Search Results for: ROM

Results 1 - 20 of 82Page 1 of 5
Results per-page: 10 | 20 | 50 | 100

SPE3 – Releases and Changelogs

     Posted on: 2021-04-16

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). Releases Changelogs Speech Engine 3.40.1, DB v1700, BSAPI 3.40.1 (2021-04-16) Public release Fixed: 6th generation STT/KWS stream result may start with words from end of previous stream Fixed: Some licensing error messages are not shown in log Fixed: Missing file names in log messages in SID and SID4 tasks Fixed: Keyword list may not work if XML is used as input and optional fields threshold or pronunciations are used Fixed: phxdamin2…

Phonexia Voice Inspector v3

     Posted on: 2021-04-09

About Phonexia Voice Inspector v3 (VIN3) provides police forces and forensic experts with a highly accurate speaker identification tool during investigation of criminal matters. It uses the power of voice biometry to automatically recognize speakers by their voice. Main features of the VIN3 application: Automatic speaker identification tool to strengthen results of the standard linguistics- and phonetics-based approach Scoring in Likelihood Ratio (LR) – result from a statistical test for a comparison of two hypotheses. The system returns a number from the interval <0, +∞>, which expresses how many times more likely the data are under one hypothesis than the…

Browser3 – Releases and Changelogs

     Posted on: 2021-04-06

Phonexia Browser v3 (Browser3) is developed as client on top of Phonexia Speech Engine v3. Phonexia Browser is a successor of Phonexia Speech Intelligence Resolver v1 (SIR1). This page lists changes in Browser releases. Releases Changelogs Phonexia Browser 3.40.0, BSAPI 3.40.0 (2021-03-26) Public release New: Compatibility with SPE 3.40 Changed: Using new licensing system under the hood (internal change) NOTE: When using Browser with FLS (Floating License Server), you need to upgrade FLS to version 2.x in order to be able to use Browser 3.40+ with FLS. Phonexia Browser v3.30.13, BSAPI 3.30.14 (2021-03-25) Public release Fixed: One more issue in…

LID adaptation

     Posted on: 2021-03-02

This article describes various ways of Language Identification adaptation. Basic terminology Languageprint (*.lp file) – numeric representation of the audio, extracted from audio file for language identification purpose of (similar to “voiceprint”, but representing the spoken language, not the speaking person) Languageprint archive (*.lpa file) – multiple languageprints combined into single archive Creation of languageprint archives is not supported by SPE, these are supported as input only.   Language model – digital characteristics of a specific language Language model can be trained from languageprints (*.lp), language prints archives (*.lpa), or from combination of both. LID language model should not be…

Language Identification (LID)

     Posted on: 2021-02-25

Phonexia Language Identification (LID) will help you distinguish the spoken language or dialect. It will enable your system to automatically route valuable calls to your experts in the given language or to send them to other software for analysis. Application areas Preselecting multilingual sources and routing audio streams/files to language dependent technologies (transcribing, indexing, etc.) Analyzing network traffic media (language statistics) Routing particular calls (languages) to human operators (language experts) Recognized languages Languages pre-trained in default language pack are listed in the table below, each LID generation is separate column (in the 4th generation we switched to using language tags…

Speech Engine configuration file explained

     Posted on: 2021-02-19

In this article we explain details of the Speech Engine configuration file phxspe.properties, located in settings subdirectory in SPE installation location. Settings in this configuration file affect the Speech Engine behavior and performance. The configuration file is usually created after SPE installation – on first use of phxadmin, a default configuration filephxspe.properties is created in the settings directory. The file is loaded during SPE startup, i.e. you need to restart SPE to apply any changes made in the file. If Speech Engine is used together with Phonexia Browser in so-called "embedded" mode (see details about "embedded SPE" mode in Browser…

Arabic dialects in Phonexia LID and STT

     Posted on: 2021-01-18

Arabic language has (a) one standardised variety, and (b) many non-standard varieties (dialects). In this article, our linguistic team explains differences between Modern Standard Arabic and Arabic dialects in the context of Phonexia Arabic models. Standard variety:  Modern Standard Arabic (MSA) All Arabs learn it at school (not from their parents, so we cannot say it is their native variety) It is lingua franca (common language) for the Arabic world – like English for Europeans; however, Arabs speak it much better since they are schooled in MSA from early age MSA is more similar to some dialects (e.g. Levantine), but…

What are STT preferred phrases and how to use them

     Posted on: 2020-11-26

Speech Engine version 3.32 and later includes new STT feature called Preferred phrases. This article explains what is the feature good for, how does it work internally and gives some tips for practical implementation. What are preferred phrases In the speech transcription tasks, there may be situations where similar sounding words get confused, e.g. "WiFi" vs. "HiFi", "route" vs. "root", "cell" vs. "sell", etc. Normally, the language model part of the Speech To Text does its job here and in the context of longer phrase or entire sentence prefers the correct word:  ×    I'm going to cell my car. Hmmm, such…

Speech Engine 3.35.3

     Posted on: 2020-11-24

Speech Engine 3.35.3, DB v1601, BSAPI 3.35.3 (2020-11-24) New Internal support for SAMPA phonetic alphabet Updated STT model RU_RU_A to version 4.5.0 of (updated language model) Updated STT/KWS/PHNREC model AR_XL to version 5.2.0 (updated language model, changed phonemes notation to X-SAMPA) Fixed Cannot create new output stream due to hanging unfinished tasks Task is not removed from pool when result is delivered via Webhook Some log messages contain format placeholder instead of numbers Missing <silence/> label in STT confusion network output STT confusion network contains <silence/> tags with confidence greater than 1.0 Diarization crashes during processing Diarization XL4 crashes on…

Speech Engine and technologies, instances, workers… explained

     Posted on: 2020-11-19

Configuring Speech Engine to utilize effectively the full power of underlying hardware can get challenging – one can easily get lost in all the strange terms like technologies, instances, slots, or workers... This article should shed some light in it. Speech Engine is like post office Thinking about Speech Engine, there is actually a very nice analogy with post office (or bank branch): Post office is a place providing different kinds of services – one can go there to send letters, send or pick up packages, get a POBox, get some financial services, insurance, etc.).   Speech Engine has various…

Phonexia Speech Engine

     Posted on: 2020-11-19

About Phonexia Speech Engine v3 (SPE3) is a main executive part of the Phonexia Speech Platform. It is a server application with REST API interface through which you can access all available speech technologies. Both, Linux 64bit and Windows 64bit operating systems are supported. Phonexia Speech Engine (SPE3) is adjustable server component which houses all speech technologies. SPE3 provides RESTfull application programming interface to access various technologies. Aside from technologies themselves the SPE has implemented other various functionality supporting work with speech technologies, recordings and streams, and others. Features Main purpose of SPE is to work as processing unit for…

Speech Engine 3.35.0

     Posted on: 2020-10-01

Speech Engine 3.35.0, DB v1600, BSAPI 3.35.0 (2020-10-01) New LID model L4 was promoted to production (LID BETA_L4 renamed to LID L4) Added new language tag documentation (doc/Technology_LID_L4_Language_tags.pdf) Updated STT model CS_CZ_5 to version 5.2.1 (fixes faulty transcription of numbers into Roman format) Added configurable STT Confusion Network threshold (in technology configuration file) Fixed STT didn't work with 4th and older generation models after introduction of the Preferred phrases feature in SPE 3.32 Update from SPE 3.30 causes errors in STT result cache memory leak in logging system Typo in name of es-XA language in LID model L4 default language…

Phonexia Partner Program for Government Partners

     Posted on: 2020-08-25

Phonexia Partner Program for Government Partners This partnership program rewards partners in the government sector for selling and integrating the Phonexia’s speech recognition and voice biometrics product portfolio. Program Enrollment If you aspire to becoming a Phonexia partner, you can enroll into the Phonexia Partner Program and complete a three-month onboarding period. During this period, you will enjoy the same partnership benefits as our Silver partners. Your assigned Phonexia Account Manager will take you through all necessary legal documents, highlight every business aspect of our cooperation, and organize two calls with a pre-sales person to ensure that you understand the…

How to convert STT confusion network results to one-best

     Posted on: 2020-04-06

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 word alternatives: The recommended algorithm for converting Confusion Network (CN) to One-best is as follows: loop through all CN timeslots from start to end in each timeslot, get the input alternative with highest score and if it's not <null/> or…

What is a user configuration file and how to use it

     Posted on: 2020-03-28

Advanced users with appropriate knowledge (gained e.g. by taking the Phonexia Academy Advanced Training) may want to finetune behavior of the technologies to adapt to the nature of their audio data. Modifying original BSAPI configuration files directly can be dangerous – inappropriate changes may cause unpredicatble behavior and without having a backup of the unmodified file it's difficult to restore working state. User configuration files provide a way to override processing parameters without modifying original BSAPI configuration files. WARNING: Inappropriate configuration changes may cause serious issues! Make sure you really know what you are doing. User configuration file is a…

How to configure STT realtime stream word detection parameters

     Posted on: 2020-03-28

One of the improvements implemented since Speech Engine 3.24 is neural-network based VAD, used for word- and segment detection. This article describes the segmenter configuration parameters and how they are affecting the realtime stream STT results. The default segmenter parametrs are as shown below: [vad.online_segmenter:SOnlineVoiceActivitySegmenterI] backward_extensions_length_ms=150 forward_extensions_length_ms=750 speech_threshold=0.5 Backward- and forward extension are intervals in miliseconds, which extend the part of the signal going to the decoder. Decoder is a component, which determines what a particular part of the signal contains (speech, silence, etc.). Based on that, decoder also decides whether segment has finished or not. Unlike in file processing…

Performance of the Speaker Identification 4th generation (SID4): Intel® Xeon® Platinum 8124M

     Posted on: 2019-10-30

Benchmark goals Find realistic performance using total recording length Find FTRT based exactly on net_speech (engineering sizing data) Find system performance using all physical cores Find system performance using all logical cores Infrastructure setup Intel® Xeon® Platinum 8124M is used in virtual machine with 8 physical cores reserved exclusively for this VM, Hyper Threading is enabled [16 logical cores available], 32GB RAM, 30GB SSD based storage, 1000 I/O.s-1  reserved per core Benchmark data setup Data set statistic: Number of files: 32 [300 seconds each] RAW recordings length ∑: 9600 [sec] Net speech length ∑: 4224.77 [sec] In the data set…

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

     Posted on: 2019-10-30

Faster Than Real Time (FTRT) is metrics developed for defining software performance reference point. Using this metric you can collect "benchmark" data of real processing speed for reviewed software, which should be found - and reproduced - on exactly defined HW. Then, comparing various benchmarks result, you can compare performance of the specified software and its parts on different HW configurations. And vice versa - using the same metric you can compare software from different vendors on the same HW configuration and for the same processing task. We are recognizing two measurable metrics: Recording based FTRT is calculated from real…