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.

Multilingual Bottleneck Features for Improving ASR Performance of Code-Switched Speech in Under-Resourced Languages

Domaine:

natural language processing

Type de record:

paper
Créateur:
PadBisDe van der Westhuizen, Ewald
Éditeur:
arXiv
Hôte:avatar
In this work, we explore the benefits of using multilingual bottleneck features (mBNF) in acoustic modelling for the automatic speech recognition of code-switched (CS) speech in African languages. The unavailability of annotated corpora in the languages of interest has always been a primary challenge when developing speech recognition systems for this severely under-resourced type of speech. Hence, it is worthwhile to investigate the potential of using speech corpora available for other better-resourced languages to improve speech recognition performance. To achieve this, we train a mBNF extractor using nine Southern Bantu languages that form part of the freely available multilingual NCHLT corpus. We append these mBNFs to the existing MFCCs, pitch features and i-vectors to train acoustic models for automatic speech recognition (ASR) in the target code-switched languages. Our results show that the inclusion of the mBNF features leads to clear performance improvements over a baseline trained without the mBNFs for code-switched English-isiZulu, English-isiXhosa, English-Sesotho and English-Setswana speech. In Proceedings of The First Workshop on Speech Technologies for Code-Switching in Multilingual Communities

Visit

doi.orgarxiv.org

Tasks

automatic speech recognitioncode switchingspeech processing

Languages

SetswanaSotho, SouthernXhosaZulu

Tags

Audio and Speech Processing (eess.AS)Computation and Language (cs.CL)Machine Learning (cs.LG)Sound (cs.SD)FOS: Electrical engineering, electronic engineering, information engineeringFOS: Electrical engineering, electronic engineering, information engineeringFOS: Computer and information sciencesFOS: Computer and information sciences

Licenses

Creative Commons Attribution 4.0 Internationalhttps://creativecommons.org/licenses/by/4.0/legalcode

Similaires

Semi-supervised Development of ASR Systems for Multilingual Code-switched Speech in Under-resourced LanguagesMultilingual Neural Network Acoustic Modelling for ASR of Under-Resourced English-isiZulu Code-Switched SpeechImproving N-Best Rescoring in Under-Resourced Code-Switched Speech Recognition Using Pretraining and Data AugmentationMultilingual training set selection for ASR in under-resourced Malian languagesASR-free CNN-DTW keyword spotting using multilingual bottleneck features for almost zero-resource languagesCode-Switched Language Modelling Using a Code Predictive Lstm in Under-Resourced South African Languages

Semi-supervised Development of ASR Systems for Multilingual Code-switched Speech in Under-resourced Languages

This paper reports on the semi-supervised development of acoustic and language models for under-resourced, code-switched speech in five South African languages. Two approaches are considered. The first constructs four separate bilingual automatic speech recognisers

Multilingual Neural Network Acoustic Modelling for ASR of Under-Resourced English-isiZulu Code-Switched Speech

Improving N-Best Rescoring in Under-Resourced Code-Switched Speech Recognition Using Pretraining and Data Augmentation

We present improvements in n-best rescoring of code-switched speech achieved by n-gram augmentation

Multilingual training set selection for ASR in under-resourced Malian languages

We present first speech recognition systems for the two severely under-resourced Malian languages Ba

ASR-free CNN-DTW keyword spotting using multilingual bottleneck features for almost zero-resource languages

We consider multilingual bottleneck features (BNFs) for nearly zero-resource keyword spotting. This forms part of a United Nations effort using keyword spotting to support humanitarian relief programmes in parts of Africa where languages are severely under-resource

Code-Switched Language Modelling Using a Code Predictive Lstm in Under-Resourced South African Languages