Difference between revisions of "Speech Technologies"

From HCE Wiki - The Human Cognitive Enhancement Wiki
Jump to navigation Jump to search
(a correction)
(Enhancement/Therapy/Treatment)
Line 46: Line 46:
 
Customers' review suggest that [[Intelligent Personal Assistants|intelligent personal assistants]] could be helpful for elderly and disabled. The devices could make them more independent due to control of environment which they provide.<ref>Patrickometry. Alexa is a Revolution for my Disabled Family Member. Amazon [online]. 2015, Sep 6. Available online at: https://www.amazon.com/Amazon-SK705DI-Echo/product-reviews/B00X4WHP5E (Retrieved 21st December, 2016).</ref> Customers also claim that the devices could call the help when elderly or disabled person have an accident.<ref>Alex S. Already very practical for overcoming disability issues. Amazon [online]. 2015, Jun 19. Available online at: https://www.amazon.com/review/RTRDKUJDZCO4B/ref=cm_cr_dp_title?ie=UTF8&ASIN=B00X4WHP5E&channel=detail-glance&nodeID=9818047011&store=amazon-home&tag (Retrieved 21st December, 2016).</ref> Notwithstanding, this claim has not been supported by a research, yet.
 
Customers' review suggest that [[Intelligent Personal Assistants|intelligent personal assistants]] could be helpful for elderly and disabled. The devices could make them more independent due to control of environment which they provide.<ref>Patrickometry. Alexa is a Revolution for my Disabled Family Member. Amazon [online]. 2015, Sep 6. Available online at: https://www.amazon.com/Amazon-SK705DI-Echo/product-reviews/B00X4WHP5E (Retrieved 21st December, 2016).</ref> Customers also claim that the devices could call the help when elderly or disabled person have an accident.<ref>Alex S. Already very practical for overcoming disability issues. Amazon [online]. 2015, Jun 19. Available online at: https://www.amazon.com/review/RTRDKUJDZCO4B/ref=cm_cr_dp_title?ie=UTF8&ASIN=B00X4WHP5E&channel=detail-glance&nodeID=9818047011&store=amazon-home&tag (Retrieved 21st December, 2016).</ref> Notwithstanding, this claim has not been supported by a research, yet.
  
Speech synthesis is used in various applications and devices for the blind or vision impaired people. It enables them to read the content from the screen.<ref name="Designing High-Coverage"/>  
+
Speech synthesis is used in various applications and devices for the blind or vision impaired people. It enables them to read the content from the screen.<ref name="Designing High-Coverage"/> The speaking devices as toys or GPS also benefit from speech synthesis. It is also used in call centres where, it could handle with common tasks of customers.<ref name="taylor"/>
 
 
Voice products - toys, GPS, Call centres
 
  
 
Organisation
 
Organisation

Revision as of 13:46, 28 February 2017

Speech technologies are technologies or devices that can understand and/or produce human-like speech. The speech generation is useful in applications such as text-to-speech, electrolarynges, speech prostheses or intelligent personal assistants. The former three technologies are used as a medical devices for people, who lost their voice. Speech synthesizers are also incorporated into devices which helped visually disabled people. Intelligent Personal Assistants allow the users to use their devices hands-free by merely saying required commands, mostly in plain, natural speech.

The speech technologies deals with voice, which is the dominant tool of interpersonal communication.[1] The importance of the voice was acknowledged also by the fact that 16th April was chosen as World Voice Day.[2]

http://archive.is/YU9D

http://www.speechatsri.com/products/eduspeak.shtml

http://www.speechtechmag.com/Articles/Editorial/Cover-Story/The-2015-State-of-the-Speech-Technology-Industry-Speech-Engine-101922.aspx

Main characteristics

Speech technologies could be divided between technologies used in medicine and technologies for commercial use. While the former group is represented primarily by electrolarynges and speech prostheses, intelligent personal assistants belong to the latter category. Speech synthesis is used for both purposes. It is contained in intelligent personal assistants or GPS navigations, but also in systems for visually impaired and speech synthesizers for people who lost their voice.[3] These technologies appear in two forms. It could be devices, software or a combination of both.

Historical overview

The first speaking machines were developed in Antiquity and Middle Ages. Nonetheless, they were not genuine speaking machines since they depended on people speaking inside of them. The first genuine speaking machine was introduced by Hungarian civil servant and inventor Wolfgan von Kempelen. He described his speech synthesiser in a book "Mechanismus der menschlichen Sprache nebst der Beschreibung seiner sprechenden Maschin" [The Mechanism of Human Speech, with a Description of a Speaking Machine] published in 1791.[4]

In the 19th century, researchers focused also on the help people, who lost their voice or have serious problem with their throat. Jan Nepomuk Czermak described the first laryngeal prosthesis in 1859. His attempt was followed by the introduction of various speech prosthesis and artificial larynges.[5] Later on, an Austrian surgeon Theodore Billroth performed the successful total extirpation of the larynx.[6]

20th century was an important breakthrough in various fields of speech technologies. The speech synthesis started to be mechanized by the introduction of Voder in 1930.[7] New techniques of voice synthesis also made the synthetic voice sounding more natural and lately allow to preserve the voices of patients, who loosing their voice.[8] The first electrolarynges were introduced in 1942 by Wright.[5] Surprisingly, the first tracheoesophageal voice prosthesis was not developed by a professional, but it was conducted by a patient using a red hot ice pick in 1931. The surgeons was, however, unable to replicate this procedure.[9] Therefore, it was abandoned until Erwin Mozolewski presented his tracheoesophageal voice prosthesis.[10]

In the middle of 20th century, the first speech recognition system were introduced. The first system was "Audrey" which was able to recognised digits spoken by a single voice. It was followed by IBM's "Shoebox" presented at 1962 World's Fair. It was able to recognised 16 English words. Another important system for voice recognition was "Harpy", which was developed by U.S. Department of Defense between years 1971 and 1976. It could recognise 1011 words similarly as 3 years old child.[11] Apple presented the idea of intelligent personal assistant in 1987. It was entitled "Knowledge Navigator", but the advertised product have never been developed.[12] The first publicly available personal assistant was Siri introduced by Apple in 2010.[13] It was followed by the similar products of other companies asAlexa, Google Now, and Cortana.[14] Siri was a software, which was contained in iPhones. In 2014, Amazon.com presented first intelligent personal assistants' device Amazon Echo, which contains Alexa.[15] Its introduction also provoke the introduction of similar devices as Google Home, Apple HomeKit, Lenovo Smart Assistant, etc.[14]

Important Dates

  • 1769 - Wolfgang von Kempelen developed the first genuine speech synthesizer[16]
  • 1859 - the first pneumatic laryngeal prosthesis was introduced by Jan Nepomuk Czermak[5]
  • 1873 - Billroth conducted the first successful total laryngectomy[5]
  • 1931 - the first laryngeal puncture was conducted by a patient[17]
  • 1937 - the speech synthesizer Voder was unveiled[7]
  • 1942 - Wright developed the first electrolarynx "Sonovox"[18]
  • 1952 - Bell Laboratories presented "Audrey"[11]
  • 1972 - Erwin Mozolewski introduced a tracheoesophageal voice prosthesis[19]
  • 1976 - "Harpy" was developed[11]
  • 1987 - Apple Knowledge Navigator was presented[20]
  • 4th February 2010 - Siri Inc. unveiled Siri[13]
  • 6th November 2014 - Amazon.com, Inc introduced Amazon Echo[15]

Enhancement/Therapy/Treatment

http://www.pcadvisor.co.uk/feature/software/how-digital-assistants-are-replacing-our-brains-3530140/

The purpose of speech prostheses and electrolarynges is to return the ability to speak to patients who underwent total laryngectomy or lost their voice by any other way.[21] Certain speech synthesizers could be also used for this purpose, even though speech synthesis is used also in non-therapeutical applications.[3] Patients could also achieve oesophageal speech, but it is difficult to learn and certain patients are not able to communicate this way.[22] Each technique of voice restoration has its pros and cons. Electrolarynx's speech sound mechanical and depends on the mechanical device, but it is easy to achieve and it is used, when any other methods fails.[21] Speech prosthesis has to be installed during surgery, the prosthesis has to be removed periodically[23] and the pitch is considerably low for women,[24] but in comparison to electrolarynx it has a certain pitch control and better ineligibility.[23] Speech synthesis could preserve patient's voice, but it depends on the voice conservation, which could be challenging.[8]

Customers' review suggest that intelligent personal assistants could be helpful for elderly and disabled. The devices could make them more independent due to control of environment which they provide.[25] Customers also claim that the devices could call the help when elderly or disabled person have an accident.[26] Notwithstanding, this claim has not been supported by a research, yet.

Speech synthesis is used in various applications and devices for the blind or vision impaired people. It enables them to read the content from the screen.[8] The speaking devices as toys or GPS also benefit from speech synthesis. It is also used in call centres where, it could handle with common tasks of customers.[3]

Organisation

Provide information

Learning foreign language

Ethical & Health Issues

Quality of voice production

Efficiency

privacy and data collection

http://www.techadvisor.co.uk/opinion/internet/no-one-cares-about-privacy/

naturalness and human-like behaviour

copycats

Public & Media Impact and Presentation

Public Policy

Related Technologies, Projects or Scientific Research

http://www.speechtechmag.com/Articles/News/Speech-Technology-News-Features/IBM-Makes-Watson-TTS-More-Expressive--109477.aspx

http://link.springer.com/journal/10772

References

  1. LALWANI, Mona. Personal assistants are ushering in the age of AI at home. Engadget [online]. 2016, Oct 5. Available online at: https://www.engadget.com/2016/10/05/personal-assistants-google-home-ai/ (Retrieved 5th January, 2017).
  2. SIEGEL-ITZKOVICH, Judy. Voice of the people. The Jerusalem Post [online]. 2015, Apr 26. Available online at: http://www.jpost.com/Israel-News/Health/Voice-of-the-people-399185 (Retrieved 17th January, 2017).
  3. 3.0 3.1 3.2 TAYLOR, Paul. Text-to-Speech Synthes. University of Cambridge Department of Engineering [online]. 2014. Available online at: http://mi.eng.cam.ac.uk/~pat40/ttsbook_draft_2.pdf (Retrieved 2nd February, 2017).
  4. DUDLEY, Homer, TARNOCZY, T. H. The speaking machine of Wolfgang von Kempelen. Journal of the Acoustical Society of America 22, 151-166. Doi:10.1121/1.1906583. Available online at: http://pubman.mpdl.mpg.de/pubman/item/escidoc:2316415:3/component/escidoc:2316414/Dudley_1950_Speaking_machine.pdf (Retrieved 2nd February, 2017).
  5. 5.0 5.1 5.2 5.3 KEITH, Robert L., SHANKS, James, Laryngectomee Rehabilitation: Past and Present. In: Speech and Language: Advances in Basic research and Practice. New York: Academic Press, 1983. Available online at: https://books.google.cz/books?id=0C60BQAAQBAJ&pg=PA126&lpg=PA126&dq=Cooper-Rand+electrolarynx&source=bl&ots=or27eudDf2&sig=22heagC08Fpk57qGILvufHxwCyM&hl=cs&sa=X&ved=0ahUKEwi1--bt3r7RAhWGuxQKHbrFCC04ChDoAQgdMAE#v=onepage&q=Cooper-Rand%20electrolarynx&f=false (Retrieved 13th January, 2017).
  6. KAZI, R. A., et al. Christian Albert Theodor Billroth: Master of surgery. Journal of postgraduate medicine, 2004, 50.1: 82. Available online at: https://tspace.library.utoronto.ca/bitstream/1807/2074/1/jp04025.pdf (Retrieved 25th February, 2016).
  7. 7.0 7.1 DUNCAN. Klatt’s Last Tapes: A History of Speech Synthesisers. Communication Aids [online]. 2013, Aug 10. Available online at: http://communicationaids.info/history-speech-synthesisers (Retrieved 2nd February, 2017).
  8. 8.0 8.1 8.2 JŮZOVÁ, M., TIHELKA, D., MATOUŠEK, J. Designing High-Coverage Multi-level Text Corpus for Non-professional-voice Conservation. In: Speech and Computer. Volume 9811 of the series Lecture Notes in Computer Science. Cham: Springer, 2016, pp 207-215. Doi: 10.1007/978-3-319-43958-7_24 Available online at: http://link.springer.com/chapter/10.1007/978-3-319-43958-7_24 (Retrieved 16th February, 2017).
  9. BLOM, Eric D. Current Status of Voice Restoration Following Total Laryngectomy. Oncology [online]. 2000, Jun 1. Available online at: http://www.cancernetwork.com/head-neck-cancer/current-status-voice-restoration-following-total-laryngectomy (Retrieved 19th January, 2017).
  10. MOZOLEWSKI, Erwin S., et al. "Arytenoid vocal shunt in laryngectomized patients." The Laryngoscope 85.5 (1975): 853-861.
  11. 11.0 11.1 11.2 PINOLA, Melanie. Speech Recognition Through the Decades: How We Ended Up With Siri. PCWorld [online]. 2011, Nov 2. Available online at: http://www.pcworld.com/article/243060/speech_recognition_through_the_decades_how_we_ended_up_with_siri.html (Retrieved 28th February, 2017).
  12. DUBBERLY, Hugh. The Making of Knowledge Navigator. DDO [online]. 2007, Mar 30. Available online at: http://www.dubberly.com/articles/the-making-of-knowledge-navigator.html (Retrieved 5th January, 2017).
  13. 13.0 13.1 HARRISON, Natalie and BREWER, Teresa. Apple Launches iPhone 4S, iOS 5 & iCloud. Apple [online]. 2011. Oct 4. Available online at: http://www.apple.com/pr/library/2011/10/04Apple-Launches-iPhone-4S-iOS-5-iCloud.html (Retrieved 16th December, 2016).
  14. 14.0 14.1 POGUE, David. The Problem with Tech Copycats. Scientific American [online].315(5), p. 23-23. Available online at: http://ve5kj6kj8s.scholar.serialssolutions.com/?sid=google&auinit=D&aulast=Pogue&atitle=The+Problem+with+Tech+Copycats&id=doi:10.1038/scientificamerican1116-23&title=Scientific+American&volume=315&issue=5&date=2016&spage=23&issn=0036-8733 (Retrieved 19th December, 2016).
  15. 15.0 15.1 WELCH, Chris. Amazon just surprised everyone with a crazy speaker that talks to you. The Verge [online]. 2014, Nov 6. Available online at: http://www.theverge.com/2014/11/6/7167793/amazon-echo-speaker-announced (Retrieved 20th December, 2016).
  16. WOODFORD, Chris. Speech synthesizers. EXPLAINTHATSTUFF [online]. 2017, Jan 21. Available online at: http://www.explainthatstuff.com/how-speech-synthesis-works.html (Retrieved 16th February, 2017).
  17. BLOM, Eric D. Current Status of Voice Restoration Following Total Laryngectomy. Oncology [online]. 2000, Jun 1. Available online at: http://www.cancernetwork.com/head-neck-cancer/current-status-voice-restoration-following-total-laryngectomy (Retrieved 19th January, 2017).
  18. LIU, Hanjun, NG, Manwa L. Electrolarynx in voice rehabilitation. Auris Nasus Larynx, 2007, 34.3: 327-332.
  19. TARNOWSKA, Czesława. Wspomnienie o profesorze Erwinie Mozolewskim. Pomorski Uniwersytet Medyczny w Szczecinie [online]. Available online at: https://www.pum.edu.pl/__data/assets/file/0009/14868/Wspomnienie_o_profesorze_Erwin_7517.pdf (Retrieved 19th January, 2017).
  20. DigiBarn Computer Museum. The Knowledge Navigator concept piece by Apple Computer (1987). DigiBarn Computer Museum [online]. Available online at: http://www.digibarn.com/collections/movies/knowledge-navigator.html (Retrieved 5th January, 2017).
  21. 21.0 21.1 BROWN, Dale H. et al. Postlaryngectomy Voice Rehabilitation: State of the Art at the Millennium, World Journal of Surgery [online]. 2003, 14 May. DOI: 10.1007/s00268-003-7107-4 Available online at: http://link.springer.com/article/10.1007/s00268-003-7107-4 (Retrieved 16th January, 2017).
  22. GARDNER, Warren H., HARRIS, Harold E. Aids and Devices for Laryngectomees. Arch Otolaryngol 73(2) [online]. 1961: 145-152. Doi: 10.1001/archotol.1961.00740020151003 Available online at: http://jamanetwork.com/journals/jamaotolaryngology/article-abstract/1766151 (Retrieved 17th January, 2017).
  23. 23.0 23.1 SERRA, A. et al. Post-laryngectomy voice rehabilitation with voice prosthesis: 15 years experience of the ENT Clinic of University of Catania. ACTA otorhinolaryngologica italica [online]. 2015; 35(6): 412-419. Doi: 10.14639/0392-100X-680 Available online at: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4755057/ (Retrieved 23rd January, 2017).
  24. TEN HALLERS, E. J. O. et al. Difficulties in the fixation of prostheses for voice rehabilitation after laryngectomy. Acta Oto-Laryngologica [online]. 2009, Jul 8. Doi: 10.1080/00016480510031506 Available online at: http://www.tandfonline.com/doi/abs/10.1080/00016480510031506 (Retrieved 23rd January, 2017).
  25. Patrickometry. Alexa is a Revolution for my Disabled Family Member. Amazon [online]. 2015, Sep 6. Available online at: https://www.amazon.com/Amazon-SK705DI-Echo/product-reviews/B00X4WHP5E (Retrieved 21st December, 2016).
  26. Alex S. Already very practical for overcoming disability issues. Amazon [online]. 2015, Jun 19. Available online at: https://www.amazon.com/review/RTRDKUJDZCO4B/ref=cm_cr_dp_title?ie=UTF8&ASIN=B00X4WHP5E&channel=detail-glance&nodeID=9818047011&store=amazon-home&tag (Retrieved 21st December, 2016).