I-Vector Estimation Using Informative Priors for Adaptation of Deep Neural Networks
MetadataShow full item record
Karanasou, P., Gales, M., & Woodland, P. (2015). I-Vector Estimation Using Informative Priors for Adaptation of Deep Neural Networks. Interspeech, 2872-2876. http://www.isca-speech.org/archive/interspeech_2015/i15_2872.html
This is the author accepted manuscript. The final version is available from ISCA via http://www.isca-speech.org/archive/interspeech_2015/i15_2872.html Supporting data for this paper is available at the http://www.repository.cam.ac.uk/handle/1810/248387 data repository.
I-vectors are a well-known low-dimensional representation of speaker space and are becoming increasingly popular in adaptation of state-of-the-art deep neural network (DNN) acoustic models. One advantage of i-vectors is that they can be used with very little data, for example a single utterance. However, to improve robustness of the i-vector estimates with limited data, a prior is often used. Traditionally, a standard normal prior is applied to i-vectors, which is nevertheless not well suited to the increased variability of short utterances. This paper proposes a more informative prior, derived from the training data. As well as aiming to reduce the non-Gaussian behaviour of the i-vector space, it allows prior information at different levels, for example gender, to be used. Experiments on a US English Broadcast News (BN) transcription task for speaker and utterance i-vector adaptation show that more informative priors reduce the sensitivity to the quantity of data used to estimate the i-vector. The best configuration for this task was utterance-level test i-vectors enhanced with informative priors which gave a 13% relative reduction in word error rate over the baseline (no i-vectors) and a 5% over utterance-level test i-vectors with standard prior.
i-vectors, speaker adaptation, prior information, deep neural networks
This work was supported by EPSRC Programme Grant EP/I031022/1 (Natural Speech Technology).
This record's URL: https://www.repository.cam.ac.uk/handle/1810/250523
Attribution-NonCommercial 2.0 UK: England & Wales
Licence URL: http://creativecommons.org/licenses/by-nc/2.0/uk/
Recommended or similar items
The following licence files are associated with this item: