Audio Search Based on Keyword Spotting in Arabic Language
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2014, Vol 5, Issue 2
Abstract
Keyword spotting is an important application of speech recognition. This research introduces a keyword spotting approach to perform audio searching of uttered words in Arabic speech. The matching process depends on the utterance nucleus which is insensitive to its context. For spotting the targeted utterances, the matched nuclei are expanded to cover the whole utterances. Applying this approach to Quran and standard Arabic has promising results. To improve this spotting approach, it is combined with a text search in case of the existence of a transcript. This can be applied on Quran as there is exact correspondence between the audio and text files of each verse. The developed approach starts by text search to identify the verses that include the target utterance(s). For each allocated verse, the occurrence(s) of the target utterance is determined. The targeted utterance (the reference) is manually segmented from an allocated verse. Then Keyword spotting is performed for the extracted reference to the corresponding audio file. The accuracy of the spotted utterances achieved 97%. The experiments showed that the use of the combined text and audio search has reduced the search time by 90% when compared with audio search only tested on the same content. The developed approach has been applied to non transcribed audio files (preaches and News) for searching chosen utterances. The results are promising. The accuracy of spotting was around 84% in case of preaches and 88% in case of the news.
Authors and Affiliations
Mostafa Awaid, Sahar Fawzi, Ahmed Kandil
Keywords
Related Articles
- EP ID EP141854
- DOI 10.14569/IJACSA.2014.050219
- Views 115
- Downloads 0
A Comparative Study of the Iterative Numerical Methods Used in Mine Ventilation Networks
Ventilation is one of the key safety tasks in underground mines. Determination of the airflow through mine openings and ducts is complex and often requires the application of numerical analysis. The governing equations u...
Strength of Crypto-Semantic System of Tabular Data Protection
The strength of the crypto-semantic method (CSM) of text data protection based on the use of lexicographical systems in the form of applied linguistic corpora within the formally defined restrictions of selected spheres...
Downlink and Uplink Message Size Impact on Round Trip Time Metric in Multi-Hop Wireless Mesh Networks
In this paper, the authors propose a novel real-time study metrics of Round Trip Time (RTT) for Multi-Hop Wireless Mesh Networks. They focus on real operational wireless networks with fixed nodes, such as industrial wire...
Comparison Study of Different Lossy Compression Techniques Applied on Digital Mammogram Images
The huge growth of the usage of internet increases the need to transfer and save multimedia files. Mammogram images are part of these files that have large image size with high resolution. The compression of these images...
Virtual Rehabilitation Using Sequential Learning Algorithms
Rehabilitation systems are becoming more impor-tant now because patients can access motor skills recovery treatment from home, reducing the limitations of time, space and cost of treatment in a medical facility. Traditio...