/enri-thumbnails/careeropportunities1f0caf1c-a12d-479c-be7c-3c04e085c617.tmb-mega-menu.jpg?Culture=en&sfvrsn=d7261e3b_1)
/cradle-thumbnails/research-capabilities1516d0ba63aa44f0b4ee77a8c05263b2.tmb-mega-menu.jpg?Culture=en&sfvrsn=1bc94f8_1)
7e6fdc03-9018-4d08-9a98-8a21acbc37ba.tmb-mega-menu.jpg?Culture=en&sfvrsn=7deaf618_1)
Customised Singlish Speech-to-Text Engine
Synopsis
The customisable Singlish Speech-to-Text (STT) engine scalable via Kubernetes, an open-source container orchestration system for automating software deployment, scaling, and management, targets a growing USD31.82 billion market. The speech-to-text engine offers cloud/on-premises deployment, rapid customisation for varied domains and continuous updates. Ideal for chatbots, virtual assistants and beyond, it enhances performance and accuracy in diverse industries.
Opportunity
The global speech and voice recognition market size is estimated to reach USD 31.82 billion, with a growth rate of CAGR of 17.2%, by 2025, according to Grand View Research, Inc. Artificial intelligence (AI), virtual reality (VR) and augmented reality (AR) solutions are anticipated to make significant contributions, particularly in continuously evolving challenges including infectious disease outbreaks.
We have devised a customisable AI-powered audio-to-text transcription engine deployable on both cloud and on-premises. We have a team of speech researchers equipped with the know-how to rapidly customise, maintain and update speech-to-text (STT) engines. Our aim is to enhance the performance of STT engines to meet industrial-grade standards and to continually advance and maintain state-of-the-art capabilities.
Technology companies relying on STT applications such as chatbots, virtual assistants, 1-1 interviews, and call centre auto-archiving systems demand highly accurate STT solutions to build superior products. Our service offers ongoing maintenance and customisation of the engine, available through an annual licensing renewal model, ensuring consistent performance and adaptability to evolving needs.
Technology
The innovative aspect of this technology lies in its localisation of STT capabilities for Singlish and local Mandarin. Additionally, it offers customisation and ongoing maintenance services for the engine. Our STT engine is versatile, deployable on both cloud and on-premise platforms. While state-of-the-art solutions provide robust ‘vanilla’ engines, they often fall short in achieving desired accuracies across various domains.
Figure 1: Speech recognition system using high availability and scalability kubernetes cluster.
Applications & Advantages
Applications:
- Workplace: Voice-activated virtual assistants for scheduling video conferences and transcribing meetings, enhancing productivity.
- Banking: Voice-activated banking reduces human customer service needs, cutting employee costs, while personalised assistants improve customer satisfaction.
- Marketing: Voice profiles for demographic inference, aiding targeted marketing; utilisation of speech archives for data analytics.
- Healthcare: Customised STT for telemedicine, transcribing consultations into doctor's notes, facilitating remote healthcare.
Advantages:
- Customisable STT for enhanced performance in any domain, with continual updates and support.
- Rapid localisation and customisation for industrial-level accuracy.
- Unique selling proposition: Rapid customisation and localisation by our expert team for individual use cases.
