Development of a Kiswahili text to speech system

Gakuru, Mucemi; Iraki, Frederick Kang’ethe; Tucker, Roger C. F.; Shalonova, Ksenia; Ngugi, K.

doi:10.21437/interspeech.2005-522

Cited by 8 publications

(2 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The CMU Wilderness dataset [11] includes up to 20 hours of high-quality, single-speaker data for several African languages, but it is not publicly available and the alignments can contain noise. TTS systems research for African languages has comprised development efforts in frameworks like Festival [25] or MaryTTS [26] for Yorùbá [27,28], Ibibio [29], Amharic [30], Fon [31], isiZulu [32], KiSwahili [33]. While many of these systems used concatenative synthesis, in large part because the available corpora were small, there have also been investigations into statistical parametric speech synthesis for Ibibio [34].…”

Section: Related Workmentioning

confidence: 99%

BibleTTS: a large, high-fidelity, multilingual, and uniquely African speech corpus

Meyer¹,

Adelani²,

Casanova³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

Section: Related Workmentioning

confidence: 99%

BibleTTS: a large, high-fidelity, multilingual, and uniquely African speech corpus

Meyer¹,

Adelani²,

Casanova³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…In addition to Open.Bible and Bible.is data that we aligned, we obtained data from the following sources in utterance format: LLSTI: The Local Language Speech Technology Initiative project developed TTS datasets for localization of speech technology. We obtained Ibibio [24] and Kiswahili [25] by converting the publicly distributed lpc and res files to wav using Festvox tools.…”

Section: Found Data Sourcesmentioning

confidence: 99%

Building African Voices

Perez¹,

Neubig²,

Black³

2022

Preprint

View full text Add to dashboard Cite

Modern speech synthesis techniques can produce naturalsounding speech given sufficient high-quality data and compute resources. However, such data is not readily available for many languages. This paper focuses on speech synthesis for low-resourced African languages, from corpus creation to sharing and deploying the Text-to-Speech (TTS) systems. We first create a set of general-purpose instructions on building speech synthesis systems with minimum technological resources and subject-matter expertise. Next, we create new datasets and curate datasets from "found" data (existing recordings) through a participatory approach while considering accessibility, quality, and breadth. We demonstrate that we can develop synthesizers that generate intelligible speech with 25 minutes of created speech, even when recorded in suboptimal environments. Finally, we release the speech data, code, and trained voices for 12 African languages to support researchers and developers.

show abstract