Tags

Type your tag names separated by a space and hit enter

Mandarin Electrolaryngeal Speech Recognition Based on WaveNet-CTC.
J Speech Lang Hear Res 2019; 62(7):2203-2212JS

Abstract

Purpose The application of Chinese Mandarin electrolaryngeal (EL) speech for laryngectomees has been limited by its drawbacks such as single fundamental frequency, mechanical sound, and large radiation noise. To improve the intelligibility of Chinese Mandarin EL speech, a new perspective using the automatic speech recognition (ASR) system was proposed, which can convert EL speech into healthy speech, if combined with text-to-speech. Method An ASR system was designed to recognize EL speech based on a deep learning model WaveNet and the connectionist temporal classification (WaveNet-CTC). This system mainly consists of 3 parts: the acoustic model, the language model, and the decoding model. The acoustic features are extracted during speech preprocessing, and 3,230 utterances of EL speech mixed with 10,000 utterances of healthy speech are used to train the ASR system. Comparative experiment was designed to evaluate the performance of the proposed method. Results The results show that the proposed ASR system has higher stability and generalizability compared with the traditional methods, manifesting superiority in terms of Chinese characters, Chinese words, short sentences, and long sentences. Phoneme confusion occurs more easily in the stop and affricate of EL speech than the healthy speech. However, the highest accuracy of the ASR could reach 83.24% when 3,230 utterances of EL speech were used to train the ASR system. Conclusions This study indicates that EL speech could be recognized effectively by the ASR based on WaveNet-CTC. This proposed method has a higher generalization performance and better stability than the traditional methods. A higher accuracy of the ASR system based on WaveNet-CTC can be obtained, which means that EL speech can be converted into healthy speech. Supplemental Material https://doi.org/10.23641/asha.8250830.

Authors+Show Affiliations

School of Biological Science & Medical Engineering, Beihang University, Beijing, China.School of Biological Science & Medical Engineering, Beihang University, Beijing, China. Beijing Research Center of Urban System Engineering, China.School of Biological Science & Medical Engineering, Beihang University, Beijing, China.School of Biological Science & Medical Engineering, Beihang University, Beijing, China.School of Biological Science & Medical Engineering, Beihang University, Beijing, China.

Pub Type(s)

Journal Article

Language

eng

PubMed ID

31200617

Citation

Qian, Zhaopeng, et al. "Mandarin Electrolaryngeal Speech Recognition Based On WaveNet-CTC." Journal of Speech, Language, and Hearing Research : JSLHR, vol. 62, no. 7, 2019, pp. 2203-2212.
Qian Z, Wang L, Zhang S, et al. Mandarin Electrolaryngeal Speech Recognition Based on WaveNet-CTC. J Speech Lang Hear Res. 2019;62(7):2203-2212.
Qian, Z., Wang, L., Zhang, S., Liu, C., & Niu, H. (2019). Mandarin Electrolaryngeal Speech Recognition Based on WaveNet-CTC. Journal of Speech, Language, and Hearing Research : JSLHR, 62(7), pp. 2203-2212. doi:10.1044/2019_JSLHR-S-18-0313.
Qian Z, et al. Mandarin Electrolaryngeal Speech Recognition Based On WaveNet-CTC. J Speech Lang Hear Res. 2019 Jul 15;62(7):2203-2212. PubMed PMID: 31200617.
* Article titles in AMA citation format should be in sentence-case
TY - JOUR T1 - Mandarin Electrolaryngeal Speech Recognition Based on WaveNet-CTC. AU - Qian,Zhaopeng, AU - Wang,Li, AU - Zhang,Shaochuan, AU - Liu,Chan, AU - Niu,Haijun, Y1 - 2019/06/14/ PY - 2019/6/16/pubmed PY - 2019/6/16/medline PY - 2019/6/16/entrez SP - 2203 EP - 2212 JF - Journal of speech, language, and hearing research : JSLHR JO - J. Speech Lang. Hear. Res. VL - 62 IS - 7 N2 - Purpose The application of Chinese Mandarin electrolaryngeal (EL) speech for laryngectomees has been limited by its drawbacks such as single fundamental frequency, mechanical sound, and large radiation noise. To improve the intelligibility of Chinese Mandarin EL speech, a new perspective using the automatic speech recognition (ASR) system was proposed, which can convert EL speech into healthy speech, if combined with text-to-speech. Method An ASR system was designed to recognize EL speech based on a deep learning model WaveNet and the connectionist temporal classification (WaveNet-CTC). This system mainly consists of 3 parts: the acoustic model, the language model, and the decoding model. The acoustic features are extracted during speech preprocessing, and 3,230 utterances of EL speech mixed with 10,000 utterances of healthy speech are used to train the ASR system. Comparative experiment was designed to evaluate the performance of the proposed method. Results The results show that the proposed ASR system has higher stability and generalizability compared with the traditional methods, manifesting superiority in terms of Chinese characters, Chinese words, short sentences, and long sentences. Phoneme confusion occurs more easily in the stop and affricate of EL speech than the healthy speech. However, the highest accuracy of the ASR could reach 83.24% when 3,230 utterances of EL speech were used to train the ASR system. Conclusions This study indicates that EL speech could be recognized effectively by the ASR based on WaveNet-CTC. This proposed method has a higher generalization performance and better stability than the traditional methods. A higher accuracy of the ASR system based on WaveNet-CTC can be obtained, which means that EL speech can be converted into healthy speech. Supplemental Material https://doi.org/10.23641/asha.8250830. SN - 1558-9102 UR - https://www.unboundmedicine.com/medline/citation/31200617/Mandarin_Electrolaryngeal_Speech_Recognition_Based_on_WaveNet-CTC L2 - https://pubs.asha.org/doi/full/10.1044/2019_JSLHR-S-18-0313?url_ver=Z39.88-2003&rfr_id=ori:rid:crossref.org&rfr_dat=cr_pub=pubmed DB - PRIME DP - Unbound Medicine ER -