Before designing and developing the application, we encourage Partner to find clear answer for the following questions:
- Do my customers need file processing (audio) or stream processing in real time?
- What is the human power of the customer that can analyze the results?
- How many minutes per day or streams in parallel do my customer need to process?
- What are real benefits for customer (finding the needle in haystack, approaching new information, processing only few data with highest possible accuracy)?
- How the solution match the current processes and infrastructure of the customer?
- How many false alarms are acceptable by customer?
- Is there high availability (HA) required for the solution?
- Does customer need to use a specific hardware (mainly CPU, virtualized infrastructure vs. HW) or are you going to buy specific HW for customer?
- What is short/long time storage requirements (ie. audio and results availability, desktop vs. distributed system)?
- Is there any synchronization required (ie. voiceprint database to clients)?
- What is the topology of the solution/app (ie. where to store audio, voiceprints, results, …)?
- How to measure evaluation results and how to process calibration?
We encourage Partner to become familiar also with the following points:
- Phonexia Speech Engine features and list of the technologies
- Best practices -typical processing flows and architecture from our previous projects
- Databases schema
- Other Phonexia components and tools as example application that can give you inspiration
- Licensing possibilities of the Phonexia product
For application design and development, please see the most important points in Best practices.