A neural network based post-filter for speech-driven head motion synthesis
Despite the fact that neural networks are widely used for speech-driven head motion synthesis, it is well-known that the output of neural networks is noisy or discontinuous due to the limited capability of deep neural networks in predicting human motion. Thus, post-processing is required to obtain s...
Saved in:
Published in | arXiv.org |
---|---|
Main Authors | , |
Format | Paper |
Language | English |
Published |
Ithaca
Cornell University Library, arXiv.org
25.07.2019
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Despite the fact that neural networks are widely used for speech-driven head motion synthesis, it is well-known that the output of neural networks is noisy or discontinuous due to the limited capability of deep neural networks in predicting human motion. Thus, post-processing is required to obtain smooth head motion trajectories for animation. It is common to apply a linear filter or consider keyframes as post-processing. However, neither approach is optimal as there is always a trade-off between smoothness and accuracy. We propose to employ a neural network trained in a way that it is capable of reconstructing the head motions, in order to overcome this limitation. In the objective evaluation, this filter is proved to be good at de-noising data involving types of noise (dropout or Gaussian noise). Objective metrics also demonstrate the improvement of the joined head motion's smoothness after being processed by our proposed filter. A detailed analysis reveals that our proposed filter learns the characteristic of head motions. The subjective evaluation shows that participants were unable to distinguish the synthesised head motions with our proposed filter from ground truth, which was preferred over the Gaussian filter and moving average. |
---|---|
AbstractList | Despite the fact that neural networks are widely used for speech-driven head motion synthesis, it is well-known that the output of neural networks is noisy or discontinuous due to the limited capability of deep neural networks in predicting human motion. Thus, post-processing is required to obtain smooth head motion trajectories for animation. It is common to apply a linear filter or consider keyframes as post-processing. However, neither approach is optimal as there is always a trade-off between smoothness and accuracy. We propose to employ a neural network trained in a way that it is capable of reconstructing the head motions, in order to overcome this limitation. In the objective evaluation, this filter is proved to be good at de-noising data involving types of noise (dropout or Gaussian noise). Objective metrics also demonstrate the improvement of the joined head motion's smoothness after being processed by our proposed filter. A detailed analysis reveals that our proposed filter learns the characteristic of head motions. The subjective evaluation shows that participants were unable to distinguish the synthesised head motions with our proposed filter from ground truth, which was preferred over the Gaussian filter and moving average. |
Author | Shimodaira, Hiroshi Lu, JinHong |
Author_xml | – sequence: 1 givenname: JinHong surname: Lu fullname: Lu, JinHong – sequence: 2 givenname: Hiroshi surname: Shimodaira fullname: Shimodaira, Hiroshi |
BookMark | eNqNyrEKwjAUQNEgClbtPzxwDsQkrV1FFHF2L9G-0tSa1LxU8e_t4Ac4neHeBZs673DCEqnUhhdayjlLiVohhMy3MstUws47cDgE043Etw93uBrCCnpPkde2ixig9gGoR7w1vAr2hQ4aNBU8fLTeAX1cbJAsrdisNh1h-nPJ1sfDZX_iffDPASmWrR-CG1MpZa4zUWy0Vv9dXzuEPsU |
ContentType | Paper |
Copyright | 2019. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
Copyright_xml | – notice: 2019. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
DBID | 8FE 8FG ABJCF ABUWG AFKRA AZQEC BENPR BGLVJ CCPQU DWQXO HCIFZ L6V M7S PIMPY PQEST PQQKQ PQUKI PRINS PTHSS |
DatabaseName | ProQuest SciTech Collection ProQuest Technology Collection Materials Science & Engineering Collection ProQuest Central (Alumni) ProQuest Central ProQuest Central Essentials ProQuest Central Technology Collection ProQuest One Community College ProQuest Central Korea SciTech Premium Collection ProQuest Engineering Collection Engineering Database Publicly Available Content Database ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic ProQuest One Academic UKI Edition ProQuest Central China Engineering Collection |
DatabaseTitle | Publicly Available Content Database Engineering Database Technology Collection ProQuest Central Essentials ProQuest One Academic Eastern Edition ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest Technology Collection ProQuest SciTech Collection ProQuest Central China ProQuest Central ProQuest Engineering Collection ProQuest One Academic UKI Edition ProQuest Central Korea Materials Science & Engineering Collection ProQuest One Academic Engineering Collection |
DatabaseTitleList | Publicly Available Content Database |
Database_xml | – sequence: 1 dbid: 8FG name: ProQuest Technology Collection url: https://search.proquest.com/technologycollection1 sourceTypes: Aggregation Database |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Physics |
EISSN | 2331-8422 |
Genre | Working Paper/Pre-Print |
GroupedDBID | 8FE 8FG ABJCF ABUWG AFKRA ALMA_UNASSIGNED_HOLDINGS AZQEC BENPR BGLVJ CCPQU DWQXO FRJ HCIFZ L6V M7S M~E PIMPY PQEST PQQKQ PQUKI PRINS PTHSS |
ID | FETCH-proquest_journals_22645081443 |
IEDL.DBID | 8FG |
IngestDate | Tue Sep 24 23:11:06 EDT 2024 |
IsOpenAccess | true |
IsPeerReviewed | false |
IsScholarly | false |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-proquest_journals_22645081443 |
OpenAccessLink | https://www.proquest.com/docview/2264508144/abstract/?pq-origsite=%requestingapplication% |
PQID | 2264508144 |
PQPubID | 2050157 |
ParticipantIDs | proquest_journals_2264508144 |
PublicationCentury | 2000 |
PublicationDate | 20190725 |
PublicationDateYYYYMMDD | 2019-07-25 |
PublicationDate_xml | – month: 07 year: 2019 text: 20190725 day: 25 |
PublicationDecade | 2010 |
PublicationPlace | Ithaca |
PublicationPlace_xml | – name: Ithaca |
PublicationTitle | arXiv.org |
PublicationYear | 2019 |
Publisher | Cornell University Library, arXiv.org |
Publisher_xml | – name: Cornell University Library, arXiv.org |
SSID | ssj0002672553 |
Score | 3.223464 |
SecondaryResourceType | preprint |
Snippet | Despite the fact that neural networks are widely used for speech-driven head motion synthesis, it is well-known that the output of neural networks is noisy or... |
SourceID | proquest |
SourceType | Aggregation Database |
SubjectTerms | Animation Ground truth Head movement Human motion Linear filters Neural networks Post-processing Random noise Smoothness Synthesis |
Title | A neural network based post-filter for speech-driven head motion synthesis |
URI | https://www.proquest.com/docview/2264508144/abstract/ |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1LS8NAEB5qg-DNJz5qWdDrkppuXidRSQyFliIKvZXso1iQNmbjwYu_3Zm10YPQ0xIWQnZJvu_L7HwzANfUo2ggDH7fpYq5CHTEZZwmXBuFBK9TmTgf93gSFS9iNAtnHShaLwylVbaY6IBarxXFyH0yfKKYQP3vl5KiAKrxb6t3Tv2j6Jx100xjB7wbqolHnvH88TfaEkQxaufhP8B1LJLvgzctK1MfQMesDmHXJV8qewSjO0ZlJcs3HFxSNiNu0axa24YvlnSezVBbMlsZo165rgmhGKKoZj9NeJj9XKGQs0t7DFd59vxQ8PYB5puXxc7_ljY8gS7-9ZtTYEgcIpGLQKiBRKJJEh2JkirdRCmCW6jOoLftTufbpy9gD5mf7Es8CHvQbeoPc4ns2si-27g-ePfZZPqEV-Ov7Bs8PYUi |
link.rule.ids | 786,790,12792,21416,33408,33779,43635,43840 |
linkProvider | ProQuest |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3PS8MwFH5oi-jNn_hjakCvwdGmaXsSlY06tzJkwm6lTTIcjK029eB_73u104OwUw6BkITk-7738l4ewC3VKOoKg_c7VyEXnpa8COOIa6OQ4HVcRE0e9yiVyZsYTINp63CzbVjlGhMboNYrRT7yO0r4RDGB-v--_OBUNYpeV9sSGtvgCh9NFQfcx146fv31sngyRM3s_wPahj36--CO89JUB7Blloew0wRdKnsEgwdG30nmC2yaYGxGnKJZubI1n83pHZuhpmS2NEa9c10RMjFET81-iu8w-7VEAWfn9hhu-r3JU8LXE8jaQ2KzvyX5J-CgtW9OgSFhiKiYeUJ1CySYKNJS5PTDjYwR1AJ1Bp1NI51v7r6G3WQyGmbD5_TlAvaQ_SmFiXtBB5y6-jSXyLB1cdVu4zcW1ILr |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=A+neural+network+based+post-filter+for+speech-driven+head+motion+synthesis&rft.jtitle=arXiv.org&rft.au=Lu%2C+JinHong&rft.au=Shimodaira%2C+Hiroshi&rft.date=2019-07-25&rft.pub=Cornell+University+Library%2C+arXiv.org&rft.eissn=2331-8422 |