Implementation of Three Text to Speech Systems for Kurdish Language

Bahrampour, Anvar; Barkhoda, Wafa; Azami, Bahram Zahir

doi:10.1007/978-3-642-10268-4_38

Cited by 9 publications

(4 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several synthesis models based on allophones, syllables, and diphones for the Kurdish language were developed in [43] , The allophone-based model had the lowest quality, and in actuality, it was the most difficult to use. The syllable-based method had a good overall quality and high intelligibility.…”

Section: Kurdish Tts Workmentioning

confidence: 99%

End-to-End Kurdish Speech Synthesis Based on Transfer Learning

muhamad

Veisi

2022

PJBAS

View full text Add to dashboard Cite

A text-to-speech (TTS) system converts the texts into speech in a specific language. Several TTS systems generate natural-like speech signals in numerous languages, such as English. On the other hand, the Kurdish language has just been examined. Existing preliminary research on Kurdish speech synthesis has utilized old methods and has generated low-quality speech. They also lack important aspects of speech, including intonation, emphasis, and rhythm. Some approaches were presented to address these challenges, including the use of concatenative systems. For example, the unit selection or statistical parametric methods. On the other hand, they need a great deal of time, effort, and domain knowledge. An additional factor for Kurdish speech synthesizers' low performance is the absence of publicly available speech corpora, unlike English, which has many freely-available corpora and audiobooks. The motivation of this paper is to create a Central Kurdish speech corpus and generate a human-like speech from the Kurdish text. This paper explains how to utilize Tacotron 2, an end-to-end neural network architecture and HiFi-GAN vocoder, to produce a high-quality, realistic, and human-like Kurdish voice. This work utilizes "text, audio" pairings, which contain 10 hours of recorded audio samples and texts collected from the Internet and textbooks. It shows how to use English character embedding as the pre-trained knowledge with Kurdish characters as input and how to preprocess these audio examples to get a great outcome. Our evaluations for various types of texts show a mean opinion score of 4.1, comparable with state-of-the-art synthesizers in other languages.

show abstract

Section: Kurdish Tts Workmentioning

confidence: 99%

End-to-End Kurdish Speech Synthesis Based on Transfer Learning

muhamad

Veisi

2022

PJBAS

View full text Add to dashboard Cite

show abstract

“…Year Field open-source applicable dialects 2012 Dialectology no no Sorani 2013 Dialectology no yes Sorani, Kurmanji (Hassani and Medjedovic, 2016) 2016 Dialectology no yes Sorani, Kurmanji (Malmasi, 2016) 2016 Dialectology yes yes Sorani (Al-Talabani et al, 2017) 2017 Dialectology no yes Sorani, Kurmanji, Gorani (Littell et al, 2016) 2016 Information retrieval and Text mining no yes Sorani (Hassani, 2017b) 2017 Information retrieval and Text mining yes yes Sorani, Kurmanji (Esmaili, 2012) 2012 Information retrieval and Text mining no no Sorani 2014 Information retrieval and Text mining yes yes Sorani, Kurmanji (Jaf, 2016) 2016 2010 Morphological and syntactic analysis yes yes Sorani 2010 Morphological and syntactic analysis yes yes Kurmanji 2013 Morphological and syntactic analysis yes yes Sorani (Jaf and Ramsay, 2014) 2014 Morphological and syntactic analysis no yes Sorani (Jaf and Ramsay, 2016) 2016 Morphological and syntactic analysis no yes Sorani (Gökırmak and Tyers, 2017) 2017 Morphological and syntactic analysis yes yes Kurmanji (Salavati and Ahmadi, 2018) 2018 (Kamal and Hassani, 2020) 2020 Sign language recognition yes yes Sorani (Daneshfar et al, 2009) 2009 Speech recognition no yes Sorani 2009 Speech recognition no no Sorani (Bahrampour et al, 2009) 2009 Speech recognition no yes Sorani (Hassani and Kareem, 2011) 2011…”

Section: A Appendixmentioning

confidence: 99%

KLPT – Kurdish Language Processing Toolkit

Ahmadi¹

2020

Proceedings of Second Workshop for NLP Open Source Software (NLP-OSS)

View full text Add to dashboard Cite

Despite the recent advances in applying language-independent approaches to various natural language processing tasks thanks to artificial intelligence, some language-specific tools are still essential to process a language in a viable manner. Kurdish language is a lessresourced language with a notable diversity in dialects and scripts and lacks basic language processing tools. To address this issue, we introduce a language processing toolkit to handle such a diversity in an efficient way. Our toolkit is composed of fundamental components such as text preprocessing, stemming, tokenization, lemmatization and transliteration and is able to get further extended by future developers. This project is publicly available 1 .

show abstract

“…Bahrampour et al (2009) state that the allophone based system has the worst quality, the syllable based system displays the intermediate overall quality and high intelligibility, and the diphone based TTS system shows the best quality, its intelligibility and naturalness are high and the overall quality is acceptable. According to , the diphone based TTS system proved to be the most natural one; meanwhile intelligibilities of all the systems are acceptable.…”

Section: Introductionmentioning

confidence: 99%

Phoneme vs. Diphone in Unit Selection TTS of Lithuanian

Kasparaitis¹,

Kancys²

2018

BJMC

View full text Add to dashboard Cite

Abstract. The present paper deals with choosing the base type for the unit selection speech synthesis method of the Lithuanian language. Phoneme and diphone units have been examined. Besides, two different methods of joining costs calculation were employed in a diphone synthesizer: one was based on the spectral similarity and the other was based on phonological classes of the sounds to be joined. Synthesizers were evaluated according to their performance, algorithm complexity, the number of joins in a synthesized speech and the human listeners' subjective judgment. Experimental testing showed that the diphone synthesizer based on phonological classes was much more acceptable to the listeners than the one based on the spectral similarity. The diphone synthesizer based on phonological classes outperformed the phonemic synthesizer in terms of performance and the number of joins though it was somewhat less acceptable to human listeners.

show abstract

Implementation of Three Text to Speech Systems for Kurdish Language

Cited by 9 publications

References 18 publications

End-to-End Kurdish Speech Synthesis Based on Transfer Learning

End-to-End Kurdish Speech Synthesis Based on Transfer Learning

KLPT – Kurdish Language Processing Toolkit

Phoneme vs. Diphone in Unit Selection TTS of Lithuanian

Contact Info

Product

Resources

About