21 |
Automatic Dialect Detection in Arabic Broadcast Speech ...
|
|
|
|
Abstract:
We investigate different approaches for dialect identification in Arabic broadcast speech, using phonetic, lexical features obtained from a speech recognition system, and acoustic features using the i-vector framework. We studied both generative and discriminate classifiers, and we combined these features using a multi-class Support Vector Machine (SVM). We validated our results on an Arabic/English language identification task, with an accuracy of 100%. We used these features in a binary classifier to discriminate between Modern Standard Arabic (MSA) and Dialectal Arabic, with an accuracy of 100%. We further report results using the proposed method to discriminate between the five most widely used dialects of Arabic: namely Egyptian, Gulf, Levantine, North African, and MSA, with an accuracy of 52%. We discuss dialect identification errors in the context of dialect code-switching between Dialectal Arabic and MSA, and compare the error pattern between manually labeled data, and the output from our classifier. ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://arxiv.org/abs/1509.06928 https://dx.doi.org/10.48550/arxiv.1509.06928
|
|
BASE
|
|
Hide details
|
|
22 |
Incorporating Lexical and Prosodic Information at Different Levels for Meeting Summarization ...
|
|
|
|
BASE
|
|
Show details
|
|
24 |
Recording speech articulation in dialogue: Evaluating a synchronized double Electromagnetic Articulography setup
|
|
|
|
BASE
|
|
Show details
|
|
25 |
Toward summarization of communicative activities in spoken conversation
|
|
|
|
BASE
|
|
Show details
|
|
26 |
Cross-lingual automatic speech recognition using tandem features
|
|
|
|
BASE
|
|
Show details
|
|
27 |
Ageing voices: The effect of changes in voice parameters on ASR performance
|
|
|
|
BASE
|
|
Show details
|
|
28 |
Evaluating speech synthesis intelligibility using Amazon Mechanical Turk
|
|
|
|
BASE
|
|
Show details
|
|
31 |
Transforming Voice Source Parameters in a HMM-based Speech Synthesiser with Glottal Post-Filtering
|
|
|
|
BASE
|
|
Show details
|
|
32 |
HMM-based speech synthesis using an acoustic glottal source model
|
|
|
|
BASE
|
|
Show details
|
|
33 |
Investigating Non-Uniqueness in the Acoustic-Articulatory Inversion Mapping
|
|
|
|
BASE
|
|
Show details
|
|
37 |
Recognition and Understanding of Meetings Overview of the European AMI and AMIDA Projects
|
|
|
|
In: http://infoscience.epfl.ch/record/145946 (2010)
|
|
BASE
|
|
Show details
|
|
38 |
Recognition and Understanding of Meetings Overview of the European AMI and AMIDA Projects
|
|
|
|
In: http://infoscience.epfl.ch/record/146377 (2010)
|
|
BASE
|
|
Show details
|
|
39 |
Combining Spectral Representations for Large Vocabulary Continuous Speech Recognition
|
|
|
|
BASE
|
|
Show details
|
|
40 |
Recognition of Dialogue Acts in Multiparty Meetings using a Switching DBN
|
|
|
|
BASE
|
|
Show details
|
|
|
|