Unsupervised Learning of Disentangled Speech Content and Style Representation
This work addresses the challenge of separating speech content from speaker style for applications like speaker recognition, but it is incremental as it builds on existing disentanglement methods.
The paper tackles the problem of unsupervised learning of speech representations by disentangling content and style, achieving low word error rates for content recognition and high speaker identity accuracy with minimal labeled data.
We present an approach for unsupervised learning of speech representation disentangling contents and styles. Our model consists of: (1) a local encoder that captures per-frame information; (2) a global encoder that captures per-utterance information; and (3) a conditional decoder that reconstructs speech given local and global latent variables. Our experiments show that (1) the local latent variables encode speech contents, as reconstructed speech can be recognized by ASR with low word error rates (WER), even with a different global encoding; (2) the global latent variables encode speaker style, as reconstructed speech shares speaker identity with the source utterance of the global encoding. Additionally, we demonstrate an useful application from our pre-trained model, where we can train a speaker recognition model from the global latent variables and achieve high accuracy by fine-tuning with as few data as one label per speaker.