Logo Lanfrica
  • Accueil
  • Atlas
  • Analyses
  • Documentation
  • Sign in

© 2026 Lanfrica. Tous droits réservés. Tous les droits d'auteur des ressources affichées sur le site Web Lanfrica appartiennent aux détenteurs de droits d'auteur d'origine, sauf indication contraire explicite.

Effects of Layer Freezing on Transferring a Speech Recognition System to Under-resourced Languages

Domaine:

natural language processing

Type de record:

paper
Créateur:
EbeZes
Hôte:avatar
In this paper, we investigate the effect of layer freezing on the effectiveness of model transfer in the area of automatic speech recognition. We experiment with Mozilla's DeepSpeech architecture on German and Swiss German speech datasets and compare the results of either training from scratch vs. transferring a pre-trained model. We compare different layer freezing schemes and find that even freezing only one layer already significantly improves results. Published at KONVENS 2021

Visit

arxiv.org

Tasks

automatic speech recognitionspeech processingtransfer learning

Tags

Computation and LanguageI.2.7

Similaires

Automatic speech recognition for under-resourced languages: A surveyImproving Speech Recognition for Under-resourced Languages Utilizing Audio-codecs for Data AugmentationSpeech recognition for under-resourced languages: Data sharing in hidden Markov model systemsAutomatic speech recognition for an under-resourced language - amharicDeploying a Speech Recognition Model for Under-Resourced Languages: A Case Study on Dioula Wake Words 1, 2, 3, and 4A primer on getting neologisms from foreign languages to under-resourced languages

Automatic speech recognition for under-resourced languages: A survey

(Impact-F 1.28 estim. in 2012) International audience no abstract

Improving Speech Recognition for Under-resourced Languages Utilizing Audio-codecs for Data Augmentation

Presenter: Nirayo Hailu Gebreegziabher, Ingo Siegert, Andreas Nürnberger, MMSP 2020, Virtual Event,

Speech recognition for under-resourced languages: Data sharing in hidden Markov model systems

For purposes of automated speech recognition in under-resourced environments, t

Automatic speech recognition for an under-resourced language - amharic

Deploying a Speech Recognition Model for Under-Resourced Languages: A Case Study on Dioula Wake Words 1, 2, 3, and 4

A primer on getting neologisms from foreign languages to under-resourced languages

Mainly due to lack of support, most under-resourced languages have a reduced lexicon in most realms