Search Results for: lid models

Results 21 - 30 of 41 Page 3 of 5
Results per-page: 10 | 20 | 50 | 100

STT Language Model Customization tutorial

Relevance: 2%      Posted on: 2019-04-24

Language Model Customization tool (LMC) provides a way to improve the Speech To Text performance by creating customized language model. Language model is an important part of Phonexia Speech To Text. In a simplified way it can be imagined as a large dictionary with multiple statistics. The Speech To Text technology uses this dictionary and statistical model to convert audio signals into the proper text equivalents. Due to general diversity of spoken speech, the default generic language model may not acknowledge the importance of certain words over other words in certain situations. Language model customization is a way to inform the…

Keyword Spotting results explained

Relevance: 2%      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…

Get better support

Relevance: 2%      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…

Q: What LLR, LR and score mean?

Relevance: 2%      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…

Q: I can’t manage to run Phonexia Browser software. I always get an error.

Relevance: 2%      Posted on: 2017-06-27

I always get the same error messages: unable to connect to the SPE unable to start the localhost: giving up and kill the localhost. A: It might be because the initialization of SPE engine is too long. Phonexia Browser software treats it as initialization failure and kills the server. You can proceed as follows: Increase timeout in Settings > Speech Engine tab > First connection timeout Use fewer instances of technologies Use smaller models of technologies


Relevance: 2%      Posted on: 2018-02-01

Likelihood Ratio – Result from statistical test for two models comparation. It gives back number which expresses how many times more likely the data are under one model than the other. LR meets numbers in interval <-∞;+∞>

Sizing of the computing units for speech technologies

Relevance: 2%      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…