Parameter Optimization for Iterative Confusion Network Decoding in Weather-Domain Speech Recognition  

Oleh:

Jalalvand, Shahab ; Falavigna, Daniele

Jenis: Article from Proceeding
Dalam koleksi: Proceedings of the 10th International Workshop on Spoken Language Translation (IWSLT 2013), Heidelberg, Germany: Dec. 5-6, 2013
Topik: automatic speech recognition; language model; neural network; confusion network; minimum error rate training
Fulltext: Parameter Optimization.pdf (11.78MB)

Isi artikel

In this paper, we apply a set of approaches to, efficiently, rescore the output of the automatic speech recognition over weather-domain data. Since the in-domain data is usually insufficient for training an accurate language model (LM) we utilize an automatic selection method to extract domain-related sentences from a general text resource. Then, an N-gram language model is trained on this set. We exploit this LM, along with a pre-trained acoustic model for recognition of the development and test instances. The recognizer generates a confusion network (CN) for each instance. Afterwards, we make use of the recurrent neural network language model (RNNLM), trained on the in-domain data, in order to iteratively rescore the CNs. Rescoring the CNs, in this way, requires estimating the weights of the RNNLM, N-gramLM and acoustic model scores. Weights optimization is the critical part of this work, whereby, we propose using the minimum error rate training (MERT) algorithm along with a novel Nbest list extraction method. The experiments are done over weather forecast domain data that has been provided in the framework of EUBRIDGE project.

Opini Anda

Klik untuk menuliskan opini Anda tentang koleksi ini!

Kembali