1 |
Recovering capitalization and punctuation marks for automatic speech recognition: case study for Portuguese broadcast news
|
|
|
|
Abstract:
The following material presents a study about recovering punctuation marks, and capitalization information from European Portuguese broadcast news speech transcriptions. Different approaches were tested for capitalization, both generative and discriminative, using: finite state transducers automatically built from language models; and maximum entropy models. Several resources were used, including lexica, written newspaper corpora and speech transcriptions. Finite state transducers produced the best results for written newspaper corpora, but the maximum entropy approach also proved to be a good choice, suitable for the capitalization of speech transcriptions, and allowing straightforward on-the-fly capitalization. Evaluation results are presented both for written newspaper corpora and for broadcast news speech transcriptions. The frequency of each punctuation mark in BN speech transcriptions was analyzed for three different languages: English, Spanish and Portuguese. The punctuation task was performed using a maximum entropy modeling approach, which combines different types of information both lexical and acoustic. The contribution of each feature was analyzed individually and separated results for each focus condition are given, making it possible to analyze the performance differences between planned and spontaneous speech. All results were evaluated on speech transcriptions of a Portuguese broadcast news corpus. The benefits of enriching speech recognition with punctuation and capitalization are shown in an example, illustrating the effects of described experiments into spoken texts. ; info:eu-repo/semantics/acceptedVersion
|
|
Keyword:
Capitalization; Domínio/Área Científica::Ciências Agrárias::Outras Ciências Agrárias; Domínio/Área Científica::Ciências Naturais::Ciências da Computação e da Informação; Domínio/Área Científica::Ciências Naturais::Ciências Físicas; Language modeling; Maximum entropy; Punctuation recovery; Rich transcription; Sentence boundary detection; Truecasing; Weighted finite state transducers
|
|
URL: https://doi.org/10.1016/j.specom.2008.05.008 http://hdl.handle.net/10071/22063
|
|
BASE
|
|
Hide details
|
|
2 |
Strong Generative Capacity of Morphological Processes
|
|
|
|
In: Proceedings of the Society for Computation in Linguistics (2021)
|
|
BASE
|
|
Show details
|
|
3 |
Past, present and future: Computational approaches to mapping historical Irish cognate verb forms
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Decomposing phonological transformations in serial derivations
|
|
|
|
In: Proceedings of the Society for Computation in Linguistics (2018)
|
|
BASE
|
|
Show details
|
|
5 |
Named entity recognition within Arabic text and their semantic relations ; Extraction d'information à partir d'un texte arabe : extraction des entités nommées et leurs relations sémantiques
|
|
|
|
In: https://hal.archives-ouvertes.fr/tel-01716911 ; Intelligence artificielle [cs.AI]. Université Djillali Liabes de Sidi Bel Abbès, 2017. Français (2017)
|
|
BASE
|
|
Show details
|
|
6 |
Long-distance consonant agreement and subsequentiality
|
|
|
|
In: Glossa: a journal of general linguistics; Vol 2, No 1 (2017); 52 ; 2397-1835 (2017)
|
|
BASE
|
|
Show details
|
|
7 |
A Compact Representation of Pronunciation Lexicons Using Finite-state Super Transducers
|
|
|
|
In: Slovenščina 2.0: Empirične, aplikativne in interdisciplinarne raziskave, Vol 4, Iss 1, Pp 79-96 (2017) (2017)
|
|
BASE
|
|
Show details
|
|
8 |
A Semi-automatic and Low Cost Approach to Build Scalable Lemma-based Lexical Resources for Arabic Verbs
|
|
|
|
In: International Journal of Information Technology and Computer Science(IJITCS) ; https://hal.archives-ouvertes.fr/hal-01270974 ; International Journal of Information Technology and Computer Science(IJITCS), IJIT, 2016, 8 (2), pp.1-13 ; http://www.mecs-press.org/ijitcs/ijitcs-v8-n2/IJITCS-V8-N2-1.pdf (2016)
|
|
BASE
|
|
Show details
|
|
9 |
Phonétisation statistique adaptable d'énoncés pour le français
|
|
|
|
In: Journées d'Études sur la Parole ; https://hal.inria.fr/hal-01321358 ; Journées d'Études sur la Parole, Jul 2016, Paris, France (2016)
|
|
BASE
|
|
Show details
|
|
10 |
Evaluating the impact of using a domain-specific bilingual lexicon on the performance of a hybrid machine translation approach
|
|
|
|
In: 10th International Conference on Recent Advances in Natural Language Processing, RANLP 201 ; https://hal-cea.archives-ouvertes.fr/cea-01844051 ; 10th International Conference on Recent Advances in Natural Language Processing, RANLP 201, Sep 2015, Hissar, Bulgaria. pp.579-587 (2015)
|
|
BASE
|
|
Show details
|
|
11 |
Using finite-state transducers to build lexical resources for Unitex Arabic package
|
|
|
|
In: CEC-TAL ; https://hal.archives-ouvertes.fr/hal-01177017 ; CEC-TAL, Mar 2015, Sousse, Tunisia. pp.90-100 (2015)
|
|
BASE
|
|
Show details
|
|
12 |
Adaptive Statistical Utterance Phonetization for French
|
|
|
|
In: Proc. of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) ; https://hal.inria.fr/hal-01109757 ; Proc. of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Apr 2015, Brisbane, Australia. 5 p., 2 columns (2015)
|
|
BASE
|
|
Show details
|
|
13 |
Weighted tree automata and transducers for syntactic natural language processing ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Intersection of Multitape Transducers vs. Cascade of Binary Transducers: The Example of Egyptian Hieroglyphs Transliteration
|
|
|
|
In: FSMNLP - International Workshop on Finite State Methods and Natural Language Processing ; https://hal.inria.fr/hal-00660490 ; FSMNLP - International Workshop on Finite State Methods and Natural Language Processing, Jul 2011, Blois, France. pp.74--82 ; http://www.aclweb.org/anthology/W11-4410 (2011)
|
|
BASE
|
|
Show details
|
|
15 |
A weighted finite state transducer implementation of phoneme rewrite rules for English-to-Korean pronunciation conversion
|
|
|
|
In: Faculty Publications (2011)
|
|
BASE
|
|
Show details
|
|
16 |
GREAT: open source software for statistical machine translation
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Methods and Tools for Weak Problems of Translation ; Méthodes et outils pour les problèmes faibles de traduction
|
|
|
|
In: https://tel.archives-ouvertes.fr/tel-00502192 ; Computer Science [cs]. Université Joseph-Fourier - Grenoble I, 2010. English (2010)
|
|
BASE
|
|
Show details
|
|
18 |
Onoma: un conjugador de verbos y neologismos verbales ; Onoma: a conjugator tool for verbs and verb neologisms
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Boosting Robustness of a Named Entity Recognizer
|
|
|
|
In: EISSN: 1793-7108 ; International Journal of Semantic Computing ; https://hal.archives-ouvertes.fr/hal-00436301 ; International Journal of Semantic Computing, World Scientific, 2009, 3 (1), pp.1-14 (2009)
|
|
BASE
|
|
Show details
|
|
20 |
Recognition of Personal Names in Serbian Texts
|
|
|
|
In: International Conference Recent Advances in Natural Language Processing (RANLP'05) ; https://hal.archives-ouvertes.fr/hal-01108230 ; International Conference Recent Advances in Natural Language Processing (RANLP'05), 2005, Borovets, Bulgaria. pp.288-292 (2005)
|
|
BASE
|
|
Show details
|
|
|
|