appealing because of several reasons such as simplifying the training and deployment process and positive performance transfer from high-resource to low-resource languages. However, scaling up the number of languages, total hours, and number of unique tokens is not a trivial task. This paper explores large-scale multilingual ASR models on 70 languages. We inspect two architectures: (1) Shared embedding and output and (2) Multiple embedding and output model. In the shared model experiments, we show the importance of tokenization strategy across different languages. Later, we use our optimal tokenization strategy to train multiple embedding and output model to further improve our result. Our multilingual ASR achieves 13.9 average WER relative improvement compared to monolingual models. We show that our multilingual ASR generalizes well on an unseen dataset and domain, achieving 9.5 and finetuning, respectively.

READ FULL TEXT

page 3

page 4

research
07/06/2020

Massively Multilingual ASR: 50 Languages, 1 Model, 1 Billion Parameters

We study training a single acoustic model for multiple languages with th...
research
04/30/2021

Scaling End-to-End Models for Large-Scale Multilingual ASR

Building ASR models across many language families is a challenging multi...
research
02/22/2023

UML: A Universal Monolingual Output Layer for Multilingual ASR

Word-piece models (WPMs) are commonly used subword units in state-of-the...
research
05/13/2020

DARTS-ASR: Differentiable Architecture Search for Multilingual Speech Recognition and Adaptation

In previous works, only parameter weights of ASR models are optimized un...
research
06/25/2020

Neural Machine Translation for Multilingual Grapheme-to-Phoneme Conversion

Grapheme-to-phoneme (G2P) models are a key component in Automatic Speech...
research
11/14/2018

Almost Zero-Resource ASR-free Keyword Spotting using Multilingual Bottleneck Features and Correspondence Autoencoders

We compare features for dynamic time warping based keyword spotting in a...
research
07/03/2023

Multilingual Contextual Adapters To Improve Custom Word Recognition In Low-resource Languages

Connectionist Temporal Classification (CTC) models are popular for their...

Please sign up or login with your details

Forgot password? Click here to reset