Speech Recognition

In computer science and information technology, Speech Recognition is the act of receiving a speaker's voice as audio input within a specific program, and subsequently rendering that input into a machine understandable format within a given software program, system or platform.

Speech Recognition can be best characterized as "knowing or deducing what the speaker has said".

Specs

• Web Speech API Specification: http://dvcs.w3.org/hg/speech-api/raw-file/tip/speechapi.html
• JSpeech Grammar Format (JSGF): https://www.w3.org/TR/jsgf/

Web Speech API

• Web Speech API demo: https://www.google.com/intl/en/chrome/demos/speech.html

Common Voice

• Mozilla - Common Voice: https://commonvoice.mozilla.org/en (initiative to help teach machines how real people speak)

Tools

• Rev.AI -- accurate Speech Recognition: https://www.rev.ai/
• Microsoft Speech API: http://msdn.microsoft.com/en-us/library/jj127860.aspx
• wikipedia: Microsoft Speech API
• Bing - Speech Search, Synthesis & Commands (for Windows8 / WindowsPhone users): http://www.bing.com/dev/en-us/speech
• Speech Recognition in Google "simulator": https://console.actions.google.com/project/speechrecognition-37401/simulator/
• Chrome extensions -- Speech Recognition Anywhere: https://chrome.google.com/webstore/detail/speech-recognition-anywhe/kdnnmhpmcakdilnofmllgcigkibjonof
• iSpeech: http://ispeech.org | iSpeech API Specification Version 2.0
• Speex - A Free Codec For Free Speech: http://www.speex.org/
• Asterisk is an open-source VoIP platform/server which can be used for call-in IVR or Speech Recognition by Phone: http://www.asterisk.org/downloads
• Nuance features the largest vocabulary (500,000+ words): http://www.nuance.com/mobilesearch/
• IBM ViaVoice seems easy to use and efficient (2007 award): http://www-306.ibm.com/software/pervasive/embedded_viavoice/
• Lumenvox is cheap to do tests and trials on (just $50 US for 500-word test engine): http://www.lumenvox.com/ (Voice Recognition & Speech-to-Text both)
• GotVoice - Mobile VoiceMail and Speech-to-Text: http://www.gotvoice.com
• Advanced Media - Japanese company with AmiVoice software, specially targeted for Mobile Phones: http://www.advanced-media.co.jp/ [1]
• 3M SyncStream: http://solutions.3m.com.au/wps/portal/3M/en_AU/HIS_AU/home/products-services/dictation-transcription/syncstream/
• FirstDraft: http://firstdraft.infraware.com/
• VoxReports: http://www.atirix.com/VoxReports.aspx
• SpeechQ (for Radiology): http://mmodal.com/products/speechq/
• MediSpeech: http://www.g2speech.com/solutions/medispeech.html

Nuance

• Nuance: http://www.nuance.con | Dragon NaturallySpeaking | DOWNLOAD | API
• wikipedia: Dragon NaturallySpeaking
• Nuance - Audio input device (compatibility checker): http://support.nuance.com/compatibility/
• Vansonic HS-GEN-C analog headset/microphone (with adaptor): http://www.ybsales.com/Nuance-HS-GEN-C-Dragon-Stereo-Communication-Headset.html

Resources

• Mozilla dev docs -- SpeechRecognition API: https://developer.mozilla.org/en-US/docs/Web/API/SpeechRecognition (Chrome support only so far)
• Sphinx: https://cmusphinx.github.io/ | SAMPLES (Java-based OSS Speech Recognition toolkit)
• J.A.R.V.I.S. (Java-Speech-API): https://github.com/lkuza2/java-speech-api
• Java Speech API (JSR 113) implementation: https://sourceforge.net/projects/jsapi/
• Java Speech API - Frequently Asked Questions: https://www.oracle.com/technetwork/java/jsapifaq-135248.html#implementation
• Windows Speech Recognition commands: https://support.microsoft.com/en-us/help/12427/windows-speech-recognition-commands
• SpeechAPI: http://www.speechapi.com/
• Bing Speech API: https://www.microsoft.com/cognitive-services/en-us/speech-api
• Nuance Dragon API: http://dragonmobile.nuancemobiledeveloper.com
• Web-Accessible Multimodal Internet Applications (WAMI): http://wami.csail.mit.edu (Speech/Voice for Flash)
• Microphone activity (FLASH): http://livedocs.adobe.com/flash/9.0/main/wwhelp/wwhimpl/common/html/wwhelp.htm?context=LiveDocs_Parts&file=00001864.html
• 10 Types of Microphones: http://electronics.howstuffworks.com/gadgets/audio-music/question309.htm
• Speech-enabled Mobile Web Apps via Nuance's new Dragon Speech Recognition API: http://dragonmobile.nuancemobiledeveloper.com/phpbb/viewtopic.php?f=21&t=416&p=1771#p1771
• wami -- A Java-script API for speech recognition: https://code.google.com/p/wami/
• The SUMO Heavy 2019 Voice Commerce Survey: https://www.sumoheavy.com/the-sumo-heavy-2019-voice-commerce-survey/

Tutorials

• Java-Speech-Recognizer-Tutorial: https://github.com/goxr3plus/Java-Speech-Recognizer-Tutorial--Calculator | VIDEO #1 to VIDEO #5
• Basics of Java Speech Grammar Format (JSGF): https://puneetk.com/basics-of-java-speech-grammar-format-jsgf
• Building a language model: https://cmusphinx.github.io/wiki/tutoriallm/
• Use the Java Speech API (JSPAPI): https://www.rgagnon.com/javadetails/java-use-java-speech-api.html
• JSAPI 1.0 Setup using FreeTTS: https://freetts.sourceforge.io/docs/jsapi_setup.html
• FreeTTS Programmer's Guide: https://freetts.sourceforge.io/docs/ProgrammerGuide.html
• Speech Recognition -- javax.speech.recognition: http://www.ling.helsinki.fi/kit/2004s/ctl310gen/L7-Speech/JSAPI/Recognition.html

• Java Sound API -- Soundbanks: https://www.oracle.com/technetwork/java/soundbanks-135798.html
• Merapi AIR/Java Speech Recognition and Voice Control: http://javadz.wordpress.com/2009/06/14/42/
• HOW TO - Developing Dragon NaturallySpeaking applications that recognize speech: http://www.chant.net/support/knowledgebase/howtos/h071128.aspx
• How to Add Voice Interactivity to Your Site: http://dev.opera.com/articles/view/add-voice-interactivity-to-your-site/ (Works only with WindowsXP)
• How To Use Speech Recognition in Windows XP: http://support.microsoft.com/kb/306901
• How Electret Energy Harvester (and Microphones) Work: http://tikalon.com/blog/blog.php?article=2011/electret
• Speaking in Context - Designing Voice Interfaces: http://punchcut.com/perspectives/speaking-context-designing-voice-interfaces
• Chunked Transfer-Encoding in PHP With Guzzle: http://mtdowling.com/blog/2012/01/27/chunked-encoding-in-php-with-guzzle/
• How to backup and restore a Dragon User Profile: https://nuance.custhelp.com/app/answers/detail/a_id/15129/~/how-to-backup-and-restore-a-dragon-user-profile
• Dragon Backup location: http://www.pcspeak.com/hints/general/backup.shtml
• Setting Speech Recognition & Text-To-Speech settings in Windows 7: Setting speech options: http://windows.microsoft.com/en-us/windows/setting-speech-options#1TC=windows-7
• Making the Most of Cortana in Windows 10: http://www.dummies.com/how-to/content/making-the-most-of-cortana-in-windows-10.html
• Microsoft Retooling Cortana For Mobile Users: https://www.mediapost.com/publications/article/323613/microsoft-retooling-cortana-for-mobile-users.html
• Ask a UXpert -- Adobe XD - How to Prototype Voice Experiences that Delight Users: https://theblog.adobe.com/how-to-voice-ui-prototyping-delight-users/

• JavaScript Speech Recognition: https://davidwalsh.name/speech-recognition

External Links

• wikipedia: Speech Recognition
• wikipedia: Voice user interface (VUI)
• wikipedia: Telematics
• wikipedia: Chunked transfer encoding
• Deconstructing Google Mobile's Voice Search on the iPhone: http://waxy.org/2008/11/deconstructing_google_mobiles_voice_search_on_the_iphone
• Cheap, Easy Human-powered Audio Transcription with Amazon's Mechanical Turk: http://waxy.org/2008/09/audio_transcription_with_mechanical_turk/
• Japanese SINGER, SONG WRITER... voice recognition, shaping and correction [2]
• HSTP: Hyperspeech Transfer Protocol: http://www.readwriteweb.com/archives/hstp_hyperspeech_transfer_protocol.php
• Speech Recognition for a Digital Video Library: http://www.informedia.cs.cmu.edu/documents/jasis96.pdf
• How to install and configure speech recognition in Windows XP: http://support.microsoft.com/kb/306537
• Siri creates legal woe for Apple: http://www.washingtonpost.com/business/technology/siri-creates-legal-woe-for-apple/2012/03/13/gIQAg8U59R_story.html?tid=pm_pop
• NTT Docomo, Japan’s biggest mobile carrier announces Siri competitor, ‘Shabette Concier’: http://www.zdnet.com/blog/asia/japans-biggest-mobile-carrier-announces-siri-competitor-8216shabette-concier/1188
• Speech Recognition AS3 Preview 2: http://vimeo.com/14025090
• Medical transcription and speech Recognition: http://www.ideamarketers.com/?articleid=2571684
• Medical Speech Recognition Software Streamlines Workflow: http://ezinearticles.com/?Medical-Speech-Recognition-Software-Streamlines-Workflow&id=3740865
• Doctors Use Speech Recognition Tools To Enhance Patient E-Health Records: http://www.informationweek.com/software/productivity-applications/doctors-use-speech-recognition-tools-to/207800986
• The Disadvantages of Medical Speech Recognition: http://www.ehow.com/info_8548829_disadvantages-medical-speech-recognition.html
• Unilever Is Right -- Voice Is The New Mobile: https://www.mediapost.com/publications/article/308502/unilever-is-right-voice-is-the-new-mobile.html
• How voice technology is transforming computing: https://www.economist.com/news/leaders/21713836-casting-magic-spell-it-lets-people-control-world-through-words-alone-how-voice
• Google Launching Amazon Echo Competitor Without Nest: https://www.mediapost.com/publications/article/276789/google-launching-amazon-echo-competitor-without-ne.html
• Making audio searchable with Cloud Speech: https://hackernoon.com/making-audio-searchable-with-cloud-speech-
• Smart Speaker Sales Projected To Grow 50% By 2019: https://www.mediapost.com/publications/article/323608/smart-speaker-sales-projected-to-grow-50-by-2019.html
• Speech Recognition Finally On The Map: https://www.mediapost.com/publications/article/323607/speech-recognition-finally-on-the-map.html
• 52% Of Consumers Worry About Passive Listening By Their Voice Assistants: https://www.mediapost.com/publications/article/340889/52-of-consumers-worry-about-passive-listening-by.html
• Google To Refine Privacy Settings For Voice Assistant: https://www.mediapost.com/publications/article/341077/google-to-refine-privacy-settings-for-voice-assist.html
• Doing more to protect your privacy with the Assistant: https://www.blog.google/products/assistant/doing-more-protect-your-privacy-assistant/
• The Year Ahead -- The Rise Of Voice-Enabled News, Media Consolidation And More Partnerships: https://www.mediapost.com/publications/article/345159/the-year-ahead-the-rise-of-voice-enabled-news-me.html
• COVID-19 may push retailers to use voice assistants instead of touch screens: https://retailwire.com/discussion/covid-19-may-push-retailers-to-use-voice-assistants-instead-of-touch-screens/
• Australian researchers collect children’s voice biometrics to help with speech impairments: https://www.biometricupdate.com/202101/australian-researchers-collect-childrens-voice-biometrics-to-help-with-speech-impairments
• How to Delete Google Assistant Recordings: https://www.howtogeek.com/713484/how-to-delete-google-assistant-recordings/
• Changelog Podcast -- 25 years of speech technology innovation: https://changelog.com/practicalai/133

See Also

Voice Recognition | STT | HCI | Nuance | Apple | Amazon | Google | Microsoft | A11Y