The development of isolated words corpus of Pashto for the automatic speech recognition research

Ahmed, Irfan; Ali, Hazrat; Ahmad, Nasir; Ahmad, Gulzar

doi:10.1109/icrai.2012.6413380

Cited by 9 publications

(4 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results which we have taken also discussed that the deterministic matrices can be applied for real time application because of the enhanced speed of the reconstruction method at the cost of lower reconstruction accuracy. In this work, speech signals from TIMIT [32], Pashto dataset [33] and Urdu dataset [34] corpora were used for the experimentation. Despite all the advantages associated with random sensing, it falls short in terms of fast and computationally feasible sampling for accurate signal recovery.…”

Section: B Random and Deterministic Samplingmentioning

confidence: 99%

Sparse Signal Representation, Sampling, and Recovery in Compressive Sensing Frameworks

et al. 2022

Self Cite

View full text Add to dashboard Cite

Compressive sensing allows the reconstruction of original signals from a much smaller number of samples as compared to the Nyquist sampling rate. The effectiveness of compressive sensing motivated the researchers for its deployment in a variety of application areas. The use of an efficient sampling matrix for high-performance recovery algorithms improves the performance of the compressive sensing framework significantly. This paper presents the underlying concepts of compressive sensing as well as previous work done in targeted domains in accordance with the various application areas. To develop prospects within the available functional blocks of compressive sensing frameworks, a diverse range of application areas are investigated. The three fundamental elements of a compressive sensing framework (signal sparsity, subsampling, and reconstruction) are thoroughly reviewed in this work by becoming acquainted with the key research gaps previously identified by the research community. Similarly, the basic mathematical formulation is used to outline some primary performance evaluation metrics for 1D and 2D compressive sensing.

show abstract

Section: B Random and Deterministic Samplingmentioning

confidence: 99%

Sparse Signal Representation, Sampling, and Recovery in Compressive Sensing Frameworks

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…A main task in developing a standard spoken corpus is to achieve a database ideally covering all the acoustic variabilities [11], however the development of such corpus with ideal attributes is practically impossible. The other attributes that need to be taken into account while developing a spoken corpus for automatic language identification are keeping balance in gender, age, dialects, nativeness/non-nativeness of the speakers.…”

Section: Database Description and Collectionmentioning

confidence: 99%

“…Pashto is Afghanistan's national language and one of the main languages of Pakistan being spoken in Khyber Pakhtunkhwa and Baluchistan provinces with 50 -60 million speakers around the world [10] [11]. Pashto is also spoken in UAE, Saudi Arabia, U.S, U.K, Qatar, Sweden, Thailand, Russia, Japan, Canada, New Zealand, Ireland and Australia by significant Pashtun population [12].…”

Section: Introductionmentioning

confidence: 99%

A Large Multilingual Corpus of Pashto, Urdu, English for Automatic Spoken Language Identification

Zahoor¹,

Ahmad²

2019

IJCA

Self Cite

View full text Add to dashboard Cite

The availability of a standard and phonetically rich speech corpus provides a common platform for comparing the performance of different speech recognition approaches and therefore is the first step for the research in a language. This work presents the development of a large multilingual speech corpus of Pashto, Urdu and English. Recordings have been made from a total of 194 speakers in the three languages, covering diverse dialects, age groups, genders and professions. Pashto and Urdu both native and non-native speakers have been considered while for English, all the speakers were non-native. The corpus comprises of three categories of phonetically rich spoken data in each language, that is, short questions regarding speaker's personal information, read speech and spontaneous speech from the domain of tourism. Although the corpus is developed primarily for research on Automatic Spoken Language Identification purpose, nevertheless, it can also be used for research on other topics such as Automatic Speech Recognition, Accent Recognition, Automatic Speaker Identification and the study of effects of non-nativeness on Language and Speaker Identification.

show abstract

“…They employed a linear discriminant analysis (LDA) classifier for digit classification, with the word error rate reaching up to 60 % for the initial ten words. Nisar et al [10] developed another database for Pashto digits, incorporating 150 speakers (75 males and 75 females). They used k-nearest neighbor (k-NN) and support vector machine (SVM) classifiers for classification.…”

Section: Introductionmentioning

confidence: 99%

Security Enabled New Term Weight Measure Technique with Data Driven for Next Generation Mobile Computing Networks

Budati,

Islam,

Shaik

et al. 2024

SCPE

View full text Add to dashboard Cite

In the field of ASIC and FPGA, Machine Learning (ML) techniques play a major role and become predominant for accurate results for different applications like big data analysis and automotive electronics, and driverless vehicles which are required speed and power savings. Due to increasing the demand for higher accuracy, low power, low area consumption, and higher throughput for the complexity of the designs in the latest technology, the proposed system is fulfilling these demands in ASIC and FPGA domains, reconfigurable hardware architecture has been proposed it consists of an ML-based Support Vector Machine (SVM), high-speed AHB protocol and Floating point (FP) operations and also the system has the flexibility to communicate with I2C and I2S protocols. In order to increase throughput with minimal latency, the proposed architecture with AHB protocol and AHB to APB bridge is incorporated between the fabric dynamically reconfigurable multi-processor (FDPM) and peripherals along with security algorithms using SHA-256bits and AES. In order to perform ML-based applications, the proposed system is incorporated double-precision floating point (DPFP) arithmetic operations. The overall proposed architecture is developed in Verilog HDL and quality checking using the LINT tool and Clock Domain Crossing (CDC) using Spyglass tool and synthesized using DC compiler for ASIC and Vivado Design Suite 2018.1 for FPGA implementation and verification. The entire design is interfaced with the Zynq processor and SDK tool to verify data transfer between hardware and software. The obtained results show the generated custom accelerator is able to compute any complex ML classifiers for a larger amount of data. The obtained results are compared with existing state-of-art results and found that 18 % improvement in throughput, a 21 % improvement in power consumption savings, and a 34 % reduction in latency.

show abstract

The development of isolated words corpus of Pashto for the automatic speech recognition research

Cited by 9 publications

References 3 publications

Sparse Signal Representation, Sampling, and Recovery in Compressive Sensing Frameworks

Sparse Signal Representation, Sampling, and Recovery in Compressive Sensing Frameworks

A Large Multilingual Corpus of Pashto, Urdu, English for Automatic Spoken Language Identification

Security Enabled New Term Weight Measure Technique with Data Driven for Next Generation Mobile Computing Networks

Contact Info

Product

Resources

About