Releases and Changelogs (VIN)
Phonexia Voice Inspector (VIN) is developed as a desktop application for forensic speaker comparison.
Releases
Version | Release Date | End of Support | Maintained Until | Release type |
---|---|---|---|---|
5.2 | 2024-04-15 | 2027-12-31 | 2027-12-31 | Public |
5.1 | 2023-12-07 | 2027-12-31 | 2027-12-31 | Public |
5.0 | 2023-06-29 | 2027-12-31 | v.5.1 | Public |
4.0 | 2019-12-12 | 2023-12-31 | 2023-12-31 | Public |
3.2 | 2018-03-16 | 2020-12-16 | 2020-12-16 | Public |
3.1 | 2016-10-24 | 2018-04-24 | v.3.2 | Public |
3.0 | 2016-08-05 | 2018-02-05 | v.3.1 | Public |
1.3 | 2015-06-04 | 2016-12-04 | 2016-12-04 | Public |
Changelogs
Voice Inspector 5.2
Voice Inspector 5.2.0, BSAPI 3.61.0 (2024-04-04)
- New: New Case wizard checks for presence of Questioned and Reference recordings
- New: Number of audio channels is displayed in
- Case view
- Recording details view
- Score table view
- Report
- Fixed: Application crash with phoneme search
- Fixed: Generalized logistic distribution for Suspected speaker vs. Suspected speaker Target score distribution
- Fixed: Population Set selected correctly even if renamed in the selection window
- Improved: Speech length display in the case view: added “Unlimited” option to display the speech length permanently
- Improved: SID Evidence score aligned with Speech Engine output of SID score
- Removed: Speech length compensation
Voice Inspector 5.1
Voice Inspector 5.1.0, BSAPI 3.60.0 (2023-12-07)
- New: A generalized logistic distribution function is added as a default option. The Gaussian distribution function is preserved as the secondary option. The figure below shows both probability distribution functions applied to the same data set.
Figure 1: shows both probability distribution functions and demonstrates that generalized logistic PDF can more accurately model a skewed distribution. Such skewed distributions are being produced by the modern highly accurate speaker identification system of Phonexia.
- Fixed: Audio files with Unicode characters in their name can be also opened on Windows.
- Changed: The histogram bins in the probability density function plot are now normalized.
- Changed: The case description (field in the information table on the left when selecting a case) is now editable.
- Changed: The description of the act and the Conclusion of the case can be edited from the case information table.
- Improved: Copying from chart values table is enhanced – added header to copied data, added Ctrl+C keyboard shortcut to copy table data.
- Improved: Report template is enhanced for all included languages – improved report layout, easier CSS styling via style.css, added new report variables for Expert and Organization
Voice Inspector 5.0
Voice Inspector 5.0.0, BSAPI 3.57.0 (2023-06-20)
- New: Speaker Identification XL5 technology model
- New: Data in lists/tables are now sorted alphabetically
- New: Enlarge the initial set of speakers included in examples; some of the speakers are multilingual
❗❗❗ Voice Inspector 5.0 requires a new license.
To upgrade from version 4 or 3, please contact the Phonexia sales representative.
Phonexia Voice Inspector 5.0 brings a Speaker Identification model XL5, that provides more accurate results for telephony data in comparison with previous generations of Speaker Identification models such as SID4 XL4. Users can observe that the SID4 XL5 model returns different values of LLR scores which are used for evidence calculation. Therefore Speaker Identification score distribution for the population sets differs from previous generations. One of the identified differences is a higher discriminability of target and non-target scores. See an example of score distributions applied to the same population set below.
Figure 2: VIN4 probability density function for British male population set
Figure 3: VIN5 probability density function for British male population set
Voice Inspector 4.0
Voice Inspector 4.0.4, BSAPI 3.40.14 (2023-02-10)
- Fixed: The app crashes when saving a recording without speech
- Fixed: Error dialogs that appeared behind the main window
- Fixed: Too small font in a report template
- Fixed: “Jagged” graphs in the SID Evaluator under certain circumstances
Voice Inspector 4.0.3, BSAPI 3.40.13 (2022-07-15)
- New: Added Romanian to the default set of available languages
- New: Added the ability to define custom language in the speaker metadata
- Fixed: When discarding a changed photo, the confirmation dialog “Do you want to save…” popped up infinitely
- Fixed: Missing file names when the SID Evaluator evaluates speakers from the workspace
- Fixed: Unwanted extra comparisons when the SID Evaluator evaluates speakers from the workspace (instead of comparing only A x B, it compared also B x A, A x A)
- Fixed: Size of graphs in the report when using the Hi-DPI screen and overlapping labels in the graph of the probability density function
- Improved: Speaker export error message
- Improved: Minor improvements to the phoneme search bar to make it clearer
Voice Inspector 4.0.2, BSAPI 3.35.5 (2021-03-25)
- Fixed: One more issue in the detection of certain USB license tokens
Voice Inspector 4.0.1, BSAPI 3.35.3 (2020-11-25)
- Fixed: Detection of certain USB license tokens
Voice Inspector 4.0.0, BSAPI 3.23.0 (2019-12-11)
- New: Speaker Identification L4 model
- New: Added Diarization Technology (available in waveform editor)
- New: Added possibility to set the type of estimation of the Target distribution
- New: Using population set to estimate Target distribution allows 1:1 comparison
- Fixed: Various bug fixes
- Improved: Reworked dialog for population set management
- Changed: Population sets structure changed
- Removed: Speaker Identification models S2, L2, L3, XL3 are no longer supported
Voice Inspector 3.2
Voice Inspector v3.2.2, BSAPI 3.15.0 (2018-06-05)
- Fixed possible application crashes on Windows
- Added phoneme type ‘affricate’ and fixed phoneme types:
- phoneme ‘C’ changed from ‘fricative’ to ‘affricate’
- phoneme ‘D’ changed from ‘fricative to ‘plosive’
- phoneme ‘T’ changed from ‘fricative to ‘plosive’
- phoneme ‘c’ changed from ‘plosive’ to ‘affricate’
Voice Inspector v3.2.1, BSAPI 3.15.0 (2018-03-16)
- Export of Speakers/Populations allows export only voiceprints
- Wave editor’s Spectrum settings allow to set up smaller values for Window length
- Added generic label panel in Wave editor
- The new version of population sets (population sets support speech length compensation)
- The added dialog which offers to import new population sets into the user’s workspace
- Forbid usage of recordings with low SNR score
- Added settings of Scoring:
- the base of the logarithm of evidence score (log10 or ln)
- estimation of non-target distribution
- recording’s speech length compensation (beta)
- SID Evaluator improvements:
- The evidence table displays the names of compared recordings
- added Spanish localization
- updated BSAPI
- fixed labels and minor bugfixes
Voice Inspector 3.1
Voice Inspector v3.1.1, BSAPI 3.9.1 (2016-12-14)
- fixed bug in Speaker Identification Evaluator – Evaluation from a directory
Voice Inspector v3.1.0, BSAPI 3.9.1 (2016-10-24)
- VIN is available with the SID_L3 technology model
Voice Inspector 3.0
Voice Inspector v3.0.0, BSAPI 3.7.0 – Aug 5 2016
- VIN is available with the SID_XL3 technology model
- Bug fixes
- fixed Tippett graph colors
- fixed WaveEditor save recording issue
- disabled multiple recordings with the same name