zabir-nabil / awesome-speaker-recognition-verification

A curated list of awesome speaker recognition/verification papers, projects, datasets, and competition.

A curated list of awesome speaker recognition/verification/identification papers, projects, datasets, and competition.

Table of Contents

• Books

• Videos and Lectures

• Tutorials

• Papers with Code

• Pretrained models/embeddings

• Papers

• Github Repositories

• Datasets

• Conferences

• Competitions

• Frameworks

• Tools

• Miscellaneous

• Contributing

Books

1. Fundamentals of Speaker Recognition by Beigi, Homayoon
2. Machine Learning for Speaker Recognition by Jen-Tzung Chien and Man-Wai Mak

Videos and Lectures

1. Speaker Verification - The present and future of voiceprint based security By Professor Eliathamby Ambikairajah
2. Identify Speaker Voice Machine learning model Neural Networks in Keras/TensorFlow
3. X-vectors: Robust DNN embeddings for speaker recognition
4. A brief Introduction to SincNet

Papers with Code

1. https://paperswithcode.com/task/speaker-recognition
2. https://paperswithcode.com/task/speaker-verification

Papers

1. SPEECH AND SPEAKER RECOGNITION FROM RAW WAVEFORM WITH SINCNET (CNN, speech + speaker)
2. Deep Neural Network Embeddings for Text-Independent Speaker Verification (x-vector)
3. How to train your speaker embeddings extractor (VAD + speaker embeddings)

Github Repositories

1. https://github.com/WeidiXie/VGG-Speaker-Recognition (python 2 + tensorflow 1.x)
2. https://github.com/zabir-nabil/tf2-speaker-recognition (python 3 + tensorflow 2.x)
3. https://github.com/mravanelli/SincNet (python 3 + pytorch)

Pretrained models/embeddings

1. deep-speaker [softmax + triplet works best, clean audio]
2. meta-SR [pytorch, short utterances]

Datasets

1. VoxCeleb mirror
2. CN-Celeb
3. ST Chinese Mandarin Corpus
4. AIF [not public]
5. MLS [big + multi-lingual]

Conferences

1. ICASSP - IEEE International Conference on Acoustics, Speech and Signal Processing

Competitions

1. AIF [not public]
2. SdSV Challenge
3. VoxSRC
4. NIST SRE

Frameworks

1. speechbrain

Tools

1. Kaldi Speech Recognition Toolkit - Extraction of x vector
2. PLDA/LDA from enrollment using Kaldi - PLDA scoring
3. Neural PLDA - Neural PLDA, kaldi

Miscellaneous

1. Awesome speaker recognition

---

Contributing

Have anything in mind that you think is awesome and would fit in this list? Feel free to send a pull request.

---

License

To the extent possible under law, Zabir Al Nazi has waived all copyright and related or neighboring rights to this work.