Completely Unsupervised Phoneme Recognition by Adversarially Learning Mapping Relationships from Audio Embeddings

@inproceedings{Liu2018CompletelyUP,
  title={Completely Unsupervised Phoneme Recognition by Adversarially Learning Mapping Relationships from Audio Embeddings},
  author={Darong Liu and Kuan-Yu Chen and Hung-yi Lee and L. Lee},
  booktitle={INTERSPEECH},
  year={2018}
}
  • Darong Liu, Kuan-Yu Chen, +1 author L. Lee
  • Published in INTERSPEECH 2018
  • Computer Science
Unsupervised discovery of acoustic tokens from audio corpora without annotation and learning vector representations for these tokens have been widely studied. Although these techniques have been shown successful in some applications such as query-by-example Spoken Term Detection (STD), the lack of mapping relationships between these discovered tokens and real phonemes have limited the down-stream applications. This paper represents probably the first attempt towards the goal of completely… Expand
15 Citations
A Study of Inductive Biases for Unsupervised Speech Representation Learning
  • Gilles Boulianne
  • Computer Science
  • IEEE/ACM Transactions on Audio, Speech, and Language Processing
  • 2020
  • 2
Unsupervised Spoken Term Discovery on Untranscribed Speech
  • PDF
Unsupervised Speech Recognition via Segmental Empirical Output Distribution Matching
  • 12
  • Highly Influenced
  • PDF
Unsupervised speech representation learning
  • 2
  • PDF
Exploiting Cross-Lingual Knowledge in Unsupervised Acoustic Modeling for Low-Resource Languages
  • PDF
Almost Unsupervised Text to Speech and Automatic Speech Recognition
  • 36
  • Highly Influenced
  • PDF
...
1
2
...

References

SHOWING 1-10 OF 36 REFERENCES
Unsupervised Iterative Deep Learning of Speech Features and Acoustic Tokens with Applications to Spoken Term Detection
  • 6
  • PDF
Unsupervised Discovery of Structured Acoustic Tokens With Applications to Spoken Term Detection
  • Cheng-Tao Chung, L. Lee
  • Computer Science
  • IEEE/ACM Transactions on Audio, Speech, and Language Processing
  • 2018
  • 3
  • PDF
Fixed-dimensional acoustic embeddings of variable-length segments in low-resource settings
  • 93
  • PDF
Segmental Audio Word2Vec: Representing Utterances as Sequences of Vectors with Applications in Spoken Term Detection
  • Y. Wang, Hung-yi Lee, L. Lee
  • Computer Science
  • 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2018
  • 34
  • PDF
Language Transfer of Audio Word2Vec: Learning Audio Segment Representations Without Target Language Data
  • 5
  • PDF
Exploiting Discriminative Point Process Models for Spoken Term Detection
  • 18
  • PDF
A segmental framework for fully-unsupervised large-vocabulary speech recognition
  • 67
  • PDF
An acoustic segment modeling approach to query-by-example spoken term detection
  • 61
  • PDF
Deep convolutional acoustic word embeddings using word-pair side information
  • 128
  • PDF
...
1
2
3
4
...