Parameter optimization for iterative confusion network decoding in weather-domain speech recognition
Abstract
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 N-best list extraction method. The experiments are done over weather forecast domain data that has been provided in the framework of EUBRIDGE project.- Anthology ID:
- 2013.iwslt-papers.19
- Volume:
- Proceedings of the 10th International Workshop on Spoken Language Translation: Papers
- Month:
- December 5-6
- Year:
- 2013
- Address:
- Heidelberg, Germany
- Editor:
- Joy Ying Zhang
- Venue:
- IWSLT
- SIG:
- SIGSLT
- Publisher:
- Note:
- Pages:
- Language:
- URL:
- https://preview.aclanthology.org/add_missing_videos/2013.iwslt-papers.19/
- DOI:
- Cite (ACL):
- Shahab Jalalvand and Daniele Falavigna. 2013. Parameter optimization for iterative confusion network decoding in weather-domain speech recognition. In Proceedings of the 10th International Workshop on Spoken Language Translation: Papers, Heidelberg, Germany.
- Cite (Informal):
- Parameter optimization for iterative confusion network decoding in weather-domain speech recognition (Jalalvand & Falavigna, IWSLT 2013)
- PDF:
- https://preview.aclanthology.org/add_missing_videos/2013.iwslt-papers.19.pdf