Search Results for: cpu

Results 1 - 18 of 18 Page 1 of 1
Results per-page: 10 | 20 | 50 | 100

SPE3 – Releases and Changelogs

     Posted on: 2020-09-12

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). This page lists changes in SPE releases. Releases Changelogs Speech Engine 3.30.13 (09/11/2020) - DB v1401, BSAPI 3.30.13 Public release New: Updated STT and KWS model AR_XL to version 5.1.0 Speech Engine 3.32.0 (08/28/2020) - DB v1500, BSAPI 3.32.0 Non-public Feature Preview release New: Added support for Webhooks and WebSockets in stream processing New: Added support for preferred phrases in 5th generation of STT (see POST /technologies/stt or POST /technologies/stt/input_stream) New:…

Language Identification (LID)

     Posted on: 2020-07-09

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. Phonexia uses state-of-the-art language identification (LID) technology based on iVectors that were introduced by NIST (National Institute of Standards and Technology, USA) during the 2010 evaluations. The technology is independent on text and channel. This highly accurate technology uses the power of voice biometrics to automatically recognize spoken language. Application areas Preselecting multilingual sources and routing audio streams/files to language dependent…

How to configure Speech Engine workers

     Posted on: 2020-03-28

Worker is a working thread performing the actual files- or realtime streams processing in Speech Engine. This article helps to understand the Speech Engine workers and provides information how to configure workers for optimal performance and server utilization. The default workers configuration in settings/phxspe.properties is as shown below – 8 workers for files processing and 8 workers for realtime streams processing. These numbers mean the maximum number of simultaneously running tasks. # Multithread settings server.n_workers = 8 server.n_realtime_workers = 8 Requests for additional file processing tasks are put in a queue and processed according their order and priorities. Requests for…

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…

Speaker Identification (SID)

     Posted on: 2019-06-13

Phonexia Speaker Identification uses the power of voice biometry to recognize speakers by their voice... i.e. to decide whether the voice in two recordings belongs to the same person or two different people. High accuracy of Speaker Identification, the Phonexia's flagship technology, has been validated in a NIST Speaker Recognition Evaluations. Basic use cases and application areas The technology can be used for various speaker recognition tasks. One basic distinction is based on the kind of question we want to answer. Speaker Identification is the case when we are asking "Whose voice is this?", such as in fake emergency calls.…

Designing and Developing Application

     Posted on: 2018-04-15

Before designing and developing the application, we encourage Partner to find clear answer for the following questions: Customer requirements: Do my customers need file processing (audio) or stream processing in real time? What is the human power of the customer that can analyze the results? How many minutes per day or streams in parallel do my customer need to process? What are real benefits for customer (finding the needle in haystack, approaching new information, processing only few data with highest possible accuracy)? How the solution match the current processes and infrastructure of the customer? How many false alarms are acceptable…

Age Estimation

     Posted on: 2018-04-12

Phonexia Age Estimation (AGE) estimates the age of a speaker from audio recording. The process of voiceprint extraction is similar to the extraction of SID, but as a result different features get extracted; therefore, the voiceprints extracted from AGE and SID are not mutually compatible. Technology Trained with emphasis on spontaneous telephony conversation The technology is language-, accent-, text-, and channel- independent Compatibility with the widest range of audio sources possible (applies channel compensation techniques): GSM/CDMA, 3G, VoIP, landlines, etc. Input Input format for processing: WAV or RAW (8 or 16 bits linear coding), A-law or Mu-law, PCM, 8kHz+ sampling…

Open Source Acknowledgement

     Posted on: 2018-04-06

This page collect information about Open Source code and licenses. You might be interested to ask your Phonexia contact what part of the page is relevant to your project. Phonexia Voice Verify dependencies Name  Version  License  Django  2.1.11  BSD Jinja2  2.11.2  BSD-3-Clause  MarkupSafe  1.1.1  BSD-3-Clause  Pygments  2.6.1  BSD License beautifulsoup4  4.9.1  MIT  behave  1.2.6  BSD behave-django  1.4.0  MIT  certifi  2020.6.20  MPL-2.0  chardet  3.0.4  LGPL  coreapi  2.3.3  BSD coreschema  0.0.4  BSD  defusedxml  0.6.0  PSFL  django-allauth  0.39.1  MIT  django-constance  2.7.0  BSD  django-cors-headers  3.4.0  MIT License  django-environ  0.4.5  MIT  django-extra-fields  2.0.5  Apache-2.0  django-picklefield  3.0.1  MIT  django-rest-auth  0.9.3  MIT  djangorestframework  3.9.1  BSD  docker  4.2.2 …

Voice Activity Detection – Essential

     Posted on: 2018-04-04

Phonexia Voice Activity Detection (VAD) identifies parts of audio recordings with speech content vs. nonspeech content. Technology Trained with emphasis on spontaneous telephony conversation The technology is language-, accent-, text-, and channel- independent Compatibility with the widest range of audio sources possible (applies channel compensation techniques): GSM/CDMA, 3G, VoIP, landlines, etc. Input Input format for processing: WAV or RAW (8 or 16 bits linear coding), A-law or Mu-law, PCM, 8kHz+ sampling Output Log file with processed information (speech vs. nonspeech segments) Segmentation The section Segmentation describes the results of VAD, which are segments of detected voice and silence. Segments are…

Speech Quality Estimator – Essential

     Posted on: 2018-04-04

Phonexia’s Speech Quality Estimator quantifies the acoustic quality of recordings. This helps the user to quickly determine whether the acoustic quality of a recording is good for processing with other speech technologies or not. As an answer for SQE, the SPE returns a json/xml file. This file includes general information about the technology and statistics of all (one or two) channels. The statistics of all channels include the numbers for many aspects of recording quality, and the overall global score. Technology The technology is language-, accent-, text-, and channel- independent Compatibility with the widest range of audio sources possible (applies…

Product Portfolio

     Posted on: 2018-04-02

Phonexia Speech Platform is an umbrella concept for all Phonexia’s products and services related to speech technologies. It gives us the ability to customize various products to a wide range of customer needs. Platform Edition is an encapsulation of specific setup of speech technologies, modules, applications, utilities and services designed for a specific market segment. We distinguish Speech Analytics (SAL) and Voice Biometrics (VBS) as most common domain of usage. It is also a tool for marketing and sales. Voice Biometrics is focused more on identifying speaker, gender, language spoken and more. Speech Analytics focuses on gathering information about content…

Licensing (technical details)

     Posted on: 2018-03-02

This document describes all licensing types for Phonexia product licensing available to our partners and customers. Each partner/customer can choose the licensing variant which best fits the current project or infrastructure. The document does not describe business conditions of Phonexia licensing. What is the License? The License is a formal agreement regarding “The Product Usage Rights” between Phonexia s.r.o. and a user of any Phonexia technology or Phonexia product. Licenses are issued by the Business Department for all speech technologies and products, and may be required in order to use utilities and tools developed by Phonexia or partners. For technical…

SPE configuration

     Posted on: 2018-02-02

Basic explanation of configuration directives for SPE with hints & tips. Overview of phxspe.properties for beginners.

Sizing of the computing units for speech technologies

     Posted on: 2018-02-02

Best practices for good sizing of Phonexia technologies depend on a few facts: Intense work with large data sets requires good performance and bandwidth between RAM and CPU. It all depends on the size of the files with technological models data, usually loaded into RAM and used intensively for computing operations Always think only about physical cores of CPU (HT, VT features can't help in performance) Also seek for CPUs with a large L3 cache. And the better CPUs are those with higher l3_cache_size/#_of_physical_CPU_cores ratio. We currently assume that CPUs from the current Intel Xeon Family in the 4th generation…

Speaker Diarization (DIAR)

     Posted on: 2017-06-26

About DIAR Phonexia Speaker Diarization (DIAR) enables segmentation of voices in one monochannel audio record. Technology Trained with emphasis on spontaneous telephony conversation The technology is language-, accent-, text-, and channel- independent Compatibility with the widest range of audio sources possible (applies channel compensation techniques): GSM/CDMA, 3G, VoIP, landlines, etc. Input Input format for processing: WAV or RAW (8 or 16 bits linear coding), A-law or Mu-law, PCM, 8kHz+ sampling Output Log file with processed information (segmentation of speech, silence, and technical signals – ie. elimination of phone lines beeps, DTMF tones, music, pauses, etc.) Audio file extracted for each…

Get better support

     Posted on: 2017-05-19

This page highlights advices based on the previous experience. If you have any suggestions or correction regarding the innovation of the tech support, please let us know. The Frequently asked questions and Lifetime Support Policies sections prepared for you on Partner Portal could also be of interest to you. 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…

Keyword Spotting (KWS)

     Posted on: 2017-05-18

About KWS Phonexia Keyword Spotting (KWS) identifies occurrences of key-words and/or key-phrases in audio recordings. Application areas: Security/defense Maintain fast reaction times by routing calls with specific content to human operators Search for specific information in large call archives Trigger alarms immediately (online) when an event occurs Call centers Increase operator and supervisor efficiency by searching calls Identify inappropriate expressions from operators Check marketing campaigns with automatic script compliance control Mass media and web search servers Index and search multimedia by keyword Route multimedia files and streams according to their content   KWS technology Acoustic based technology robust even with…