|
2 years ago | |
---|---|---|
.. | ||
conf | 2 years ago | |
local | 2 years ago | |
.gitignore | 3 years ago | |
README.md | 2 years ago | |
path.sh | 3 years ago | |
run.sh | 2 years ago | |
utils | 3 years ago |
README.md
Speaker Diarization on AMI corpus
About the AMI corpus:
"The AMI Meeting Corpus consists of 100 hours of meeting recordings. The recordings use a range of signals synchronized to a common timeline. These include close-talking and far-field microphones, individual and room-view video cameras, and output from a slide projector and an electronic whiteboard. During the meetings, the participants also have unsynchronized pens available to them that record what is written. The meetings were recorded in English using three different rooms with different acoustic properties, and include mostly non-native speakers." See ami overview for more details.
About the example
The script performs diarization using x-vectors(TDNN,ECAPA-TDNN) on the AMI mix-headset data. We demonstrate the use of different clustering methods: AHC, spectral.
How to Run
prepare annotations and audios
Download AMI corpus, You need around 10GB of free space to get whole data The signals are too large to package in this way, so you need to use the chooser to indicate which ones you wish to download
## download annotations
wget http://groups.inf.ed.ac.uk/ami/AMICorpusAnnotations/ami_public_manual_1.6.2.zip && unzip ami_public_manual_1.6.2.zip
then please follow https://groups.inf.ed.ac.uk/ami/download/ to download the Signals:
- Select one or more AMI meetings: the IDs please follow ./ami_split.py
- Select media streams: Just select Headset mix
start running
Use the following command to run diarization on AMI corpus.
./run.sh --data_folder ./amicorpus --manual_annot_folder ./ami_public_manual_1.6.2
Best performance in terms of Diarization Error Rate (DER).
System | Mic. | Orcl. (Dev) | Orcl. (Eval) | Est. (Dev) | Est. (Eval) |
---|---|---|---|---|---|
ECAPA-TDNN + SC | HeadsetMix | 1.54 % | 3.07 % | 1.56 % | 3.28 % |