Robust Speech Processing using Observation Uncertainty and Uncertainty Propagation

Special Session at Interspeech 2015, 6-10 September in Dresden, *Deadline 20 March*

We are pleased to announce a special session at Interspeech 2015 focusing on uncertainty for robust speech processing across all sub-fields. This would cover

• Methods exploiting observation and parameter uncertainty as well as uncertainty propagation for robust speech processing e.g. for inference, learning or adaptation

• Especially welcome are papers on the topic deep learning and uncertainty. We are confident this is the right moment to tackle this issue and already expect works on the topic

• All sub-fields are wellcome. Not only ASR and speaker recognition communities but also exploratory works on e.g. paralinguistics or transcription level uncertainties (lattices).

In order to motivate exploratory ideas, and facilitate research we will provide the following tools to those interested in participating:

• Feature extractors for different types of uncertainties (Wiener posterior, sparsity assumption, Supergaussian) compatible with HTK and Kaldi in Matlab

• Patches for uncertainty decoding and modified imputation in HTK, thus allowing to use uncertainties in the existing recipes.

• Patches to read Matlab produced DNN posteriors with Kaldi, thus allowing to implement uncertainty techniques based on DNNs in Matlab.

The use of these tools is *not* obligatory. They are just provided for those interested.

Ramón Fernandez Astudillo (ramon.astudillo@inesc-id.pt), Shinji Watanabe (watanabe@merl.com), Ahmed Hussen AbdelAziz (Ahmed.HussenAbdelAziz@rub.de), Dorothea Kolossa (dorothea.kolossa@rub.de)