Problem-Agnostic Speech Embeddings for Multi-Speaker Text-to-Speech with SampleRNN

David Álvarez, Santiago Pascual, Antonio Bonafonte


Text-to-speech (TTS) acoustic models map linguistic features into an acoustic representation out of which an audible waveform is generated. The latest and most natural TTS systems build a direct mapping between linguistic and waveform domains, like SampleRNN. This way, possible signal naturalness losses are avoided as intermediate acoustic representations are discarded. Another important dimension of study apart from naturalness is their adaptability to generate voice from new speakers that were unseen during training. In this paper we first propose the use of problem-agnostic speech embeddings in a multi-speaker acoustic model for TTS based on SampleRNN. This way, we feed the acoustic model with speaker acousticallydependent representations that enrich the waveform generation more than embeddings unrelated to these factors. Our first results suggest that the proposed embeddings lead to better quality voices than those obtained with one-hot embeddings. Furthermore, as we can use any speech segment as an encoded representation during inference, the model is capable to generalize to new speaker identities without retraining the network. We finally show that, with a small increase of speech duration in the embedding extractor, we dramatically reduce the spectral distortion to close the gap towards the target identities.


 DOI: 10.21437/SSW.2019-7

Cite as: Álvarez, D., Pascual, S., Bonafonte, A. (2019) Problem-Agnostic Speech Embeddings for Multi-Speaker Text-to-Speech with SampleRNN. Proc. 10th ISCA Speech Synthesis Workshop, 35-39, DOI: 10.21437/SSW.2019-7.


@inproceedings{Álvarez2019,
  author={David  Álvarez and Santiago  Pascual and Antonio  Bonafonte},
  title={{Problem-Agnostic Speech Embeddings for Multi-Speaker Text-to-Speech with SampleRNN}},
  year=2019,
  booktitle={Proc. 10th ISCA Speech Synthesis Workshop},
  pages={35--39},
  doi={10.21437/SSW.2019-7},
  url={http://dx.doi.org/10.21437/SSW.2019-7}
}