…Engine 3.58.0, DB v1901, BSAPI 3.58.0 (2023-04-03) New: Added 6th generation models for STT and KWS UK_UA_6 (Ukrainian) SR_RS_6 (Serbian) New: Added VAD SID4_XL5 model, which detects speech/non-speech exactly the same way as SID4 XL5 model does Improved: Reduced memory consumption by tuning ONNX runtime parameters. Mostly visible when processing (many) long recordings in STT. Improved: SID4 comparator now returns…
Search: SID%20API
54 results
…wizard for creating SID calibration set [#5047] Added tracers to SID evaluation wizards which are synchronized across all graphs [#5112] Added FAR an FRR to tracer labels to Error rate and PDF plots in SID evaluation graphs [#5050] Presentation mode in graphs in SID evaluation [#5141] Added limitation of processing time or processed files in SID evaluation/calibration wizards [#5131] Calibration…
…by SPE users: rest_model_sid list of SID speaker models – name, owner (SPE user), modification timestamp rest_model_sid_sources list of files used as sources for SID speaker models creation rest_model_sid_metafiles list of files used as SID speaker models metafiles rest_group_sid list of SID speaker groups – name, owner (SPE user) rest_group_sid_models associations between SID speaker groups and speaker models rest_voiceprint SID…
…was detected with 8 SID4 instances using 8 physical CPU cores on a single CPU Under those conditions we can measure total system performance 1200 FTRT when single CPU is used CPU Hyper Threading feature doesn’t bring any performance improvement for SID4 The following data visualization shows performance of the Phonexia SID4 on specific CPU family and its type. Explanation…
…this Microsoft Excel sheet demonstrating the sigmoid function: Score-to-Confidence. SID evaluation Before implementing Speaker Identification, it’s important to evaluate its accuracy using real data from the production environment. To evaluate the SID system, you’ll need enough of labeled data, i.e. recordings with speaker labels. The principle of SID system evaluation is to compare (voiceprints of) all the individual recordings against…
…speaker voiceprints. In general, both sides (enroll and test) can be calibrated by either the same profile (in case they come from the same source) or by two different profiles in case they have a different source. Examples: We are selling SID to Wakanda’s Ministry of Defense. They like to monitor telephone network of their happy people speaking the Wakandan…
…SID4C (SID4 extractor and SID4 comparator) with both L4 and XL4 models, depending on actual availability of the technologies/models in that SPE installation. Due to the “…single character” pattern definition, the list won’t include SID4E_STREAM, SID4C_STREAM and SID4CALIB technologies. phxadmin2: example 3 ./phxadmin2 technology enable sid?_stream:*l?=3 sid4?_stream:*l?=1 enable 3 instances of technologies with names matching “sid followed by single character,…
…Diarization GID Gender Identification KWS Keyword Spotting KWS_STREAM Keyword Spotting Stream LIDC Language Identification Languageprint Comparator LIDE Language Identification Languageprint Extractor PHNREC Phoneme Recognition SID4C Speaker Identification 4 Voiceprint Comparator SID4C_STREAM Speaker Identification 4 Voiceprint Stream Comparator SID4CALIB Speaker Identification 4 VoicePrint Calibration SID4E Speaker Identification 4 Voiceprint Extractor SID4E_STREAM Speaker Identification 4 Voiceprint Stream Extractor SQE Speech Quality Estimation…
…name Release Date End of Support GID O1 / GENERIC AGE L1 S1 SID XL3 2015-11 5th gen. SID L3 2015-11 5th gen. SID L2 2012-11 4th gen. SID S2 2012-11 4th gen. SID LID L2 2012-11 4th gen. LID S2 2012-11 4th gen. LID …
…3 or 4 in the model name. Other technology models (SID, LID, GID, DIAR, AGE, SQE, VAD, DENOISE) Tech. models supported (generation specified by number in “Tech. model name”). Technology Tech. model name Released End of support Maintenance SID4 XL5 2022-09 6th gen. SID 5th gen. SID XL4 2020-03 6th gen. SID 5th gen. SID L4 2019-02 6th gen….
This part requires higher (and non-anonymous) access level.
How to solve this situation:
- Log in here if you are not logged in.
- Register here. It takes just a few clicks and it’s free.
…3.58.0) The SID4_XL5 model uses exactly the same parameters as internal VAD built-in in Speaker Identification 4 (SID4), giving exactly the same results (amount of speech, speech segments boundaries). This model should help preventing rare situations when analyzing a recording using VAD GENERIC_3 model detected just enough speech for a voiceprint, but actual voiceprint creation failed due to not enough…
…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…
For evaluating the real life scenario of Phonexia Speaker Identification technology, the system needs to be calibrated by SID dataset. SID dataset (minimum requirements): To measure SID performance precisely, it’s important to prepare evaluation recordings set very carefully. The requirements are: 50+ known speakers, 200+ recordings in total (i.e. 3 to 5 recordings per speaker*) 1+ minute of net speech…
This part requires higher (and non-anonymous) access level.
How to solve this situation:
- Log in here if you are not logged in.
- Register here. It takes just a few clicks and it’s free.