Skip to content Skip to main navigation Skip to footer

Search: test

43 results

Understand SPE configuration

…physical server, configure your technologies.xml to the following number of instances: SQE: <#_cpu_cores>/4 VAD: <#_cpu_cores>/2 any other technology: <#_cpu_cores> (Note: your license should also be configured properly. Ask our Sales department for cooperation in case of hot-load evaluation tests. The production license will be configured with our assistance, of course) Optimal RAM recommendation: 4 cores: 16 GB RAM 8 cores:…

Licensing (technical details)

…by firewall, routing issues, maintenance of the Phonexia servers, etc. NOTE: Although we usually achieve 98 % availability, it cannot be guaranteed and SLA cannot be declared. Therefore we do not provide NET license type for production deployments. Typical recommended usage: development testing functionality of the software data evaluation Not recommended for: demonstration purposes (partner to customer) due to its…

Speech Engine update

…concerns the SPE configuration file, especially when updating from rather old SPE version) do the changes – again, a visual comparison tool makes this step much easier! test the updated installation Example of update process for SPE: Stop running SPE Make a backup of SPE (see Understand SPE administration and backup) Optionally(!) delete bsapi directory – this decision is fully…

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

…FtRTaudio when calculating hardware sizing and scaling options, especially for installation built for mass data processing where each I/O matters. Don’t forget to test real data-sets (recordings) for statistical information like speech/non-speech ratio and so on. This approach can help you with budget calculation significantly. Use FtRTnet_speech when comparing individual CPU performance using strict academic methodology using exact reference point….

Understand SPE configuration file

…be useful to use a shared database file, so that all SPE instances can access the same internal data (files information, speaker models, …). On the other hand, shared SQLite database may create a performance bottleneck, i.e. it’s recommended to do some testing of particular setup. server.db.mariadb.host, server.db.mariadb.port # Database address # ! Note that the property name was changed…

Quick Start Guide (VIN)

Follow these steps to use Phonexia Voice Inspector: Download its latest version (provided as a ZIP archive here) Unpack the archive Download a license obtained from Phonexia. Please, don´t change name of the license (always in license.dat format). Note that a NET type of license needs an Internet connection to connect to our phonexia.com license server. The USB dongle type…

Understand SPE executable files

…registered Windows service phxclient phxclient is simple command line SPE client. It is specifically designed for the SPE REST API, e.g. it automatically handles polling for asynchronous requests results. phxclient also provides additional functionality related to SPE features, like ability to stream audio recordings via RTP or HTTP stream. Therefore it’s useful for quick testing of the SPE API without…

Time Analysis Extraction (TAE)

…to the other: places of speaker’s longest and shortest reaction, i.e., where this speaker stopped talking and the other speaker started talking the average reaction times number of speaker-turns 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….

STT: Adding words to language model on the fly

…using the input example shown above. The added parts are highlighted. { “result”: { “version”: 5, “name”: “SpeechRecognitionResult”, “file”: “/test.wav”, “model”: “EN_US_6”, . . . “phrases”: [ { “phrase”: “this is preferred phrase” }, { “phrase”: “and some other phrase” } ], “dictionary”: [ { “word”: “preferred”, “pronunciations”: [ { “phonemes”: “p r ih f er d”, “out_of_vocabulary”: false, “class”:…

Critical Issue

…fails again on a different data input after Phonexia’s software restart. If the issue does not appear on the latest version of Phonexia’s software, it will not be considered a Critical Issue. A Critical Issue is being fixed on a best-effort basis and a fixed version of the Product is delivered within the next Bug fix release or Software Update….

FAQs (Browser)

…score sharpness value to calibrate the recalculation. Please see Calibration in technology documentation. in FAQ Phonexia Browser, FAQ Speech Platform Permalink Q: What do LLR, LR and score mean? A: These abbreviations mean the following: LR – likelihood ratio, result from statistical test for two models comparison. It returns a number which expresses how many times more likely the data…

Support

latest version of Phonexia’s software, it will not be considered a Critical Issue. A Critical Issue is being fixed on a best-effort basis and a fixed version of the Product is delivered within the next Bug fix release or Software Update. Permalink Minor Issue Any scenario that does not fall under the Critical or Severe Issue definitions above. The Product…