SoapBox Labs is a developer of a speech technology software intended for language learning and development. SoapBox Labs has developed child-specific speech technology that creates accurate, age-appropriate and safe voice-enabled experiences for children. SoapBox Labs' technology and their API is licensed and integrated across a range of application areas including toys, gaming, robotics, augmented and virtual reality, and Education (reading and English Language Learning). SoapBox Labs develops their voice technology products for 2 to 12 year old children.
The company's products offer full transparency with respect to the processing and storage of all voice data, with explicit parental consent and in full compliance with US COPPA and EU GDPR legislation, enabling users to access the most accurate, safe and accessible kids' speech recognition technology.SoapBox Labs's estimated revenue is $2 million.
SoapBox Labs voice engine has been built for children from 2 to 12 year old children. The voice engine is intended to work with children's unpredictable speech patterns and behaviors with accuracy across accents and dialects. The company also says their voice engine works in the noisy environments that kids tend to inhabit. The voice engine, developed with natural language processing, natural language understanding, language models, and acoustic models, is intended to be capable of recognizing:
- Voice Search
- Speech to text transcription
- Voice activity detection
- Conversation and dialogue
- Voice control
- Comprehension questions
- Keyword spotting
- Fluency assessment
- Reading practice
- Pronunciation assessment
- Multiple choice questions
The company's voice technology's earliest use case was for language learning. The tools allow kids to speak out loud, get feedback on their speech, and improve language fluency through conversation.
SoapBox Labs voice engine is capable of helping teachers and educators with fluency and language assessments through voice-enable reading assessments. This integration is through the SoapBox Fluency product and is integrated through the company's partnership with Amplify.
Toys & Entertainment
SoapBox Labs integration into toys and entertainment products offer children voice-enabled controls with age-appropriate internet searches and chats with toys. The integration is capable of being online and can be contained in offline experiences.
Developed by SoapBox Labs, SoapBox Fluency offers teachers a voice-enabled alternative to the manual assessment of fluency for K-5 children. The technology works through the integration of voice technology into existing formative and summative assessments, which give educators and parents to receive immediate and longitudinal feedback on a child's progress.
SoapBox Fluency and the automated speech recognition technology behind it have been challenged by longer reading passages and stories. The strength of the technology is in words and short sentences in the assessment of fluency. But the technology focuses on children's voice and speech behaviors for the assessment, and works to handle the acoustic and behavioral differences in children's speech when performing reading tasks.
SoapBox Labs' client focused product, SoapBox Studio, uses their natural language processing and voice technology to develop bespoke services for clients in areas including:
- Voice UI/UX
- Prototype development
- Data privacy and compliance
- Acoustic modelling
- Custom language domains
- Custom offline implementations
- Natural language processing
- Data analytics
- Custom client libraries
- Integration and maintenance support services
Patricia Scanlon founded SoapBox Labs in 2013 when they began working on the problem of speech recognition technology and children. Most speech recognition technology found in devices such as the Amazon Echo or Google Home, do not work well with kids. This is in part due to children having higher pitched voices and different speech patterns. As well, children, unlike adults, do not adapt their speech to suit machines in order to improve the utility of voice-enabled user interfaces and smart assistants. These challenges, along with Scanlon's experience with voice-enabled interfaces and her daughter's interaction with them, led to the creation of SoapBox Labs.
The work to solving the challenges and developing voice-enabled technology for children involved focusing on the differences between adult speech patterns and a child's speech patterns. This includes the tendency of children to not enunciate words properly, their tendency to pause, or become distracted while speaking. SoapBox Labs voice recognition technology is developed with intention of understanding these challenges and understand a child's speech pattern.
In June of 2020, Patricia Scanlon partook in SXSW EDU virtual panel discussion for the education, education technology, and voice technology industries.
- SoapBox Labs' Fluency is short-listed for the Reimagine Education Awards & Conference 2020 awards under the learning assessment category.
- SoapBox Labs is awarded the Best Use of AI in a Sector award from the AI Ireland Awards for the use of their voice technology in the PreK-12 education area.
- Voicebot.ai names SoapBox Labs' founder and CEO Patricia Scanlon a Visionary in Voice.
Introducing SoapBox Labs
July 24, 2020
Irish startup SoapBox Labs is building speech recognition tech for kids
January 13, 2018
Patricia Scanlon, Founder and CEO of SoapBox Labs
November 13, 2019
Smart Review: Better Voice Recognition with SoapBox Labs | Getting Smart
Rachelle Dene Poth
May 16, 2020
SoapBox Labs and Microsoft Announce Partnership to Tackle Childhood Literacy - UK Business Angels Association
March 20, 2019
- Speech recognitionSpeech Recognition is a technology that allows users of information systems to speak entries rather than punching numbers on a keypad.
- CompanyA company, abbreviated as "Co." within a company name, is a legal entity made up of an association of people, be they natural, legal, or a mixture of both, for carrying on a commercial or industrial enterprise.
- Natural language processing (NLP)Natural language processing is a branch of artificial intelligence that is concerned with giving computers the ability to comprehend spoken words and text in the same way humans can.