LumenVox, a provider of speech and voice technology, announced its next-generation Automatic Speech Recognition (ASR) engine with transcription. The new engine, built on a foundation of artificial intelligence (AI) and deep machine learning (ML), helps deliver more accurate speech-enabled customer experiences.

The new LumenVox ASR engine uses a Deep Neural Network (DNN) architecture and its speech recognition processing capabilities. The new ASR engine accelerates the ability to add new languages and dialects and provides a modern toolset to expand the language model to serve a more diverse base of users. LumenVox enables customers to:

  • Future-proof speech technology: LumenVox’s single language model enables customers to quickly add new languages and non-native speaking accents.
  • Migrate legacy speech applications: Through the LumenVox Speech Tuner, customers can migrate most of their grammars and confidence values from legacy applications to the LumenVox ASR.
  • Deliver a seamless customer experience: By converting speech-to-text in real-time, the LumenVox ASR engine delivers high availability and accurate transcription with little or no latency.
  • Deploy in any environment: LumenVox provides customers with complete flexibility to deploy their speech applications in any environment: on-premise, multi-cloud, or a hybrid model.