Search Results for: score transformation

Results 1 - 20 of 25 Page 1 of 2
Results per-page: 10 | 20 | 50 | 100

Speech To Text results explained

Relevance: 100%      Posted on: 2019-05-27

This article aims on giving more details about Speech To Text outputs and hints on how to tailor Speech To Text to suit best your needs. In the process of transcribing speech, the Speech To Text technology usually identifies multiple alternatives for individual speech segments, as multiple phrases can have similar pronunciations, possibly with different word boundaries, e.g. “eight tea machines” vs. “eighty machines”. The technology provides various output types which show only single or multiple transcription alternatives. For processing realtime streams, two result modes are supported – one mode provides complete transcription, second mode provides incremental results. Output types…

Q: What LLR, LR and score mean?

Relevance: 12%      Posted on: 2017-06-27

A: These abbreviations mean the following: LR - likelihood ratio, result from statistical test for two models comparison. It returns a number which expresses how many times more likely the data are under one model than the other.  LR meets numbers in interval <0;+inf). LLR - abbreviation for log-likelihood ratio statistic, logarithmic function of LR. LLR meets numbers in interval (-inf;+inf). Percentage (normalised) score - commonly used mathematical transformation of the LLR to percentage. This number is better for human readability but may bring some doubts if LLR numbers are too high (typically for some non-adapted installations). Interval <0;100> (or…

Keyword Spotting results explained

Relevance: 8%      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…

Terminology

Relevance: 6%      Posted on: 2017-06-15

Document which briefly describes processes and relations in Phonexia Technologies with consideration on correct word usage.   SID - Speaker Identification Technology (about SID technology) which recognize the speaker in the audio based on the input data (usually database of voiceprints). XL3, L3,L2,S2 - Technology models of SID. Speaker enrollment - Process, where the speaker model is created (usually new record in the voiceprint database). Speaker model: 1/ should reach recommended minimums (net speech, audio quality), 2/ should be made with more net speech and thus be more robust. The test recordings (payload) are then compared to the model (see…

Voice Inspector – Interpretation of results

Relevance: 5%      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)

Relevance: 4%      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.…

Age Estimation

Relevance: 4%      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…

Language Identification results explained

Relevance: 4%      Posted on: 2019-05-20

This article aims on giving more details about Language Identification scoring and hints on how to tailor Language Identification to suit best your needs. Scoring and results explanation When Phonexia Language Identification identifies a language in audio recording (or languageprint) using a language pack, it creates languageprint of the recording (if input is audio recording) compares that languageprint with each language in a language pack and calculates probability that these two languages are the same The final scores are returned as logarithms of these individual probabilities – i.e. as values from {-inf,0} interval – for each language in the language pack.…

Speaker Identification: Results Enhancement

Relevance: 2%      Posted on: 2019-05-29

Speaker Identification (SID) Results Enhancement is a process that adjusts the score threshold for detecting/rejecting speakers by removing the effect of speech length and audio quality. This is achieved by use of Audio Source Profiles, that represent as closely as possible the source of the speech recording (device, acoustic channel, distance from microphone, language, gender, etc.). Although the out-of-the-box system is robust in such factors, several result enhancement procedures can provide even better results and stronger evidence. Audio Source Profile An Audio Source Profile is a representation of the speech source, e.g., device, acoustic channel, distance from microphone, language, gender,…

Browser3 – Releases and Changelogs

Relevance: 1%      Posted on: 2020-07-24

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 v3.31.2, BSAPI 3.31.0 - Jul 24 2020 Non-public Feature Preview release Fixed: STT result version mismatch Phonexia Browser v3.31.1, BSAPI 3.31.0 - Jul 08 2020 Non-public Feature Preview release New: Browser now requires CentOS 7 or other Linux based OS with glibc >= 2.17 Version 3.31.0 was skipped Phonexia Browser v3.30.8, BSAPI 3.30.8 - Jun 29 2020 Public release Fixed: SID Evaluator…

Speech Quality Estimator – Essential

Relevance: 1%      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…

Time Analysis (TAE)

Relevance: 1%      Posted on: 2017-05-18

Technology description Technology Time Analysis Extraction by Phonexia extracts base information from dialogue in a recording, providing essential knowledge about conversation flow. That makes it easy to identify long reaction time, crosstalk, or responses of speakers in both channels.  This technology is only meaningful when used on recordings with 2 channels. As an answer to the TAE technology, SPE returns a json/xml file. This file includes general information about the technology and details of the time analysis. The technology can work either with a closed recording or with a stream. Monologue Describes the statistics of a recording related to one…

Language Identification (LID)

Relevance: 1%      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…

Keyword Spotting

Relevance: 1%      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…

Voice Activity Detection – Essential

Relevance: 1%      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…

VIN – Releases and Changelogs

Relevance: 1%      Posted on: 2018-04-08

Phonexia Voice Inspector (VIN) is developed as a desktop application for forensic speaker comparison. This page lists changes in VIN releases. Releases Changelogs Voice Inspector v4.0.0, BSAPI 3.23.0 - Dec 11 2019 - VIN is available with L4 technology model - Other technology models (S2, L2, L3, XL3) are no longer supported - Added Diarization Technology (available in waveform editor) - Population Sets structure changed - Reworked dialog for population set management - Added possibility to set type of estimation of the Target distribution - Using population set to estimate Target distribution allows 1:1 comparison - Bug fixes Voice Inspector…

Time Analysis

Relevance: 1%      Posted on: 2018-04-15

Time Analysis Extraction (TAE) by Phonexia extracts base information from dialogue in a recording, providing essential knowledge about conversation flow. That makes it easy to identify long reaction time, crosstalk, or responses of speakers in both channels. This technology is only meaningful when used on recordings with 2 channels. As an answer to the TAE technology, SPE returns a json/xml file. This file includes general information about the technology and details of the time analysis. The technology can work either with a closed recording or with a stream. Monologue Describes the statistics of a recording related to one channel. channel…

How to convert STT confusion network results to one-best

Relevance: 1%      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…

Speech Quality Estimation

Relevance: 0%      Posted on: 2018-04-02

Speech Quality Estimation (SQE) is a language-, domain- and channel-independent technology that quantifies the quality of an audio recording. 2 most important statistics used in the calculation of the SQE score are SNR (signal-to-noise ratio) and the bitrate of the recording. SQE is usually part of the rapid filtration process in deployments. SQE also measures over 20 other properties of the recording, all of which can be found in the output file and further processed. See description in SPE documentation. Typical use cases are: verification of recording quality on the input, searching based on quality of the recording, noise of…