AI engineering glossary · Generative media multimodal
What is speaker embedding?
Speaker embedding: A fixed-length vector that captures the characteristics of a person's voice, so recordings by the same speaker lie close together. Embeddings such as x-vectors serve speaker verification, diarisation and voice-cloning conditioning.
Speaker embedding: an example
Two clips of the same person give embeddings with cosine similarity 0.85, while clips of different people give about 0.2.
Related terms
More Generative media multimodal terms
- Spectrogram
- Speech-to-speech translation
- SSIM
- Stable Diffusion
- Streaming ASR
- StyleGAN
- Super-resolution
- Tacotron
Where you learn it
Speaker embedding is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.