Wespeaker: A Research and Production Oriented Speaker Embedding Learning Toolkit

By Hongji Wang, Che-Yuan Liang, Shuai Wang, Zhengyang Chen, Binbin Zhang, Xu Xiang, Yan Deng, Yanmin Qian. 2022

247 citations recorded by the source corpus.

Speaker modeling is essential for many related tasks, such as speaker recognition and speaker diarization. The dominant modeling approach is fixed-dimensional vector representation, i.e., speaker embedding. This paper introduces a research and production oriented speaker embedding learning toolkit, Wespeaker. Wespeaker contains the implementation of scalable data management, state-of-the-art speaker embedding models, loss functions, and scoring back-ends, with highly competitive results achieved by structured recipes which were adopted in the winning systems in several speaker verification challenges. The application to other downstream tasks such as speaker diarization is also exhibited in the related recipe. Moreover, CPU- and GPU-compatible deployment codes are integrated for production-oriented development. The toolkit is publicly available at https://github.com/wenet-e2e/wespeaker.

Subfields: Artificial Intelligence, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Chutong Meng
2. Zhichao Huang
3. Tom Ko
4. Daniel Povey
5. Sanjeev Khudanpur
6. Shinji Watanabe

In Signal Processing

1. Chutong Meng
2. Zhichao Huang
3. Tom Ko
4. Daniel Povey
5. Sanjeev Khudanpur

Citations in the corpus

• RepCodec: A Speech Representation Codec for Speech Tokenization (2023, background): “The Speaker Similarity follows Wang et al. (2023b) and calculates the cosine similarity between the speaker embedding.”