Atts2s-vc: Sequence-to-sequence Voice Conversion With Attention And Context Preservation Mechanisms | Awesome LLM Papers Contribute to Awesome LLM Papers

Awesome LLM Papers

A curated collection of research papers on Large Language Models (LLMs), transformers, prompting, fine-tuning, and multi-modal systems. Maintained by Sean Moran.

Contact Sean Moran about this survey or website. Made with Jekyll and Hyde.

Atts2s-vc: Sequence-to-sequence Voice Conversion With Attention And Context Preservation Mechanisms

Kou Tanaka, Hirokazu Kameoka, Takuhiro Kaneko, Nobukatsu Hojo . ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2019 – 105 citations

[Paper]   Search on Google Scholar   Search on Semantic Scholar
ICASSP Time Series Tools Training Techniques

This paper describes a method based on a sequence-to-sequence learning (Seq2Seq) with attention and context preservation mechanism for voice conversion (VC) tasks. Seq2Seq has been outstanding at numerous tasks involving sequence modeling such as speech synthesis and recognition, machine translation, and image captioning. In contrast to current VC techniques, our method 1) stabilizes and accelerates the training procedure by considering guided attention and proposed context preservation losses, 2) allows not only spectral envelopes but also fundamental frequency contours and durations of speech to be converted, 3) requires no context information such as phoneme labels, and 4) requires no time-aligned source and target speech data in advance. In our experiment, the proposed VC framework can be trained in only one day, using only one GPU of an NVIDIA Tesla K80, while the quality of the synthesized speech is higher than that of speech converted by Gaussian mixture model-based VC and is comparable to that of speech generated by recurrent neural network-based text-to-speech synthesis, which can be regarded as an upper limit on VC performance.

Similar Work