Mongolian Text-to-Speech System Based on Deep Neural Network

Liu, Rui; Bao, Feilong; Gao, Guanglai; Wang, Yonghe

doi:10.1007/978-981-10-8111-8_10

Cited by 23 publications

(9 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We now evaluate the effectiveness of the proposed enhanced word embedding techniques in phrase break prediction, and their contributions to a DNN-based Mongolian TTS system [72].…”

Section: Methodsmentioning

confidence: 99%

“…Mongolian speech data: We conducted experiments on a well-formulated Mongolian TTS database, that has rich phonetic and prosodic content [72][73][74]. The database contains Mongolian daily expressions recorded by a female native speaker.…”

Section: A Experimental Corporamentioning

confidence: 99%

“…We conducted listening tests to further evaluate the contributions of phrase break prediction to speech synthesis quality. We compare four DNN-based Mongolian TTS systems [72], which differ only in terms of prosodic break inputs.…”

Section: F Subjective Evaluationmentioning

confidence: 99%

See 2 more Smart Citations

Exploiting Morphological and Phonological Features to Improve Prosodic Phrasing for Mongolian Speech Synthesis

Liu

Şişman

Bao

et al. 2021

IEEE/ACM Trans. Audio Speech Lang. Process.

Self Cite

View full text Add to dashboard Cite

Prosodic phrasing is an important factor that affects naturalness and intelligibility in text-to-speech synthesis. Studies show that deep learning techniques improve prosodic phrasing when large text and speech corpus are available. However, for low-resource languages, such as Mongolian, prosodic phrasing remains a challenge for various reasons. First, the database suitable for system training is limited; Second, word composition knowledge that is prosody-informing has not been used in prosodic phrase modeling. To address these problems, in this paper, we propose a feature augmentation method in conjunction with a self-attention neural classifier. We augment input text with morphological and phonological decompositions of words to enhance the text encoder. We study the use of self-attention classifier, that makes use of global context of a sentence, as a decoder for phrase break prediction. Both objective and subjective evaluations validate the effectiveness of the proposed phrase break prediction framework, that consistently improves voice quality in a Mongolian text-to-speech synthesis system.

show abstract

“…We now evaluate the effectiveness of the proposed enhanced word embedding techniques in phrase break prediction, and their contributions to a DNN-based Mongolian TTS system [72].…”

Section: Methodsmentioning

confidence: 99%

Section: A Experimental Corporamentioning

confidence: 99%

See 1 more Smart Citation

Exploiting Morphological and Phonological Features to Improve Prosodic Phrasing for Mongolian Speech Synthesis

Liu

Şişman

Bao

et al. 2021

IEEE/ACM Trans. Audio Speech Lang. Process.

Self Cite

View full text Add to dashboard Cite

show abstract

“…We carried out comparative evaluation through a DNN-based Mongolian TTS system [29]. A group of 10 subjects were asked to choose which one was better in terms of the naturalness of synthesis speech.…”

Section: Preference Testmentioning

confidence: 99%

“…However, the Mongolian PB prediction research is at its initial stage compared with Chinese and English [27]. There are many works on Mongolian Text-to-Speech (TTS) which have made great contributions [28,29], but the naturalness of synthetic speech is less than satisfactory especially without a good rhythm.…”

Section: Introductionmentioning

confidence: 99%

Improving Mongolian Phrase Break Prediction by Using Syllable and Morphological Embeddings with BiLSTM Model

et al. 2018

Self Cite

View full text Add to dashboard Cite

In the speech synthesis systems, the phrase break (PB) prediction is the first and most important step. Recently, the state-of-the-art PB prediction systems mainly rely on word embeddings. However this method is not fully applicable to Mongolian language, because its word embeddings are inadequate trained, owing to the lack of resources. In this paper, we introduce a bidirectional Long Short Term Memory (BiLSTM) model which combined word embeddings with syllable and morphological embedding representations to provide richer and multi-view information which leverages the agglutinative property. Experimental results show the proposed method outperforms compared systems which only used the word embeddings. In addition, further analysis shows that it is quite robust to the Out-of-Vocabulary (OOV) problem owe to the refined word embedding. The proposed method achieves the state-of-the-art performance in the Mongolian PB prediction.

show abstract

Mongolian Word Segmentation Based on Three Character Level Seq2Seq Models

Liu

Gao

et al. 2018

Neural Information Processing

View full text Add to dashboard Cite

Mongolian Text-to-Speech System Based on Deep Neural Network

Cited by 23 publications

References 13 publications

Exploiting Morphological and Phonological Features to Improve Prosodic Phrasing for Mongolian Speech Synthesis

Exploiting Morphological and Phonological Features to Improve Prosodic Phrasing for Mongolian Speech Synthesis

Improving Mongolian Phrase Break Prediction by Using Syllable and Morphological Embeddings with BiLSTM Model

Mongolian Word Segmentation Based on Three Character Level Seq2Seq Models

Contact Info

Product

Resources

About