Most previous work on trainable language generation has focused on two paradigms: (a) using a statistical model to rank a set of generated utterances, or (b) using statistics to i...
This paper introduces a new neural network language model (NNLM) based on word clustering to structure the output vocabulary: Structured Output Layer NNLM. This model is able to h...
Hai Son Le, Ilya Oparin, Alexandre Allauzen, Jean-...
This paper investigates unsupervised vocabulary and language model self-adaptation (VLA) from just one speech file using the web as a knowledge source and without prior knowledge...
We describe the use of meeting metadata, acquired using a computerized meeting organization and note-taking system, to improve automatic transcription of meetings. By applying a t...
Abstract. Test processes in the automotive industry are tool-intensive and affected by technologically heterogeneous test infrastructures. In the industrial practice a product has ...
Juergen Grossmann, Ines Fey, Alexander Krupp, Mirk...