Skip to content Skip to main navigation Skip to footer

Search: se

132 results

Understand SPE metafiles

…can store whichever type of data would help your application. The files are physically stored in the SPE user’s “home”, in data subdirectory (see Understanding SPE home directory article for details). Maximum size of single metafile can be set using server.max_metadata_size setting in SPE cofiguration file. Example As an example, the picture below shows how Phonexia Browser uses SPE metafiles…

Q: We prefer USB dongle but without the USB storage

A: We don’t provide USB without memory storage, possible solutions are: establish security directives related to work with the USB dongle (persons allowed to, in/out memory scan check), use HW based licensing, use license server….

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….

Phonexia Ethical Code

…financial records and in cases of suspected or actual non-compliance to provide them to Phonexia. Unless otherwise required by applicable laws or relevant official authority, we will always keep provided information in strict confidentiality and use it solely in the extent and for the purpose of maintaining continuous compliance with the principles set forth in this Code.      …

Speech To Text / Keyword Spotting supported languages

…Standard Hungarian (Beta – only Keyword Spotting) HU1 2014-09 – On project basis Italian (Italy) IT_IT_6 2022-06 8th gen. Standard Kazakh (Kazakhstan) KK_KZ_6 2022-11 8th gen. Standard Pashto (Afghanistan) PS_6 2021-05 8th gen. Standard PS_5 2021-02 7th gen. Standard Polish (Poland) PL_PL_6 2022-04 8th gen. Standard PL_PL_5 2018-07 7th gen. Standard Serbian (Serbia) SR_RS_6 2023-04 8th gen. Standard Spanish (mix)…

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…

Get better support

Any errors should be tested on the latest version of the product. Please ask your Phonexia contact for a link to download the latest version. Before submitting issue/ticket… Any errors should be tested on the latest version of the product. Please ask your Phonexia contact for a link to download the latest version. For each issue, please collect the following…

SID: TUTORIAL: Speaker Identification – How to Do a Basic Test

…to download for commercial/research purposes under a Creative Commons 4.0 license. Data originates from OXFORD VGG VoxCeleb Dataset which detailed license can be found here. SpeakerID Example Data Set v1.0 83.89 MB Download Publications: S. Chung, A. Nagrani, A. Zisserman VoxCeleb2: Deep Speaker Recognition INTERSPEECH, 2018. Nagrani, J. S. Chung, A. Zisserman VoxCeleb: a large-scale speaker identification dataset INTERSPEECH, 2017….

Support

…the Product partially functional, the use of which in a production environment is substantially reduced. The Issue contains an error that impairs the ability of the system to process a majority of audio files or audio streams, or that renders the setup and maintenance of the system inoperable. Permalink Critical Issue The system is inoperative, and it has a critical…

Understand SPE home directory

…location might be useful e.g. in complex deployments with multiple separate SPEs which need to be accessing single centralized file storage placed on high-performance networked disk array, etc. Similarly to the operating systems, the SPE home directory contains subdirectories for each SPE user (see SPE user management article). These subdirectories contain data belonging to the respective users: – user’s file…

Documentation (Browser)

Partners and customers are encouraged to see the Browser3 software End User Manual available in [BROWSER]/ PhxBrowser_manual.pdf in a standard software package and installation. You might be interested in getting familiar with the following information in the manual: Typical Use Cases Technical Requirements Installation (the First Start) Update Using the Application – Features Using the Application – Typical Workflows…

KWS: Results explained

…sheet demonstrating the sigmoid function: Score-to-Confidence. Score-to-confidence conversion tuning Starting with SPE/BSAPI 3.24 (October 2019) it’s possible to modify the confidence calculation using confidence_shift and confidence_sharpness values in user configuration file in [score_calib:SKeywordScoreCalibrationI] section. User configuration file must have the same name as original configuration file, with added .usr extension, e.g. kws_en_us_5.bs.usr – see the What is a user configuration…

Q: How do you calculate SNR in Speech Quality Estimation?

A: Signal-to-Noise Ratio (SNR) is an important metric of whether a recording is worth further processing by other speech technologies, so it is part of our Speech Quality Estimation. However, calculating SNR automatically is not a trivial task. We use the fact that the statistical distribution of the frequencies in the waveform of speech has Gamma distribution. In contrast, noise

STT: How to properly convert Confusion Network results to One-best

Confusion Network output is the most detailed Speech Engine STT output as it provides multiple word alternatives for individual timeslots of processed speech signal. Therefore many applications want use it as the main source of speech transcription and perform eventual conversion to less verbose output formats internally. This article provides the recommended way to do the conversion. Time slots and…

Key Features (VIN)

Phonexia Voice Inspector software offers several features that strongly support the work of voice forensic experts: A standalone application with a complete easy-to-use Graphical User Interface (GUI) Automatic comparison of questioned recording (unknown speaker recording or voiceprint) against a suspected reference speaker (group of recordings or voiceprints) with a known speaker i.e. 1:1 identification and 1:N identification. Implemented speech technologies:…