Brickroad
Brickroad
IndexSignalsBlog
/Index//

Product

  • Information Frontier Agent
  • Vendor Management Agent
  • Product Tour
  • Pricing

Solutions

  • All Solutions
  • Atlas
  • Wayfinder
  • Horizon

Suppliers

  • Sell Your Data
  • Start Onboarding
  • Programmatic Data License

Community

  • Public Index
  • Signals
  • Blog

Company

  • About
  • Team
  • Careers
  • Brand

Connect

  • LinkedIn
  • X
PrivacyTermsCookies

© 2026 Brickroad

/Index/Phonexia/Phonexia
P

Phonexia

PHONEXIAManage supplier listing

Proprietary labelled speech-authenticity evaluation corpora, disclosed indirectly but decisively through the product's calibration statement: the Replay Attack Detection score is a Log-Likelihood Ratio whose zero point corresponds to the Equal Error Rate (EER) on their evaluation datasets, with practical scores falling between -4.5 and +1.0. Producing an EER-calibrated threshold requires a held-out corpus with per-clip genuine-versus-replay ground truth, so the vendor necessarily maintains a labelled authenticity evaluation set. Content spans the acoustic dimensions named as the detection features — room reverberation, microphone quality, background noise and transmission characteristics — implying paired live-versus-replayed recordings of the same speakers across differing capture and transmission conditions. Part of a wider Deepfake Detection suite, so synthesis labels likely accompany replay labels

Open buyer room →
Phonexia/Phonexia
SampleCoverage

Sample

Brickroad customers

Sample this dataset before you buy it.

Your sourcing agent asks Phonexia and files the sample in your catalog — private to you.

Start 7-day trial→Nothing is charged until the trial ends.

Coverage

Universe, instruments and categories.

Industry
Application Software
Instruments
equities
Categories
AlternativeReference
Regions
USOther
Sample tickers
MSFTAAPLCRMNICETTEC
Dataset card
Type
not stated
Format
Audio (speech clips, live and replayed or synthetic, across varying capture devices, rooms and transmission channels) + Tabular metadata (LLR scores, speaker identity, attack-type label, channel and device provenance)
Volume
The authenticity evaluation corpus is not sized publicly, but computing an Equal Error Rate implies a substantial held-out labelled set rather than a handful of samples — realistically tens of thousands of paired live-and-attack clips across the four named nuisance dimensions to support a stable EER estimate. Phonexia's wider speech portfolio (speaker recognition, language and speaker identification, transcription across multiple languages) implies a far larger aggregate speech corpus than the authenticity slice alone. Request further research for corpus sizes and language coverage
Users
N/A — enterprise speech-technology vendor licensing SDKs and platform deployments, no registered consumer base; coverage is integrated enterprise deployments
History
12 years
Update frequency
not stated
Growth
Active (documentation versioned 2026.05.1 with current product releases; Replay Attack Detection flagged EXPERIMENTAL and under active development; wider Deepfake Detection suite maintained alongside)
Launched
~2013-2014 for the company and its speech-platform lineage (organisation record dates from 2014, and the funding record notes a merger/acquisition in its history); the Deepfake Detection and authenticity-verification line is considerably later, est. 2023-2026
Delivery
not stated
Entity mapping
not stated
Sample
not stated
Point-in-time
not stated
Licence
not stated

supplier index read from their site

Phonexia has not added their own details yet. Not yet on file:

  • Dataset
  • Data dictionary
  • Coverage
  • Provenance
  • Rights & data handling