Search Results for: spe

Results 1 - 20 of 121 Page 1 of 7
Results per-page: 10 | 20 | 50 | 100

Phonexia Speech Platform Release Plan

     Posted on: 2020-05-15

Starting with year 2020, Phonexia products use two types of releases: RELEASE TYPE FREQUENCY GENERAL AVAILABILITY SUPPORT Feature Max. once per month Limited (project based) Limited (project based) Public Twice a year (end of Q1 and Q3) No restrictions Standard Phonexia support Feature releases contain fresh new features, primarily intended for Proof-of-Concept projects and partners' testing of the new features in the wild and collecting feedback. Based on the feedback, the behavior of the features can be improved or changed in subsequent releases. Feature releases are created on approx. monthly basis. Feature releases are provided on a project basis, or…

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…

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…

Browser3 – Releases and Changelogs

     Posted on: 2020-03-27

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 v3.30.0, BSAPI 3.30.0 - Mar 27 2020 Public release Fixed: Target and non-target graphs in SID evaluator are swapped Fixed: PDF chart could be empty in the SID evaluator report Fixed: JSON parsing error during evaluation set creation when some file doesn't contain any speech Updated: Synchronize versioning with BSAPI Phonexia Browser v3.26.0, BSAPI 3.26.0 - Feb 28 2020 Non-public Feature Preview release…

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…

TUTORIAL: Speaker Identification – How to Do a Basic Test

     Posted on: 2019-10-08

Phonexia Speaker Identification is a voice biometry tool for recognition of speakers by their voice. In this video, we will show you how to start using this technology! You will learn how to create a "Speaker Model" to identify a speaker in a set of data. Ready to test it? Start with our video: What else is needed? 1. Phonexia Evaluation Package Evaluation package (download page) is consisting of Phonexia Browser and Phonexia Speech Engine including all necessary technologies. 2. Data We prepared the dataset for your testing. Package contains data for speaker model creation and speaker spotting too. The…

Workflow – Releases and Changelogs

     Posted on: 2019-10-07

Phonexia Workflow is a set of tools complementing Phonexia Speech Engine (SPE), which allow users to chain speech technologies into scenarios and process audio recordings automatically using these scenarios. This page lists changes in Workflow releases. Changelogs == Phonexia Workflow v1 == Phonexia Workflow 1.4.1 (10/07/2019) - SPE 3.16 - 3.17 Support for IPv4 only (since SPE does not support IPv6) Configurable application webhook address in both Workflow Runner and Data Discovery Tool This address is auto-detected when no value is supplied - default In some cases like network specific configuration it might be necessary to configure it manually Rapid…

Technical Training Essentials

     Posted on: 2019-09-27

Core objective: Understanding technical essentials of using Phonexia technologies and products Duration: ~94 minutes (7 + 19 + 22 + 23 + 23 min chapters) intended for product architects or developers assumes you have already watched Phonexia technologies introduction video assumes understanding of working in command line REST API principles processing JSON or XML Introduction (7 min) technologies recap CLI, REST and GUI interfaces overview https://youtu.be/xzrHyyIl01s MODULE 1: Getting started with Speech Engine (19 min) Installation Technologies configuration Server and database configuration Users configuration Files processing Synchronous and asynchronous requests, results polling Stream processing https://youtu.be/4qrB-GfFdWY MODULE 2: Filtering and supporting…

Phonexia Workflow

     Posted on: 2019-08-06

Phonexia Workflow is a set of tools complementing Phonexia Speech Engine (SPE), which allow users to chain speech technologies into scenarios and process audio recordings automatically using these scenarios. Scenarios are programmed using uniform API which provides an abstraction over Phonexia Speech Engine application. Provided Phonexia Workflow scenarios: SalEssentials - Speech Analytics Essentials filters out low quality audio files, provides demographic information, age estimation and speech to text processing VbsEssentials - Voice Biometrics Essentials filters out low quality audio files, provides gender identification, age estimation and speaker identification  The scenario is a tiny Java application which interacts with Phonexia technologies…

How do you calculate SNR in Speech Quality Estimation?

     Posted on: 2019-07-01

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 has Gaussian distribution. So we can estimate the SNR by looking at the frequency distribution in individual frames. This approach to SNR estimation is based on the article by Kim Chanwoo, and Richard M. Stern, called "Robust Signal-to-Noise Ratio Estimation Based…

Voice Inspector – supporting technologies

     Posted on: 2019-06-28

Automatic Speaker Identification (SID) is the most important but not the only Phonexia technology that is implemented in Voice Inspector (VIN). Apart from SID, forensic experts, users of VIN, can benefit from automatic Signal-to-Noise Ratio calculation, Voice Activity detection, Phoneme search, and a Wave editor which incorporates the waveform, spectrum and power panel. Let's have a look on how to utilize individual technologies. Signal-to-Noise Ratio Recording quality can strongly influence the reliability of SID results and so the outcome of a forensic case. Therefore, VIN uses a module of Phonexia Speech Quality Estimation (SQE) to calculate the Signal-to-Noise Ratio (SNR)…

Voice Inspector – Interpretation of results

     Posted on: 2019-06-24

Introduction Phonexia Voice Inspector (VIN) is a tool for forensic automatic speaker identification, compliant with the Methodological Guidelines for Best Practice in Forensic Semiautomatic and Automatic Speaker Recognition, published by the European Network of Forensic Science Institutes.  This post explains individual SID score types and ways to visualize the results in a speaker identification case implemented in Voice Inspector. Evidence In VIN, the term evidence has two meanings. In general, it refers to any SID score that the system calculates for any pair of recordings in the case. These scores are the output of the Phonexia SID technology which runs…

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.…

Keyword Spotting results explained

     Posted on: 2019-06-12

This article aims on giving more details about Keyword Spotting outputs and hints on how to tailor Keyword Spotting to suit best your needs. Scoring Keyword Spotting works by calculating likelihoods that at a given spot occurs a keyword or just any other speech, and comparing those two likelihoods. The following scheme shows Background model for anything before the keyword (1), the Keyword model (2) and a Background model of any speech parallel with the keyword model (3). Models 2 and 3 produce two likelihoods – Lkw and Lbg (any speech = background). Raw score is calculated as log likelihood…

Keyword Spotting

     Posted on: 2019-06-03

Phonexia Keyword Spotting (KWS) identifies occurrences of keywords and/or keyphrases in audio recordings. It can help you to get valuable information from huge quantities of speech recordings. You only need to specify the keywords or phrases you wish to find. This technology identifies all recordings with keyword occurrences and allows you to automatically route important recordings or calls to your experts. Typical use cases 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…