Most Recent Articles

  • Among the most useful of the LumenVox command-line tools are the "Simple" clients: SimpleASRClient, SimpleTTSClient, and SimpleMRCPClient. Each of these provides an example of how to perform basic functionality with LumenVox, and source code is provided for SimpleASRClient and SimpleTTSClient, illustrating how to use our C/C++ API to do speech recognition and text-to-speech synthesis.

  • A standard LumenVox installation has a number of command-line tools that are really useful for testing/verifying a new installation, and to help users get started working with our software. Even if you're not a command line expert, these tools are simple to use, and contain verbose help information, meaning that we recommend anyone using our software should familiarize themselves with them.

  • A fairly common task for IVR developers is to allow an appliation to recognize both DTMF keypresses and a caller's speech at the same time. Though generally voice user interface experts caution against the dreaded "Press or say 1..." menu type, there are some valid reasons to allow mixed-mode interactions. For instance, if you ask callers for a PIN, users may react differently depending on their situation.

  • Speech recognition, often called automatic speech recognition, is the process by which a computer recognizes what a person said. If you are familiar with speech recognition, it's probably from applications based around the telephone. If you've ever called a company and a computer asked you to say the name of the person you want to talk to, the computer recognized the name you said through speech recognition.

  • An old proverb says, "Man plans, God laughs." Nowhere is this more true than in software development. As developers, we try to plan for every contingency. In our minds we walk down every path our users may travel and compensate accordingly. Without fail, customers will traverse paths never intended for a user's feet. Immediately they come back to us and say "Look, it's broken!" No matter how much we plan, we must be able to modify our systems based on how our users actually use them, not on how we expect them to be used.

  • With the proper amount and quality of transcribed audio data, LumenVox can build new acoustic models to support speech recognition for new languages.

  • The LumenVox ASR includes support for American, Australian/NZ, UK and Indian English, Mexican Spanish, Colombian Spanish, and Canadian French, while the TTS has support for well over a dozen different languages.

    By setting the language identifier in a grammar or an SSML document, you can load different ASR acoustic models or TTS voices and effectively work with a variety of languages.