Cross-dialectal data sharing for acoustic modeling in Arabic speech recognition

Kirchhoff, Katrin; Vergyri, Dimitra

doi:10.1016/j.specom.2005.01.004

Cited by 40 publications

(28 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, many modern speech recognition systems perform the recognition process without prior segmentation. These systems tend to be based on the use of features extraction techniques such as MFCC [6,[11][12][13][14], FFT [15][16][17], HFCC [18], Linear Predictive Coefficient (LPC) [8] ... etc.…”

Section: Arabic Phoneme Segmentation Techniquesmentioning

confidence: 99%

Biologically inspired Continuous Arabic Speech Recognition

Hmad

Allen

2012

Research and Development in Intelligent Systems XXIX

View full text Add to dashboard Cite

show abstract

Section: Arabic Phoneme Segmentation Techniquesmentioning

confidence: 99%

Biologically inspired Continuous Arabic Speech Recognition

Hmad

Allen

2012

Research and Development in Intelligent Systems XXIX

View full text Add to dashboard Cite

show abstract

“…Current literature solves the heterophone HMM training problem using three broad approaches:Diacritize the words and then model them phonemically (Kirchhoff and Vergyri 2005). We refer to this approach as the Simple Phoneme (SP) method, since the standard phoneme is the pronunciation unit.…”

Section: Introductionmentioning

confidence: 99%

Heterophonic speech recognition using composite phones

Alkhairy

Jafri

2016

SpringerPlus

View full text Add to dashboard Cite

Heterophones pose challenges during training of automatic speech recognition (ASR) systems because they involve ambiguity in the pronunciation of an orthographic representation of a word. Heterophones are words that have the same spelling but different pronunciations. This paper addresses the problem of heterophonic languages by developing the concept of a Composite Phoneme (CP) as a basic pronunciation unit for speech recognition. A CP is a set of alternative sequences of phonemes. CP’s are developed specifically in the context of Arabic by defining phonetic units that are consonant centric and absorb phonemically contrastive short vowels and gemination, not represented in the Arabic Modern Orthography (MO). CPs alleviate the need to diacritize MO into Classical Orthography (CO), to represent short vowels and stress, before generating pronunciation in terms of Simple Phonemes (SP). We develop algorithms to generate CP pronunciation from MO, and SP pronunciation from CO to map a word into a single pronunciation. We investigate the performance of CP, SP, UG (Undiacritized Grapheme), and DG (Diacritized Grapheme) ASRs. The experimental results suggest that UG and DG are inferior to SP and CP. For the A-SpeechDB corpus with MO vocabulary of 8000, the WER for bigram and context dependent phone are: 11.78, 12.64, and 13.59 % for CP, SP_M (SP from manual diacritized CO), and SP_A (SP from automated diacritized MO) respectively. For vocabulary of 24,000 MO words, the corresponding WER’s are 13.69, 15.08, and 16.86 %. For uniform statistical model, SP has a lower WER than CP. For context independent phone (CI), CP has lower WER than SP.

show abstract

“…In one phase, transcriptions are written without diacritics. Afterwards, automatic diacritization is performed to estimate missing diacritic marks (WER is 15%-25%) as in [2] and [3]. Finally, the mapping from diacritized text to phonetic transcription is almost a one-to-one mapping.…”

Section: Introductionmentioning

confidence: 99%

Rapid phonetic transcription using everyday life natural Chat Alphabet orthography for dialectal Arabic speech recognition

Elmahdy

Gruhn

Abdennadher

et al. 2011

2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

We propose the Arabic Chat Alphabet (ACA) as naturally written in everyday life for dialectal Arabic speech transcription. Our assumption is that ACA is a natural language that includes short vowels that are missing in traditional Arabic orthography. Furthermore, ACA transcriptions can be rapidly prepared. Egyptian Colloquial Arabic was chosen as a typical dialect. Two speech recognition baselines were built: phonemic and graphemic. Original transcriptions were re-written in ACA by different transcribers. Ambiguous ACA sequences were handled by automatically generating all possible variants. ACA variations across transcribers were modeled by phonemes normalization and merging. Results show that the ACA-based approach outperforms the graphemic baseline while it performs as accurate as the phoneme-based baseline with a slight increase in WER.

show abstract

Cross-dialectal data sharing for acoustic modeling in Arabic speech recognition

Cited by 40 publications

References 18 publications

Biologically inspired Continuous Arabic Speech Recognition

Biologically inspired Continuous Arabic Speech Recognition

Heterophonic speech recognition using composite phones

Rapid phonetic transcription using everyday life natural Chat Alphabet orthography for dialectal Arabic speech recognition

Contact Info

Product

Resources

About