Self-organized language modeling for speech recognition
Readings in speech recognition
Tagging English text with a probabilistic model
Computational Linguistics
TnT: a statistical part-of-speech tagger
ANLC '00 Proceedings of the sixth conference on Applied natural language processing
The LIMSI continuous speech dictation system
HLT '94 Proceedings of the workshop on Human Language Technology
Statistical Language Models for On-line Handwritten Sentence Recognition
ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
Unlimited vocabulary speech recognition for agglutinative languages
HLT-NAACL '06 Proceedings of the main conference on Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics
Multilingual stochastic n-gram class language models
ICASSP '96 Proceedings of the Acoustics, Speech, and Signal Processing, 1996. on Conference Proceedings., 1996 IEEE International Conference - Volume 01
Reshaping automatic speech transcripts for robust high-level spoken document analysis
AND '10 Proceedings of the fourth workshop on Analytics for noisy unstructured text data
Topic segmentation: application of mathematical morphology to textual data
ISMM'11 Proceedings of the 10th international conference on Mathematical morphology and its applications to image and signal processing
Automatic speech recognition for under-resourced languages: A survey
Speech Communication
| Hi-index | 0.01 |
Many automatic speech recognition (ASR) systems rely on the sole pronunciation dictionaries and language models to take into account information about language. Implicitly, morphology and syntax are to a certain extent embedded in the language models but the richness of such linguistic knowledge is not exploited. This paper studies the use of morpho-syntactic (MS) information in a post-processing stage of an ASR system, by reordering N-best lists. Each sentence hypothesis is first part-of-speech tagged. A morpho-syntactic score is computed over the tag sequence with a long-span language model and combined to the acoustic and word-level language model scores. This new sentence-level score is finally used to rescore N-best lists by reranking or consensus. Experiments on a French broadcast news task show that morpho-syntactic knowledge improves the word error rate and confidence measures. In particular, it was observed that the errors corrected are not only agreement errors and errors on short grammatical words but also other errors on lexical words where the hypothesized lemma was modified.