Audio Indexing of Arabic broadcast news

Billa, Jayadev; Noamany, Mohamed; Srivastava, Amit; Liu, D.; Stone, Rebecca; Xu, Jun; Makhoul, John; Kubala, Francis

doi:10.1109/icassp.2002.5743640

Cited by 33 publications

(37 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All popcomp has to do is to compare the two positions in the corpus. 1 The make_kbest_suf program below is similar to the make_standard_suf program above except we now sort by the two orders at alternating depths in the tree. First we sort lexicographically and then we sort by popularity and so on, using a construction similar to KD-Trees (Bentley, 1975).…”

Section: K-best Suffix Arraysmentioning

confidence: 99%

“…The code below is simple to describe (though there are more efficient implementations that avoid unnecessary qsorts). int* make_kbest_suf () { int N = strlen(corpus); int* suf = (int*)malloc(N * sizeof(int)); 1 With a little extra book keeping, one can keep a table on the side that makes it possible to map back and forth between popularity rank and the actual popularity. This turns out to be useful for some applications.…”

Section: K-best Suffix Arraysmentioning

confidence: 99%

“…We simulate on the word level because generating student's dialog acts alone does not provide sufficient information for 1 Kappa of 0.79 is gained comparing to human judgements. 2 Kappa of 0.68 is gained in a preliminary agreement study.…”

Section: Simulation Modelsmentioning

confidence: 99%

See 2 more Smart Citations

Automatic acquisition of grammatical types for nouns

Bel

Espeja

Marimon

2007

Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics

View full text Add to dashboard Cite

The work 1 we present here is concerned with the acquisition of deep grammatical information for nouns in Spanish. The aim is to build a learner that can handle noise, but, more interestingly, that is able to overcome the problem of sparse data, especially important in the case of nouns. We have based our work on two main points. Firstly, we have used distributional evidences as features. Secondly, we made the learner deal with all occurrences of a word as a single complex unit. The obtained results show that grammatical features of nouns is a level of generalization that can be successfully approached with a Decision Tree learner.

show abstract

Section: K-best Suffix Arraysmentioning

confidence: 99%

Section: K-best Suffix Arraysmentioning

confidence: 99%

See 1 more Smart Citation

Automatic acquisition of grammatical types for nouns

Bel

Espeja

Marimon

2007

Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics

View full text Add to dashboard Cite

show abstract

“…Final system has been built using a lexicon which contains 10,130 unique grapheme words. As in [12], [11], we used grapheme as modeling unit to create our own lexicon because. An example of its content obtained after text pre-processing is shown in Table IV.…”

Section: Tonal Vowels Normalizatiońmentioning

confidence: 99%

First Automatic Fongbe Continuous Speech Recognition System: Development of Acoustic Models and Language Models

Laleye¹,

Besacier²,

Ezin³

et al. 2016

Annals of Computer Science and Information Systems

View full text Add to dashboard Cite

Abstract-This paper reports our efforts toward an ASR system for a new under-resourced language (Fongbe). The aim of this work is to build acoustic models and language models for continuous speech decoding in Fongbe. The problem encountered with Fongbe (an African language spoken especially in Benin, Togo, and Nigeria) is that it does not have any language resources for an ASR system. As part of this work, we have first collected Fongbe text and speech corpora that are described in the following sections. Acoustic modeling has been worked out at a graphemic level and language modeling has provided two language models for performance comparison purposes. We also performed a vowel simplification by removing tones diacritics in order to investigate their impact on the language models.

show abstract

“…A "machine translation" system is trained based on an initial phonetic dictionary and afterwards this system can be used to convert any other word to its phonetic form. Finally, another approach, to generate a pronunciation dictionary for ASR, consists in simply modeling graphemes instead of phonemes [38,39]. The "phonetic transcription" of the word is, in fact, its written form.…”

Section: Grapheme-to-phoneme Conversion For Romanianmentioning

confidence: 99%

SMT-based ASR domain adaptation methods for under-resourced languages: Application to Romanian

Cucu

Buzo

Besacier

et al. 2014

Speech Communication

View full text Add to dashboard Cite

This study investigates the possibility of using statistical machine translation to create domainspecific language resources. We propose a methodology that aims to create a domain-specific automatic speech recognition (ASR) system for a low-resourced language when in-domain text corpora are available only in a high-resourced language. Several translation scenarios (both unsupervised and semi-supervised) are used to obtain domain-specific textual data. Moreover this paper shows that a small amount of manually post-edited text is enough to develop other natural language processing systems that, in turn, can be used to automatically improve the machine translated text, leading to a significant boost in ASR performance. An in-depth analysis, to explain why and how the machine translated text improves the performance of the domain-specific ASR, is also made at the end of this paper. As bi-products of this core domainadaptation methodology, this paper also presents the first large vocabulary continuous speech recognition system for Romanian, and introduces a diacritics restoration module to process the Romanian text corpora, as well as an automatic phonetization module needed to extend the Romanian pronunciation dictionary.

show abstract

Audio Indexing of Arabic broadcast news

Cited by 33 publications

References 4 publications

Automatic acquisition of grammatical types for nouns

Automatic acquisition of grammatical types for nouns

First Automatic Fongbe Continuous Speech Recognition System: Development of Acoustic Models and Language Models

SMT-based ASR domain adaptation methods for under-resourced languages: Application to Romanian

Contact Info

Product

Resources

About