基于语义的汉语普通话电子喉语音转换增强

doi:10.3969/j.issn.0372-2112.2020.05.002

电子学报 ›› 2020, Vol. 48 ›› Issue (5): 840-845.DOI: 10.3969/j.issn.0372-2112.2020.05.002

基于语义的汉语普通话电子喉语音转换增强

钱兆鹏¹, 肖克晶², 刘蝉³, 孙悦¹

1. 北京航空航天大学生物与医学工程学院, 北京 100191;
2. 中国人民大学信息学院, 北京 100872;
3. 北京机械设备研究所, 北京 100854

收稿日期:2019-08-05 修回日期:2019-10-08 出版日期:2020-05-25
- 通讯作者:
- 钱兆鹏
- 作者简介:
- 肖克晶 女,1991年生于河南信阳.现为中国人民大学博士研究生.主要研究方向为自然语言处理,语义分析与文本挖掘.E-mail:xiaokejing0501@163.com
- 基金资助:
- 北京市自然科学基金 (No.4194079）; 北京航空航天大学虚拟现实国家重点实验室开放课题 (No.VRLAB2018B06）; 北京工商大学农产品质量安全追溯技术及应用国家工程实验室开放课题 (No.AQT-2018-YB4）

Voice Conversion for Enhancing Mandarin Electro-Laryngeal Speech Based on Semantic Information

QIAN Zhao-peng¹, XIAO Ke-jing², LIU Chan³, SUN Yue¹

1. School of Biological Science&Medical Engineering, Beihang University, Beijing 100191, China;
2. Information School, Renmin University of China, Beijing 100872, China;
3. Beijing Mechanical Equipment Institute, Beijing 100854, China

Received:2019-08-05 Revised:2019-10-08 Online:2020-05-25 Published:2020-05-25

摘要/Abstract

摘要： 电子喉语音存在基频单一、发声机械、辐射噪声大等多种缺陷，这严重影响了电子喉语音可懂度和自然度，特别是对汉语普通话之类的声调语言，问题尤其严重.汉语普通话电子喉语音识别存在辅音混淆的问题并且识别结果没有声调，因此本文在识别结果的基础之上设计了拼音拼写修正器和声调标注工具，再结合基于Tacotron-2的TTS实现了电子喉语音向正常语音的转换.客观评价实验结果表明，拼音拼写修正器可以提高拼音准确率，声调标注在有上下文的语义环境中具有较高准确率.主观听力测试结果表明，本文所提方法在不同语言水平上提高了汉语普通话电子喉语音的可懂度和自然度.研究结果表明，本文设计的方法可以将不带声调的电子喉语音转换为正常语音，相比于传统语音转换方法具有更高的性能.

关键词: 电子喉语音, 拼音修正, 拼音声调标注, 语音转换

Abstract: The Electro-Laryngeal (EL) speech has some drawbacks such as single fundamental frequency,mechanical sound and large radiation noise.The drawbacks affect the intelligibility and naturalness of the EL speech.Especially,the tonal language such as Mandarin EL speech would be worse understanding.In this paper,the spelling corrector for pinyin and the tone labelling tool are designed to solve the problems that Mandarin EL speech recognition has some errors in consonants and the recognition result has no tone.The result is synthesized into the healthy speech by TTS based on Tacotron-2.The objective evaluation results show that the accuracy of pinyin spelling corrector has been improved; the accuracy of tone labelling under contextual environment is very high.The subjective results shows the proposed method can improve the intelligibility and naturalness of the EL speech a lot.The results illustrate that the proposed method can convert the EL speech without tone into the healthy speech.And the proposed method performs better than the traditional method based on speech signal processing.

Key words: electro-laryngeal speech, pinyin spelling corrector, pinyin tone labelling, voice conversion

中图分类号:

TP391.42

钱兆鹏, 肖克晶, 刘蝉, 孙悦. 基于语义的汉语普通话电子喉语音转换增强[J]. 电子学报, 2020, 48(5): 840-845.

QIAN Zhao-peng, XIAO Ke-jing, LIU Chan, SUN Yue. Voice Conversion for Enhancing Mandarin Electro-Laryngeal Speech Based on Semantic Information[J]. Acta Electronica Sinica, 2020, 48(5): 840-845.

参考文献

[1] Liu H,Ng M L.Electrolarynx in voice rehabilitation[J].Auris Nasus Larynx,2007,34(3):327-332.
[2] Watson P J,Schlauch R S.Fundamental frequency variation with an electrolarynx improves speech understanding:A case study[J].American Journal of Speech-Language Pathology,2009,18(2):162-167.
[3] Guo L,Nagle K F,Heaton J T.Generating tonal distinctions in Mandarin Chinese using an electrolarynx with preprogrammed tone patterns[J].Speech Communication,2016,78:34-41.
[4] Goldstein E A,Heaton J T,Stepp C E,Hillman RE.Training effects on speech production using a hands-free electromyographically controlled electrolarynx[J].Journal of Speech,Language,and Hearing Research,2007,50(2):335-351.
[5] Wang L,Feng Y,Yang Z,Niu HJ.Development and evaluation of wheel-controlled pitch-adjustable electrolarynx[J].Medical & Biological Engineering & Computing,2017,55(8):1463-1472.
[6] Goldstein E A,Heaton J T,Kobler J B,Stanley G B,Hillman R E.Design and implementation of a hands-free electrolarynx device controlled by neck strap muscle electromyographic activity[J].IEEE Transactions on Biomedical Engineering,2004,51(2):325-332.
[7] Liu HJ,Zhao Q,Wan MX,Wang SP.Enhancement of electrolarynx speech based on auditory masking[J].IEEE Transactions on Biomedical Engineering,2006,53(5):865-874.
[8] Li W,Zhaopeng Q,Yijun F,Haijun Niu.Design and preliminary evaluation of electrolarynx with F0 control based on capacitive touch technology[J].IEEE Transactions on Neural Systems and Rehabilitation Engineering,2018,26(3):629-636.
[9] Nakamura K,Toda T,Saruwatari H,Shikano K.Speaking-aid systems using GMM-based voice conversion for electrolaryngeal speech[J].Speech Communication,2012,54(1):134-146.
[10] Qian Z,Wang L,Zhang S,Liu C,Niu H.Mandarin electrolaryngeal speech recognition based on wWaveNet-CTC[J].Journal of Speech,Language,and Hearing Research,2019,62(7):2203-2212.
[11] Hyman M.An experimental study of the relative sound pressure,duration,intelligibility,and aesthetic aspects of the speech of artificial-larynx,esophageal,and normal speakers[D].USA:The Ohio State University,1953.
[12] Levenshtein V I.Binary codes capable of correcting deletions,insertions,and reversals[J].Soviet Physics Doklady,1966,10(8):707-710.
[13] Ristad E S,Yianilos P N.Learning string-edit distance[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1998,20(5):522-532.
[14] Kukich K.Techniques for automatically correcting words in text[J].Acm Computing Surveys (CSUR),1992,24(4):377-439.
[15] Huang Z,Xu W,Yu K.Bidirectional LSTM-CRF models for sequence tagging[J/OL].https://arxiv.org/abs/1508.01991v1.2015-08-09.
[16] Ma X,Hovy E.End-to-end sequence labeling via bi-directional lstm-cnns-crf[J/OL].https://arxiv.org/abs/1603.01354.2016-05-29.
[17] Toda T,Tokuda K.A speech parameter generation algorithm considering global variance for HMM-based speech synthesis[J].IEICE TRANSACTIONS on Information and Systems,2007,90(5):816-824.
[18] Shen J,Pang RM,Weiss RJ,Schuster M,Jaitly N,Yang ZH,Chen ZF,Zhang Y,Wang YX,Skerry-Ryan RJ,Saurous RA,Agiomyrgiannakis Y,Wu YH.Natural tts synthesis by conditioning wavenet onmel spectrogram predictions[A].2018 IEEE International Conference on Acoustics,Speech and Signal Processing (ICASSP)[C].Calgary IEEE Press,2018.4779-4783.
[19] Kernighan M D,Church K W,Gale W A.A spelling correction program based on a noisy channel model[A].Proceedings of the 13^th conference on Computational Linguistics-Volume 2.Association for Computational Linguistics[C].Finland:ACL Press,1990.205-210.
[20] Brill E,Moore R C.An improved error model for noisychannel spelling correction[A].Proceedings of the 38^th Annual Meeting on Association for Computational Linguistics.Association for Computational Linguistics[C].Hong Kong:ACL Press,2000.286-293.
[21] Golding A R.A Bayesian hybrid method for context-sensitive spelling correction[J/OL].http://arxiv.org/abs/cmp-lg/9606001v1.1996-01-03.
[22] Mangu L,Brill E.Automatic rule acquisition for spelling correction[A].ICML[C].Nashville:ICML Press,1997.97:187-194.
[23] Fossati D,Di Eugenio B.I saw TREE trees in the park:How to CorrectReal-Word Spelling Mistakes[A].LREC[C].Marrakech:LREC Press,2008.
[24] Gupta S,Sharma S.A Spelling Mistake Correction (SMC) Model for Resolving Real-Word Error[M].Computational Intelligence in Data Mining-Volume 1.Springer,New Delhi,2016.429-438.
[25] Viterbi A.Error bounds for convolutional codes and an asymptotically optimum decoding algorithm[J].IEEE transactions on Information Theory,1967,13(2):260-269.
[26] Forney G D.The viterbi algorithm[J].Proceedings of the IEEE,1973,61(3):268-278.
[27] Humboldt W.On Language:The Diversity of Human Language-Structure and Its Influence on the Mental Development of Mankind[M].Cambridge:Cambridge University Press,1988.

基于语义的汉语普通话电子喉语音转换增强

Voice Conversion for Enhancing Mandarin Electro-Laryngeal Speech Based on Semantic Information

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 2

编辑推荐

Metrics

[1]	车滢霞, 俞一彪. 约束条件下的结构化高斯混合模型及非平行语料语音转换[J]. 电子学报, 2016, 44(9): 2282-2288.
[2]	徐宁;杨震;张玲华. 基于状态空间模型的子频带语音转换算法[J]. 电子学报, 2010, 38(3): 646-653.