paper-with-me

Papers

Improving Low-Resource Dialect Classification Using Retrieval-based Voice Conversion

2025-07-04 · Lea Fischbach, Akbar Karimi, Caroline Kleen, Alfred Lameli, Lucie Flek arxiv

Deep learning models for dialect identification are often limited by the scarcity of dialectal data. To address this challenge, we propose to use Retrieval-based Voice Conversion (RVC) as an effective data augmentation method for a low-resource German dialect classification task. By converting audio samples to a uniform target speaker, RVC minimizes speaker-related variability, enabling models to focus on dialect-specific linguistic and phonetic features. Our experiments demonstrate that RVC enhances classification performance when utilized as a standalone augmentation method. Furthermore, combining RVC with other augmentation methods such as frequency masking and segment removal leads to additional performance gains, highlighting its potential for improving dialect classification in low-resource scenarios.

📄 PDF Abstract BibTeX arXiv:2507.03641

Code (0)

등록된 구현이 없습니다.

Tasks

Data AugmentationVoice Conversion

Similar Papers 제목 키워드 기반

Custom Data Augmentation for low resource ASR using Bark and Retrieval-Based Voice Conversion

2023-11-24 · Anand Kamble, Aniket Tathe, Suyash Kumbharkar, Atharva Bhandare 외

This paper proposes two innovative methodologies to construct customized Common Voice datasets for low-resource languages like Hindi. The first methodology leverages Bark, a transformer-based text-to-audio model develope…

Data AugmentationRetrievalVoice Conversion

Saar-Voice: A Multi-Speaker Saarbrücken Dialect Speech Corpus

2026-04-13 · Lena S. Oberkircher, Jesujoba O. Alabi, Dietrich Klakow, Jürgen Trouvain arxiv

Natural language processing (NLP) and speech technologies have made significant progress in recent years; however, they remain largely focused on standardized language varieties. Dialects, despite their cultural signific…

Voice Conversion Improves Cross-Domain Robustness for Spoken Arabic Dialect Identification

2025-05-30 · Badr M. Abdullah, Matthew Baas, Bernd Möbius, Dietrich Klakow

Arabic dialect identification (ADI) systems are essential for large-scale data collection pipelines that enable the development of inclusive speech technologies for Arabic language varieties. However, the reliability of …

Dialect IdentificationVoice Conversion

Crowdsourcing Latin American Spanish for Low-Resource Text-to-Speech

2020-05-01 · LREC 2020 5 · Adriana Guevara-Rukoz, Isin Demirsahin, Fei He, Shan-Hui Cathy Chu 외

In this paper we present a multidialectal corpus approach for building a text-to-speech voice for a new dialect in a language with existing resources, focusing on various South American dialects of Spanish. We first pres…

text-to-speechText to Speech

Dziri Voicebot: An End-to-End Low-Resource Speech-to-Speech Conversational System for Algerian Dialect

2026-06-24 · Dihia Lanasri, Rebeh Imane Ammar Aouchiche, Abdelkarim Remmide, Fairouz Taki 외 arxiv

Automatic speech and language technologies are still heavily biased toward high-resource languages, limiting their applicability to dialectal and low-resource settings such as Algerian Dialect. This language presents add…

Natural Language UnderstandingText-To-Speech SynthesisIntent ClassificationResponse Generation