Ultrasound-based Silent Speech Interface Built on a Continuous Vocoder

被引:8
|
作者
Csapo, Tamas Gabor [1 ,2 ]
Al-Radhi, Mohammed Salah [1 ]
Nemeth, Geza [1 ]
Gosztolya, Gabor [3 ,4 ]
Grosz, Tamas [4 ]
Toth, Laszlo [4 ]
Marko, Alexandra [2 ,5 ]
机构
[1] Budapest Univ Technol & Econ, Dept Telecommun & Media Informat, Budapest, Hungary
[2] MTA ELTE Lendulet Lingual Articulat Res Grp, Budapest, Hungary
[3] MTA SZTE Res Grp Artificial Intelligence, Szeged, Hungary
[4] Univ Szeged, Inst Informat, Szeged, Hungary
[5] Eotvos Lorand Univ, Dept Phonet, Budapest, Hungary
来源
关键词
Silent speech interface; articulatory-to-acoustic mapping; F0; prediction; CNN; HMM;
D O I
10.21437/Interspeech.2019-2046
中图分类号
R36 [病理学]; R76 [耳鼻咽喉科学];
学科分类号
100104 ; 100213 ;
摘要
Recently it was shown that within the Silent Speech Interface (SSI) field, the prediction of F0 is possible from Ultrasound Tongue Images (UTI) as the articulatory input, using Deep Neural Networks for articulatory-to-acoustic mapping. Moreover, text-to-speech synthesizers were shown to produce higher quality speech when using a continuous pitch estimate, which takes non-zero pitch values even when voicing is not present. Therefore, in this paper on UTI-based SSI, we use a simple continuous F0 tracker which does not apply a strict voiced / unvoiced decision. Continuous vocoder parameters (ContF0, Maximum Voiced Frequency and Mel-Generalized Cepstrum) are predicted using a convolutional neural network, with UTI as input. The results demonstrate that during the articulatory-to-acoustic mapping experiments, the continuous F0 is predicted with lower error, and the continuous vocoder produces slightly more natural synthesized speech than the baseline vocoder using standard discontinuous F0.
引用
收藏
页码:894 / 898
页数:5
相关论文
共 50 条
  • [41] Silent Speech Eyewear Interface: Silent Speech Recognition Method using Eyewear with Infrared Distance Sensors
    Yuya, Igarashi
    Kyosuke, Futami
    Kazuya, Murao
    [J]. PROCEEDINGS OF THE 2022 ACM INTERNATIONAL SYMPOSIUM ON WEARABLE COMPUTERS, ISWC 2022, 2022, : 33 - 38
  • [42] Silent Speech Eyewear Interface: Silent Speech Recognition Method using Eyewear with Infrared Distance Sensors
    Igarashi, Yuya
    Futami, Kyosuke
    Murao, Kazuya
    [J]. Proceedings - International Symposium on Wearable Computers, ISWC, 2022, : 33 - 38
  • [43] ULTRASOUND-BASED ASSEMBLY OF TISSUES AND BIOMATERIALS
    Armstrong, James
    [J]. TISSUE ENGINEERING PART A, 2023, 29 (11-12) : 301 - 301
  • [44] An Ultrasound-Based Biomedical System for Continuous Cardiopulmonary Monitoring: A Single Sensor for Multiple Information
    Shahshahani, Amirhossein
    Zilic, Zeljko
    Bhadra, Sharmistha
    [J]. IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2020, 67 (01) : 268 - 276
  • [45] Ultrasound-Based Drug Delivery System
    Ren, Wei-Wei
    Xu, Shi-Hao
    Sun, Li-Ping
    Zhang, Kun
    [J]. CURRENT MEDICINAL CHEMISTRY, 2022, 29 (08) : 1342 - 1351
  • [46] Ultrasound-based servoing of manipulators for telesurgery
    Stoll, J
    Dupont, P
    Howe, R
    [J]. TELEMANIPULATOR AND TELEPRESENCE TECHNOLOGIES VIII, 2002, 4570 : 78 - 85
  • [47] Recognition of phonemes in a continuous speech stream by means of PARCOR parameter in LPC vocoder
    Cui, Ying
    Takaya, Kunio
    [J]. 2007 CANADIAN CONFERENCE ON ELECTRICAL AND COMPUTER ENGINEERING, VOLS 1-3, 2007, : 1606 - 1609
  • [48] SonoWand, an ultrasound-based neuronavigation system
    Gronningsaeter, A
    Kleven, A
    Ommedal, S
    Aarseth, TE
    Lie, T
    Lindseth, F
    Lango, T
    Unsgard, G
    [J]. NEUROSURGERY, 2000, 47 (06) : 1373 - 1379
  • [49] Artifacts in ultrasound-based image guidance
    OBrien, P.
    Szpala, S.
    Morton, G.
    Tirona, R.
    [J]. RADIOTHERAPY AND ONCOLOGY, 2007, 84 : S204 - S204
  • [50] Silent Speech Interface Using Ultrasonic Doppler Sonar
    Lee, Ki-Seung
    [J]. IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2020, E103D (08): : 1875 - 1887