Skip to content Skip to main navigation Skip to footer

Search: se

95 results

Time Analysis Extraction (TAE)

…in the particular direction and details about crosstalk, for example where the other speaker is talking “over” this speaker Segmentation This section is optional and need to be explicitly turned on. It describes segments of detected voice and silence (the same as Voice Activity Detection technology). More information You can find more information in corresponding chapter of API documentation: https://download.phonexia.com/docs/spe/#Time%20Analysis…

Pricing

…of that period depending on the contractual agreement. Phonexia will deliver a license key and activation instructions to each customer individually and perform the initial license activation within the set-up phase. The license will be valid for the whole term agreed in the contract. Further licensing details and agreements covered in detail in separate dedicated documents – EULA or others….

FAQs (VIN)

Voice Inspector FAQ Q: When I start VIN software, it gives me “License is not for this application” error. A: Please attach the licensing file (license.dat) to the support ticket at our Service Desk. in FAQ Voice Inspector Permalink Q: When I start VIN software, it gives me “License expired” error. A: Please check that the licensing file (license.dat) file…

Proof of Concept

Voice Verify Proof of Concept Structure To successfully deploy and test the Phonexia Voice Verify product, the following steps need to take place. There are several areas where focus needs to be placed during the PoC. Process change Evaluation, calibration Technical integration Delivery of the solution to customers Evaluation of PoC results These steps are designed to take place in…

Understand SPE benchmark

…lengths and speech/non-speech ratios it is recommended to run the benchmark using multiple different audio files and calculate the average FtRT processing speed yourself. Alternatively, you can tune (or hack) SPE and prepare your own, or replace the default set of benchmarking recordings – see further below… Benchmark recordings sets The default sets of audio files supplied with SPE are…

Language Identification (LID)

…actually expected in your use case. This process of tailoring the language pack for particular needs is called language pack adaptation and is described in LID: Terminology and adaptation article. Example usages of custom language packs Law enforcement agency monitoring a network of criminals using only a particular set of languages can use the approach of keeping only languages expected…

Phonexia Speech Engine

…file to configure server and optionally database Optionally, run phxadmin –add-user in console to configure user account(s) to access the REST API (or use pre-configured user admin) Finally, run phxspe in console to start Speech Engine Now your SPE server is running and you can access the REST API via IP address and port set in properties file (settings/phxspe.properties). Details…

Q: How can we test Phonexia technologies?

…functionality of all technologies. The license validity is 90 days to allow you to test the technologies. Note: by default a NET license is provided for testing. This license needs to have active Internet connection to a phonexia licensing server in order to function. Rest assured no data – audio, metafiles or even analytical files, are ever sent to phonexia.com….

Speech Quality Estimation (SQE)

…of an empty recording SNR would divide by zero => is_valid would be false waveform_snr – the signal to noise ratio (SNR) describes the ratio of the useful signal to the noise signal it is measured in dB calculated from the waveform distribution, (silence – has Gaussian distribution, voice – has Gamma distribution); SNR = 20 * log10(S/N) technical signal…

Measuring of a software processing speed – what is the FtRT (Faster than Real Time)

noise, technical signals like ringing, DTMF tones, etc). This metric is useful for finding performance on actual audio data coming into audio processing pipeline. Regular recording with Voice and Silence segments in waveform Net Speech based FtRT is conservative, purely technical number. It is calculated from only spoken speech data, i.e. with all non-speech parts (silence, noise, DTMF tones, etc.)…

Understand SPE processing queue

…can be handled simultaneously is defined by server.n_workers for audio files processing and server.n_realtime_workers for realtime streams processing settings in SPE configuration file. This is by default set automatically, based on your hardware and software configuration – see How to configure Speech Engine workers article. The picture below demonstrates the queue processing (for the sake of simplicity, technologies assignments to…

Installation Guide

…In case you installed the Phonexia Orbis on a central server, to which the individual users connect, make sure to enable all the necessary Firewall rules and exceptions. As the steps needed to perform differ based on your IT services and infrastructure, follow your company guidelines to enable connection to the selected IP. Step #6 – Shutting Orbis down If…

Download Voice Inspector 5.1

…USB port, when USB licensing is in use. Run ./VoiceInspector (Linux) / VoiceInspector.exe (Windows). Set up wizard will be launched automatically and help you with the first launch. You can use example data included in the ZIP package (located in ./examples/). Step #3 – Check Documentation and Tutorials Please check the additional information Quick Start Guide (VIN) & Documentation (VIN)….

Phonexia Academy

…Technical Training Advanced – 2 courses: Voice Biometrics Course (in-person, 2 days) Speech Analytics Course (in-person, 2 days) In Technical Training Advanced courses, we share best practices, detailed use-cases analysis, and hands on. Both courses are adjusted to our partners’ requests considering their typical projects. You might be interested to read also the following: How to prepare for course?  …