LOGIN TO YOUR ACCOUNT

Username
Password
Remember Me
Or use your Academic/Social account:

CREATE AN ACCOUNT

Or use your Academic/Social account:

Congratulations!

You have just completed your registration at OpenAire.

Before you can login to the site, you will need to activate your account. An e-mail will be sent to you with the proper instructions.

Important!

Please note that this site is currently undergoing Beta testing.
Any new content you create is not guaranteed to be present to the final version of the site upon release.

Thank you for your patience,
OpenAire Dev Team.

Close This Message

CREATE AN ACCOUNT

Name:
Username:
Password:
Verify Password:
E-mail:
Verify E-mail:
*All Fields Are Required.
Please Verify You Are Human:
fbtwitterlinkedinvimeoflicker grey 14rssslideshare1
Heck, Michael; Sakti, Sakriani; Nakamura, Satoshi (2017)
Publisher: Zenodo
Type: dataset
Subjects: ComputingMethodologies_PATTERNRECOGNITION, zerospeech2017, dpgmm

This is the official submission of NAIST for track 1 of the zero resource speech challenge 2017 (ZeroSpeech2017).

Our system uses feature vector optimized DPGMM based clustering for unsupervised subword modeling. The general idea is to unsupervisedly learn frame-level class labels in a first run of DPGMM based clustering. These labels are then used to automatically learn speech feature transformations (LDA, MLLT, (basis) fMLLR) to improve discriminability and to reduce speaker variance. The optimized feature vectors are re-clustered and frame-wise posteriorgrams are extracted to serve as new speech representation.

The system also applies posteriorgram based model combination.

This pipeline is entirely unsupervised and only needs the raw audio recordings as input. No pre-defined segmentation, speaker IDs or other meta data is required.

The only parameter subject to tuning is the LDA output dimensionality, which in this case has been optimized on the development data sets (english, french, mandarin) and tested on the surprise language data sets (LANG1, LANG2).

Since the output is posteriorgrams, the ABX scoring needs to be done with the Kullback-Leibler (KL) divergence.

  • No related publications.
  • No related research data.

Share - Bookmark

Download from

Funded by projects

No projects found

Cite this research data

Collected from