Automatic language identification with recurrent neural networks

Braun, Jerome; Levkowitz, Haim

doi:10.1109/ijcnn.1998.687199

Cited by 5 publications

(4 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A study was carried out by Braun et al [19] for LID concerning three different languages: English, German, and Mandarin. they relied on several feature extraction techniques such as RASTA, Spectral, and Cepstral.…”

Section: B Language Identificationmentioning

confidence: 99%

Spoken Arabic dialects identification: The case of Egyptian and Jordanian dialects

Al‐Ayyoub

Rihani

Dalgamoni

et al. 2014

2014 5th International Conference on Information and Communication Systems (ICICS)

View full text Add to dashboard Cite

Language identification systems have been the subject of extensive research efforts since the 1970's. Dialect identification is a natural extension of such systems. Most of the current systems do not consider the Arabic language and its dialects despite its immense importance. This paper addresses the problem of Arabic dialects identification. To the best of our knowledge, this is the first attempt to address this specific problem. Due to the lack of existing datasets, we collect our own dataset. To avoid collecting a prohibitively large dataset for the dozens of existing Arabic dialects, we focus on two specific dialects, viz. the Jordanian dialect and the Egyptian dialect. Several audio processing techniques (for feature extraction) and classifiers are tested to determine which combination of features/classifier generates the best results. Surprisingly, the results are very good.

show abstract

Section: B Language Identificationmentioning

confidence: 99%

Spoken Arabic dialects identification: The case of Egyptian and Jordanian dialects

Al‐Ayyoub

Rihani

Dalgamoni

et al. 2014

2014 5th International Conference on Information and Communication Systems (ICICS)

View full text Add to dashboard Cite

show abstract

“…Dialect recognition can be performed on various levels, such as acoustic (e.g., spectral data), prosodic, phonotactical (e.g., language models) and lexical [21]. With regards to acoustic level, the spectral information of the speech signal is extracted through speech parameterization methods, and classification algorithms are then applied, such as a Gaussian mixture model [6], support vector model [22], and neural networks [23]. In [24], an acoustic approach is presented to recognize the four languages of India: Indian, English, Hindi, Assamese, Bengali.…”

Section: Dialect Recognitionmentioning

confidence: 99%

Dialects Recognition Based on Acoustic Model

İmamverdiyev¹,

Sukhostat²

2016

JPIT

View full text Add to dashboard Cite

Regional dialect recognition is important in the field of speech technologies. It is widely used in telephone reference systems, adapting the output synthesized speech in dialog systems, and also in forensics for profiling speaker in judicial or military situations, etc. The article describes different approaches that allow the usage of multiple information sources from the acoustic signal for the construction of dialects recognition system. In particular, acoustic, prosodic, phonetic, and phonotactic approaches are considered.

show abstract

“…Thomas [46] has shown that a languagedependent lexicon need not be available in advance; rather, it can be learned automatically from the training data. Ramesh [39], Matrouf [29], Lund [28,27] and Braun [3] have all proposed similar systems.…”

Section: Word Level Approachesmentioning

confidence: 99%