…</item> </models> </item> </technologies> </technology_subsystem_settings> The meaning of individual elements should be pretty self-explanatory. Probably the only element which deserves more info is the config_file element – this one should be basically kept empty ;-)… but allows to specify a name of *.bs BSAPI configuration file to be used by the technology initializer instead of the default file belonging to…
Search: api
46 results
…WAVE file format” BSAPI exception is somehow confusing here, since it’s actually a harmless error, meaning just that the format detection failed. However, since the converter is enabled, SPE called the converter, file was converted and successfully recognized afterwards – the response contains the converted file attributes. The second time, the file was uploaded to SPE with converter disabled –…
…of Phonexia Browser. Installation of new language or technology model can be done in the following steps: Unzip installation package with new models to a temporary directory. Each installation package will contain phxadmin (Linux) or phxadmin.exe (Windows) binary. When Phonexia Browser is stopped, move the new models from the bsapi directory to the bsapi directory in your SPE installation. In…
…want to test, contact our sales to arrange the cooperation. Download the files with additional languages locally and unzip them. Then copy the additional languages over to where you saved the default Evaluation package. In other words, merge the contents of the /bsapi/ directory with the /SPE/bsapi/ 4. Configure Phonexia Browser from the /Browser/ directory start PhxBrowser.exe (on Windows) or…
…package. In other words, merge the contents of the /bsapi/ directory with the /SPE/bsapi/ 4. Configure Speech Engine In order to configure the Speech Engine, we have to navigate to /SPE/ directory and start the configuration utility called phxadmin SPE on Windows In the /SPE/ directory type cmd in the Address bar, to open the Command line. In the command…
…the system: SPE database – the technology models, SPE user accounts, etc. are stored here SPE configuration file (usually /settings/phxspe.properties) technologies configuration file (usually /settings/ technologies.xml, or see phxspe.properties for details) licensing file (license.dat, usually stored along to phxspe.exe, or see phxspe.properties for details) Optimally, Partner should backup also the following entire SPE directory [optional], with all subdirectories (/bsapi/, etc.)…
…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…
…being a speech“, i.e. end of segment is detected less frequently. These values can be modified using a “user configuration file” – see What is a user configuration file article for additional details. In short, create appropriately named user config file with modified parameters along the standard config file in <SPE directory>/bsapi/stt/settings directory and restart SPE – it will automatically…
…(REST API) for myself? Unless you are a Gold partner, our NFR licenses are provided in the Starter Kit. The kit also includes the services of our consultants to ensure you can fully understand the Phonexia portfolio and all related technical details necessary for the installation, usage, and tuning of Phonexia systems. Do I really need to buy the Starter…
…is good quality? The technology is being developed to automatically detect low quality audio segments and try to reconstruct them. On the contrary, well-recorded segments should be automatically recognized and retained their original speech quality. Q: Is there a way to adapt this technology? No, unfortunately the software does not currently offer easy customization. Link to API reference https://download.phonexia.com/docs/spe/#Denoiser…
…output) Note: The outputs can contain the following special tokens: sil silent part (or no speech detected) The list of phonemes is available in the document phonemes_for_stt_and_kws.pdf (delivered as part of manuals in SPE or STT or KWS). Languages Supported List of supported languages in Phoneme Recogniser is same as in Keyword Spotting. Link to API reference https://download.phonexia.com/docs/spe/#%2Ftechnologies%2Fphnrec…
…by a number from (highest priority) to 99 (lowest priority) and can be set using X-Priority HTTP header when starting the asynchronous task. The PendingInfoResult response contains information about task priority. Priority can be set only when starting the task, it’s not possible to modify it afterwards. For additional info and example, see Task prioritization section in REST API documentation….
…i.e. should be handled by the application built on top of the SPE API. This includes handling of any metadata associated with the processed audiofiles, like phone numbers, source of the recording, date/time the audio was recorded, references to the persons speaking in the recording (names, photos, …), languages spoken in the recording, etc. – all this data is expected…
…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…
Adding words to STT language model on-the-fly is possible in SPE 3.45 or newer as part of preferred phrases feature. The POST /technologies/stt or POST /technologies/stt/input_stream API calls actually serve two purposes: specify the actual preferred phrases (in the phrases part) specify words to be added to STT language model (in the dictionary part) Each part can be used independently,…