Compliance and Call Recording
Recent changes in legislation (MFiD II, Dodd-Frank etc.) require large amounts of calls to be recorded and analysable. Our on-premise solution can help you add value to your customers and support your compliance needs.
Automated Language Assessment
We have been developing ground-breaking technology that enables automatic spoken language assessment of non-native speakers. For this we extract >80 features and apply cutting-edge machine learning technology to grade a speaker’s ability relative
to CEFR levels (The Common European Framework of Reference for Languages).
Our core ASR is being used in a wide variety of use cases to make audio content discovery. This includes podcasts, video feedback or radio shows. We even have one company building a system to produce and manage radio content better.
Government and other public institutions
Our high levels of accuracy are helping institutions capture audio content from lectures & meetings and make these available as searchable text transcripts to end-users. We are particularly impressed by UCL’s approach to use our technology to assist
students with hearing impediments.
Time Alignment & Closed Captioning
Our universal time aligner, which can align any audio & text in any language, is helping companies add value to their end-users by making
content more searchable. Our general ASR also provides time stamps which can be used to produce closed captioning. Udemy recently conducted a market wide comparison of speech recognition and identified Speechmatics as clear winners – thanks guys!
Supporting of Start-ups
We love hearing when other companies are building fascinating applications on-top of our technology. These include workflow editors to support journalists, media analysis (Fraim), text-to-speech platform (Innoetics), transcription editors.
(BBC, NowTranscribe), audio search (Clarify) or survey reports (GoReport). We keep hearing of new applications for our technology and would love to hear your idea contact us.