Sequence-to-Sequence Autoencoder (SA)

Theano implementation of the SA model proposed in Audio Word2Vec: Unsupervised Learning of Audio Segment Representations using Sequence-to-Sequence Autoencoder, in Proceedings of the 17th Annual Conference of the International Speech Communication Association (INTERSPEECH), 2016.

If you use the code, please cite the paper as:

@inproceedings{chung2016audio2vec,
  title     = {Audio word2vec: Unsupervised learning of audio segment representations using sequence-to-sequence autoencoder},
  author    = {Chung, Yu-An and Wu, Chao-Chung and Shen, Chia-Hao and Lee, Hung-Yi and Lee, Lin-Shan},
  booktitle = {INTERSPEECH},
  year      = {2016}
}