Logo Lanfrica

Analyzing cross-language similarities to enhance low-resource text-to-speech via transfer learning, case study: the Moroccan Berber Amazigh

Type de record:

paper
Créateur:
FatImaNaoAno
Éditeur:
Spr
Hôte:

Tasks

speech processingtext to speechtransfer learning

Languages

AmazighBerber

Licenses

https://www.springernature.com/gp/researchers/text-and-data-mininghttps://www.springernature.com/gp/researchers/text-and-data-mining

Similaires

Text-to-speech system for low-resource language using cross-lingual transfer learning and data augmentation

Abstract Deep learning techniques are currently being applied in automated text-to-speech (TTS) sys

Using Transfer Learning to Realize Low Resource Dungan Language Speech Synthesis

This article presents a transfer-learning-based method to improve the synthesized speech quality of

Low-data? No problem: low-resource, language-agnostic conversational text-to-speech via F0-conditioned data augmentation

The availability of data in expressive styles across languages is limited, and recording sessions ar

The Effects of Input Type and Pronunciation Dictionary Usage in Transfer Learning for Low-Resource Text-to-Speech

We compare phone labels and articulatory features as input for cross-lingual transfer learning in te

Enhancing Low-Resource Language Reasoning via High-Resource Language Feature Transfer

Large language models exhibit substantial performance variation across languages, even when solving

Adversarial Text-to-Speech for low-resource languages

Improving the adversarial TTS models for low-resource languages by utilizing the high-frequency similarities between the different languages.