Speech Engine (SPE) is developed as RESTfull API on top of Phonexia BSAPI.
SPE was formerly known as BSAPI-rest (up to v2.x) or as Phonexia Server (up to v3.2.x).
This page lists changes in SPE releases.
Tag Archives: Speech Engine
TUTORIAL: Speaker Identification – How to Do a Basic Test
Premium Content. This is a part which requires a higher (and non-anonymous) Site access level. How to solve this situation:
- Not registered yet? It’s easy to register – and it’s for free!.
- May you are simply not logged. Login here, please.
- Last resort – check your current Site access level here. You can ask Phonexia for “Partner upgrade” on the same page.
Phonexia Workflow
About
Phonexia Workflow is a set of tools complementing Phonexia Speech Engine (SPE), which allow users to chain speech technologies into scenarios and process audio recordings automatically using these scenarios.
Scenarios are programmed using uniform API which provides an abstraction over Phonexia Speech Engine application.
Provided Phonexia Workflow scenarios:
- SalEssentials – Speech Analytics Essentials filter out low quality audio files, provides demographic information, age estimation and speech to text processing
- VbsEssentials – Voice Biometrics Essentials filter out low quality audio files, provides gender identification, age estimation and speaker identification
The scenario is a tiny Java application which interacts with Phonexia technologies and optionally can use your service or database. Our team can help you implement your custom scenario.
Features
- Conditional processing and chaining of Phonexia speech technologies in one scenario
- Scenario oriented processing of data
- Predefined out-of-the-box scenarios for seamless processing of data
- Uses Phonexia Speech Engine for audio processing
- Covers majority of Phonexia speech technologies
- Results are stored into file, database, Elasticsearch or available via REST
- Optional automatic data fetching and processing from a directory
First steps
Installation
- Go through the following steps to install Phonexia Workflow with SPE
- Download package SPE3 according to your platform (Linux/Windows; your Phonexia contact will provide it)
- Download the license file (your Phonexia contact will provide it)
- Install the SPE3 according the SPE3 manual
- Download and install and runtime environment, LTS versions 8 or 11 are supported
- Download Phonexia Workflow package
- Unpack Phonexia Workflow package into your installation directory
- (Optional) Configure Phonexia Data Discovery Tool (see manual in /doc folder in Workflow package for more details)
- Configure Phonexia Workflow Runner (see manual in /doc folder in Workflow package for more details)
Brief and quick How-To-Start information are provided in README.txt placed in installation directory
End User Manual
Partners and customers are encouraged to see Phonexia Workflow software manual available as PDF file in /doc sub-directory in standard software package and installation.
You might be interested to see the following information in manual:
- Introduction
- Usage
- Installation
- Workflow Runner API
- Scenarios Overview
Troubleshooting
In case of any problems, please view the log directory with logs and consult the Troubleshooting section in the README.txt or the End User Manual.
If problem remains, please describe intended action to support@phonexia.com. In case of technical problems, please send us also logs from the log directory.
Releases and Changelogs
You might browse the Releases and Changelogs for Phonexia Workflow.