speechbrainteam commited on
Commit
5a9f979
1 Parent(s): f403b5f

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +84 -0
README.md ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: "en"
3
+ thumbnail:
4
+ tags:
5
+ - embeddings
6
+ - Speaker
7
+ - Verification
8
+ - Identification
9
+ - pytorch
10
+ - xvectors
11
+ - TDNN
12
+ license: "apache-2.0"
13
+ datasets:
14
+ - voxceleb
15
+ metrics:
16
+ - EER
17
+ - min_dct
18
+ ---
19
+
20
+ # Speaker Verification with xvector embeddings on Voxceleb
21
+
22
+ This repository provides all the necessary tools to extract speaker embeddings with a pretrained TDNN model using SpeechBrain.
23
+ The system is trained on Voxceleb 1+ Voxceleb2 training data.
24
+
25
+ For a better experience, we encourage you to learn more about
26
+ [SpeechBrain](https://speechbrain.github.io). The given ASR model performance on Voxceleb1-test set are:
27
+
28
+ | Release | EER(%) | minDCF |
29
+ |:-------------:|:--------------:|:--------------:|
30
+ | 05-03-21 | -.- | -.- |
31
+
32
+
33
+ ## Pipeline description
34
+ This system is composed of a TDNN model coupled with statistical pooling. The system is trained with Categorical Cross-Entropy Loss.
35
+
36
+ ## Install SpeechBrain
37
+
38
+ First of all, please install SpeechBrain with the following command:
39
+
40
+ ```
41
+ pip install \\we hide ! SpeechBrain is still private :p
42
+ ```
43
+
44
+ Please notice that we encourage you to read our tutorials and learn more about
45
+ [SpeechBrain](https://speechbrain.github.io).
46
+
47
+ ### Compute your speaker embeddings
48
+
49
+ ```python
50
+ import torchaudio
51
+ from speechbrain.pretrained import SpeakerRecognition
52
+ verification = SpeakerRecognition.from_hparams(source="speechbrain/spkrec-xvect-voxceleb")
53
+ signal, fs =torchaudio.load('samples/audio_samples/example1.wav')
54
+ embeddings = verification.encode(signal)
55
+ ```
56
+
57
+ #### Referencing xvectors
58
+ ```@inproceedings{DBLP:conf/odyssey/SnyderGMSPK18,
59
+ author = {David Snyder and
60
+ Daniel Garcia{-}Romero and
61
+ Alan McCree and
62
+ Gregory Sell and
63
+ Daniel Povey and
64
+ Sanjeev Khudanpur},
65
+ title = {Spoken Language Recognition using X-vectors},
66
+ booktitle = {Odyssey 2018},
67
+ pages = {105--111},
68
+ year = {2018},
69
+ }
70
+ ```
71
+
72
+
73
+ #### Referencing SpeechBrain
74
+
75
+ ```
76
+ @misc{SB2021,
77
+ author = {Ravanelli, Mirco and Parcollet, Titouan and Rouhe, Aku and Plantinga, Peter and Rastorgueva, Elena and Lugosch, Loren and Dawalatabad, Nauman and Ju-Chieh, Chou and Heba, Abdel and Grondin, Francois and Aris, William and Liao, Chien-Feng and Cornell, Samuele and Yeh, Sung-Lin and Na, Hwidong and Gao, Yan and Fu, Szu-Wei and Subakan, Cem and De Mori, Renato and Bengio, Yoshua },
78
+ title = {SpeechBrain},
79
+ year = {2021},
80
+ publisher = {GitHub},
81
+ journal = {GitHub repository},
82
+ howpublished = {\url{https://github.com/speechbrain/speechbrain}},
83
+ }
84
+ ```