Abualsoud Hanani

Contrasting the Effects of Different Frequency Bands on Speaker and Accent Identification

This letter presents an experimental study investigating the effect of frequency sub-bands on regional accent identification (AID) and speaker identification (SID) performance on the ABI-1 corpus. The AID and SID systems are based on Gaussian mixture modeling. The SID experiments show up to 100% accuracy when using the full 11.025 kHz bandwidth. The best AID performance of 60.34% is obtained when using band-pass filtered (0.23-3.4 kHz) speech. The experiments using isolated narrow sub-bands show that the regions (0-0.77 kHz) and (3.40-11.02 kHz) are the most useful for SID, while those in the region (0.34-3.44 kHz) are best for AID. AID experiments are also performed with intersession variability compensation, which provides the biggest performance gain in the (2.23-5.25 kHz) region.

Identifying dialects with textual and acoustic cues.

We describe several systems for identifying short samples of Arabic or SwissGerman dialects, which were prepared for the shared task of the 2017 DSL Workshop (Zampieri et al., 2017). The Arabic data comprises both text and acoustic files, and our best run combined both. The SwissGerman data is text-only. Coincidently, our best runs achieved a accuracy of nearly 63% on both the Swiss-German and Arabic dialects tasks.

Speech-based identification of social groups in a single accent of British English by humans and computers

Classification of social groups within a given accent is a challenging refinement of language identification (LID) and accent/dialect recognition. The 2001 census of England and Wales identifies two main ethnic groups in the city of Birmingham, which it refers to as Asian and white. In this paper LID techniques are applied to the problem of identifying individuals from these two groups who were born in Birmingham and hence speak British English with a Birmingham accent. An Equal Error Rate (EER) of 3.57% is obtained using a LID system which fuses the outputs of several acoustic and phonotactic systems. This performance is much better than expected and compares to an EER of 8.72% achieved by human listeners. The implications of this result for automatic speech recognition are discussed.

Language identification using multi-core processors

Graphics processing units (GPUs) provide substantial processing power for little cost. We explore the application of GPUs to speech pattern processing, using language identification (LID) to demonstrate their benefits. Realization of the full potential of GPUs requires both effective coding of predetermined algorithms, and, if there is a choice, selection of the algorithm or technique for a specific function that is most able to exploit the GPU. We demonstrate these principles using the NIST LRE 2003 standard LID task, a batch processing task which involves the analysis of over 600h of speech. We focus on two parts of the system, namely the acoustic classifier, which is based on a 2048 component Gaussian Mixture Model (GMM), and acoustic feature extraction. In the case of the latter we compare a conventional FFT-based analysis with IIR and FIR filter banks, both in terms of their ability to exploit the GPU architecture and LID performance. With no increase in error rate our GPU based system, with an FIR-based front-end, completes the NIST LRE 2003 task in 16h, compared with 180h for the conventional FFT-based system on a standard CPU (a speed up factor of more than 11). This includes a 61% decrease in front-end processing time. In the GPU implementation, front-end processing accounts for 8% and 10% of the total computing times during training and recognition, respectively. Hence the reduction in front-end processing achieved in the GPU implementation is significant.