Central Kurdish Text-to-Speech Synthesis with Novel End-to-End Transformer Training

Recent advancements in text-to-speech (TTS) models have aimed to streamline the two-stage process into a single-stage training approach. However, many single-stage models still lag behind in audio quality, particularly when handling Kurdish text and speech. There is a critical need to enhance text-t...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Algorithms Jg. 17; H. 7; S. 292
Hauptverfasser: Ahmad, Hawraz, Rashid, Tarik
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Basel MDPI AG 01.07.2024
Schlagworte:
central Kurdish text to speech (TTS)
Coders
Datasets
deep learning
Efficiency
end-to-end autoregressive transformers
Linguistics
Methods
Performance evaluation
Real time
Semantics
Speech
Speech recognition
transformers
Waveforms
ISSN:1999-4893, 1999-4893
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Recent advancements in text-to-speech (TTS) models have aimed to streamline the two-stage process into a single-stage training approach. However, many single-stage models still lag behind in audio quality, particularly when handling Kurdish text and speech. There is a critical need to enhance text-to-speech conversion for the Kurdish language, particularly for the Sorani dialect, which has been relatively neglected and is underrepresented in recent text-to-speech advancements. This study introduces an end-to-end TTS model for efficiently generating high-quality Kurdish audio. The proposed method leverages a variational autoencoder (VAE) that is pre-trained for audio waveform reconstruction and is augmented by adversarial training. This involves aligning the prior distribution established by the pre-trained encoder with the posterior distribution of the text encoder within latent variables. Additionally, a stochastic duration predictor is incorporated to imbue synthesized Kurdish speech with diverse rhythms. By aligning latent distributions and integrating the stochastic duration predictor, the proposed method facilitates the real-time generation of natural Kurdish speech audio, offering flexibility in pitches and rhythms. Empirical evaluation via the mean opinion score (MOS) on a custom dataset confirms the superior performance of our approach (MOS of 3.94) compared with that of a one-stage system and other two-staged systems as assessed through a subjective human evaluation.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1999-4893
1999-4893
DOI:10.3390/a17070292