Deprecated: The each() function is deprecated. This message will be suppressed on further calls in /home/zhenxiangba/zhenxiangba.com/public_html/phproxy-improved-master/index.php on line 456
Paper page - Continual Learning for On-Device Speech Recognition using Disentangled Conformers
[go: Go Back, main page]

Papers
arxiv:2212.01393

Continual Learning for On-Device Speech Recognition using Disentangled Conformers

Published on Dec 2, 2022
Authors:
,
,
,
,
,

Abstract

DisConformer models, featuring a disentangled architecture, achieve superior general ASR performance and efficient speaker-specific adaptation compared to baselines on LibriContinual.

Automatic speech recognition research focuses on training and evaluating on static datasets. Yet, as speech models are increasingly deployed on personal devices, such models encounter user-specific distributional shifts. To simulate this real-world scenario, we introduce LibriContinual, a continual learning benchmark for speaker-specific domain adaptation derived from LibriVox audiobooks, with data corresponding to 118 individual speakers and 6 train splits per speaker of different sizes. Additionally, current speech recognition models and continual learning algorithms are not optimized to be compute-efficient. We adapt a general-purpose training algorithm NetAug for ASR and create a novel Conformer variant called the DisConformer (Disentangled Conformer). This algorithm produces ASR models consisting of a frozen 'core' network for general-purpose use and several tunable 'augment' networks for speaker-specific tuning. Using such models, we propose a novel compute-efficient continual learning algorithm called DisentangledCL. Our experiments show that the DisConformer models significantly outperform baselines on general ASR i.e. LibriSpeech (15.58% rel. WER on test-other). On speaker-specific LibriContinual they significantly outperform trainable-parameter-matched baselines (by 20.65% rel. WER on test) and even match fully finetuned baselines in some settings.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2212.01393
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2212.01393 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2212.01393 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2212.01393 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.