…BSAPI 3.60.1 (2024-01-17) Fixed: Docker image phonexia/spe:3.60-stt-en_us_6 does not start Fixed: Phoneme Recognizer does not work in STT EN_US_A model Fixed: Reading wave files in ieee_float format with out-of-range sample values, causing e.g. invalid voiceprints or “null” comparison scores Speech Engine 3.60.0, DB v1901, BSAPI 3.60.0 (2023-12-05) New: Added floating_window parameter to /technologies/speakerid4/input_stream and /technologies/speakerid4/input_stream/voiceprint endpoints, for using only last…
Search: speakerid
3 results
…normalization. The Audio Source Profile includes: a set of calibration voiceprints extracted from the source files NOTE: these voiceprints are not compatible with standard voiceprints created using the /technologies/speakerid4/extractvp REST API endpoint or the vpextract4 command-line tool! information about profile version, creation date and version of voiceprints hash of all data in the profile and hash of its parent profile…
…to download for commercial/research purposes under a Creative Commons 4.0 license. Data originates from OXFORD VGG VoxCeleb Dataset which detailed license can be found here. SpeakerID Example Data Set v1.0 83.89 MB Download Publications: S. Chung, A. Nagrani, A. Zisserman VoxCeleb2: Deep Speaker Recognition INTERSPEECH, 2018. Nagrani, J. S. Chung, A. Zisserman VoxCeleb: a large-scale speaker identification dataset INTERSPEECH, 2017….