Search results for: speech compression

Authors: Ajish K. Abraham

Abstract:

Hearing aid is the most fundamental technology employed towards rehabilitation of persons with sensory neural hearing impairment. Hearing in noise is still a matter of major concern for many hearing aid users and thus continues to be a challenging issue for the hearing aid designers. Several techniques are being currently used to enhance the speech at the hearing aid output. Most of these techniques, when implemented, result in reduction of intelligibility of the speech signal. Thus the dissatisfaction of the hearing aid user towards comprehending the desired speech amidst noise is prevailing. Multichannel Wiener Filter is widely implemented in binaural hearing aid technology for noise reduction. In this study, Wiener filter based noise reduction approach is experimented for a single microphone based hearing aid set up. This method checks the status of the input speech signal in each frequency band and then selects the relevant noise reduction procedure. Results showed that the Wiener filter based algorithm is capable of enhancing speech even when the input acoustic signal has a very low Signal to Noise Ratio (SNR). Performance of the algorithm was compared with other similar algorithms on the basis of improvement in intelligibility and SNR of the output, at different SNR levels of the input speech. Wiener filter based algorithm provided significant improvement in SNR and intelligibility compared to other techniques.

Keywords: hearing aid output speech, noise reduction, SNR improvement, Wiener filter, speech enhancement

Procedia PDF Downloads 243

Authors: Mumtaz Begum Mustafa, Siti Salwah Salim, Feizal Dani Rahman

Abstract:

Recently, Automatic Speech Recognition (ASR) systems were used to assist children in language acquisition as it has the ability to detect human speech signal. Despite the benefits offered by the ASR system, there is a lack of ASR systems for Malay-speaking children. One of the contributing factors for this is the lack of continuous speech database for the target users. Though cross-lingual adaptation is a common solution for developing ASR systems for under-resourced language, it is not viable for children as there are very limited speech databases as a source model. In this research, we propose a two-stage adaptation for the development of ASR system for Malay-speaking children using a very limited database. The two stage adaptation comprises the cross-lingual adaptation (first stage) and cross-age adaptation. For the first stage, a well-known speech database that is phonetically rich and balanced, is adapted to the medium-sized Malay adults using supervised MLLR. The second stage adaptation uses the speech acoustic model generated from the first adaptation, and the target database is a small-sized database of the target users. We have measured the performance of the proposed technique using word error rate, and then compare them with the conventional benchmark adaptation. The two stage adaptation proposed in this research has better recognition accuracy as compared to the benchmark adaptation in recognizing children’s speech.

Keywords: Automatic Speech Recognition System, children speech, adaptation, Malay

Procedia PDF Downloads 389

Authors: Tanju Deveci

Abstract:

It appears that the speech act of complaint has not received as much attention as other speech acts. However, the face-threatening nature of this speech act requires a special attention in multicultural contexts in particular. The teaching context in the UAE universities, where a big majority of teaching staff comes from other cultures, requires investigations into this speech act in order to improve communication between students and faculty. This session will outline the results of a study conducted with this purpose. The realization of complaints by Freshman English students in Communication courses at Petroleum Institute was investigated to identify communication patterns that seem to cause a strain. Data were collected using a role-play between a teacher and students, and a judgment scale completed by two of the instructors in the Communications Department. The initial findings reveal that the students had difficulty putting their case, produced the speech act of criticism along with a complaint and that they produced both requests and demands as candidate solutions. The judgement scales revealed that the students’ attitude was not appropriate most of the time and that the judges would behave differently from students. It is concluded that speech acts, in general, and complaint, in particular, need to be taught to learners explicitly to improve interpersonal communication in multicultural societies. Some teaching ideas are provided to help increase foreign language learners’ sociolinguistic competence.

Keywords: speech act, complaint, pragmatics, sociolinguistics, language teaching

Procedia PDF Downloads 503

Authors: M. Habibi

Abstract:

The time-resolved studies of soft and hard X-ray were carried out over a wide range of argon pressures by employing an array of eight filtered photo PIN diodes and a scintillation detector, simultaneously. In 50% of the discharges, the soft X-ray is seen to be emitted in short multiple pulses corresponding to different compression, whereas it is a single pulse for hard X-rays corresponding to only the first strong compression. It should be stated that multiple compressions dominantly occur at low pressures and high pressures are mostly in the single compression regime. In 43% of the discharges, at all pressures except for optimum pressure, the first period is characterized by two or more sharp peaks.The X–ray signal intensity during the second and subsequent compressions is much smaller than the first compression.

Keywords: plasma focus device, SXR, HXR, Pin-diode, argon plasma

Procedia PDF Downloads 402

Authors: Tamara Matevosyan

Abstract:

The present paper discusses the main problems that students face while developing oral skills through authentic films. It states that special attention should be paid not only to the study of verbal speech but also to non-verbal communication. Authentic films serve as an important tool to understand both native speaker’s gestures and their culture of pausing while speaking. Various phonetic difficulties causing phonetic interference in actual speech are covered in the paper emphasizing the role of authentic films in overcoming them.

Keywords: compressive speech, filled pauses, unfilled pauses, pausing culture

Procedia PDF Downloads 350

Authors: Mohammed F. Almograbi

Abstract:

For reinforced concrete panels the risk of failure due to compression -tension state of stresses, results from pure shear or torsion, can be a major problem. The present calculation methods for such stresses from multiple influences are without taking into account the softening of cracked concrete remains conservative. The non-linear finite element method has become an important and increasingly used tool for the analysis and assessment of the structures by including cracking softening and tension-stiffening. The aim of this paper is to test a computer program refined recently and to simulate the compression response of cracked concrete element and to compare with the available experimental results.

Keywords: reinforced concrete panels, compression-tension, shear, torsion, compression softening, tension stiffening, non-linear finite element analysis

Procedia PDF Downloads 335

Authors: Sudeepti Dayal, Neelesh Gupta

Abstract:

Image abbreviation is utilized for reducing the size of a file without demeaning the quality of the image to an objectionable level. The depletion in file size permits more images to be deposited in a given number of spaces. It also minimizes the time necessary for images to be transferred. Storage of medical images is a most researched area in the current scenario. To store a medical image, there are two parameters on which the image is divided, regions of interest and non-regions of interest. The best way to store an image is to compress it in such a way that no important information is lost. Compression can be done in two ways, namely lossy, and lossless compression. Under that, several compression algorithms are applied. In the paper, two algorithms are used which are, discrete cosine transform, applied to non-region of interest (lossy), and discrete wavelet transform, applied to regions of interest (lossless). The paper introduces SPIHT (set partitioning hierarchical tree) algorithm which is applied onto the wavelet transform to obtain good compression ratio from which an image can be stored efficiently.

Keywords: Compression ratio, DWT, SPIHT, DCT

Procedia PDF Downloads 345

Authors: Qiuxiao Chen, Yan Hou, Ning Wu

Abstract:

As there are deficiencies of the classic Douglas-Peucker Algorithm (DPA), such as high risks of deleting key nodes by mistake, high complexity, time consumption and relatively slow execution speed, a new Deletion-Cost Based Compression Algorithm (DCA) for linear vector data was proposed. For each curve — the basic element of linear vector data, all the deletion costs of its middle nodes were calculated, and the minimum deletion cost was compared with the pre-defined threshold. If the former was greater than or equal to the latter, all remaining nodes were reserved and the curve’s compression process was finished. Otherwise, the node with the minimal deletion cost was deleted, its two neighbors' deletion costs were updated, and the same loop on the compressed curve was repeated till the termination. By several comparative experiments using different types of linear vector data, the comparison between DPA and DCA was performed from the aspects of compression quality and computing efficiency. Experiment results showed that DCA outperformed DPA in compression accuracy and execution efficiency as well.

Keywords: Douglas-Peucker algorithm, linear vector data, compression, deletion cost

Procedia PDF Downloads 246

Authors: B. V. Lande, Suhas Kongare

Abstract:

Fuel blend of alcohol and conventional hydrocarbon fuels for a spark ignition engine can increase the fuel octane rating and the power for a given engine displacement and compression ratio. The greatest advantage of ethanol as a fuel in SI Engines is its high octane number. The efficiency of an SI engine that is the ability to convert fuel energy to mechanical energy, mainly depends on the compression ratio. It is, therefore, an advantage to increase this as much as possible. The major restraint is the fuel octane number – high octane fuels can be used with high compression ratios, thus yielding higher energy efficiency. This work investigates to suggest suitable ethanol gasoline blend and compression ratio for single cylinder four strokes SI Engine on the basis of performance and exhaust emissions. A single cylinder four stroke SI Engine was tested with different blend of ethanol – gasoline like E5 (5% ethanol +95% gasoline), E10 (10% ethanol + 90% gasoline) E15 (15% ethanol + 85% petrol) and E20 ( 20% + 80% gasoline) with Variable compression ratio. The performance parameter evaluated BSFC, Brake thermal efficiency and also exhaust emission CO2, Co & HC%. The result showed that higher compression ratio improved engine Performance and reduction in exhaust emission.

Keywords: blend, compression ratio, ethanol, performance, blend

Procedia PDF Downloads 395

Authors: M. C. Padma, R. J. Prathibha

Abstract:

Parts of speech tagging is the process of assigning appropriate parts of speech tags to the words in a given text. The critical or crucial information needed for tagging a word come from its internal structure rather from its neighboring words. The internal structure of a word comprises of its morphological features and grammatical information. This paper presents a morpheme based parts of speech tagger for Kannada language. This proposed work uses hierarchical tag set for assigning tags. The system is tested on some Kannada words taken from EMILLE corpus. Experimental result shows that the performance of the proposed system is above 90%.

Keywords: hierarchical tag set, morphological analyzer, natural language processing, paradigms, parts of speech

Procedia PDF Downloads 291

Authors: Jawairia Umar, Tanveer Hussain, Zulfiqar Ali, Muhammad Maqsood

Abstract:

Different knitted structures and knitted parameters play a vital role in the stretch and recovery management of compression sportswear in addition to the materials use to generate this stretch and recovery behavior of the fabric. The present work was planned to predict the different performance indicators of a compression sportswear fabric with some ground parameters i.e. base yarn stitch length (polyester as base yarn and spandex as plating yarn involve to make a compression fabric) and linear density of the spandex which is a key material of any sportswear fabric. The prediction models were generated by response surface method for performance indicators such as stretch & recovery percentage, compression generated by the garment on body, total elongation on application of high power force and load generated on certain percentage extension in fabric. Certain physical properties of the fabric were also modeled using these two parameters.

Keywords: Compression, sportswear, stretch and recovery, statistical model, kikuhime

Procedia PDF Downloads 374

Authors: Ergun Guntekin

Abstract:

Elastic constants of Fir wood (Abies cilicica) have been investigated by means of ultrasound and compression tests. Three modulus of elasticity in principal directions (EL, ER, ET), six Poisson’s ratios (ʋLR, ʋLT, ʋRT, ʋTR, ʋRL, ʋTL) and three shear modules (GLR, GRT, GLT) were determined. 20 x 20 x 60 mm samples were conditioned at 65 % relative humidity and 20ºC before testing. Three longitudinal and six shear wave velocities propagating along the principal axes of anisotropy, and additionally, three quasi-shear wave velocities at 45° angle with respect to the principal axes of anisotropy were measured. 2.27 MHz longitudinal and 1 MHz shear sensors were used for obtaining sound velocities. Stress-strain curves of the samples in compression tests were obtained using bi-axial extensometer in order to calculate elastic constants. Test results indicated that most of the elastic constants determined in the study are within the acceptable range. Although elastic constants determined from ultrasound are usually higher than those determined from compression tests, the values of EL and GLR determined from compression tests were higher in the study. The results of this study can be used in the numerical modeling of elements or systems under load using Fir wood.

Keywords: compression tests, elastic constants, fir wood, ultrasound

Procedia PDF Downloads 213

Authors: Sergei Aleinik, Yuri Matveev

Abstract:

In this paper a novel method for the detection of clipping in speech signals is described. It is shown that the new method has better performance than known clipping detection methods, is easy to implement, and is robust to changes in signal amplitude, size of data, etc. Statistical simulation results are presented.

Keywords: clipping, clipped signal, speech signal processing, digital signal processing

Procedia PDF Downloads 389

Authors: Ergun Guntekin

Abstract:

Effects of heat treatment on elastic constants of Black pine (Pinus nigra) wood were investigated. Specimens were exposed to heat under atmospheric pressure at two different temperatures (180 and 210 °C) and three different time levels (2, 5, 8 hours). Three Young’s modulus in three anatomical directions, six Poisson’s ratios and three Shear modulus values associated with the main directions were evaluated by compression tests. Compression strength of the samples in three principal directions was also determined. All of the properties of the specimens tested were altered by heat treatment. The degree of alteration depends on the temperature as well as duration applied. Results indicate that EL and compression strength in L direction were not significantly influenced, compression strength in R direction significantly decreased, ER, ET and compression strength in T direction were increased for shorter periods, then dropped for 8-hour application of 180 ºC. ER was not significantly affected, compression strength in R direction and EL was significantly decreased, ET and compression strength in T direction were increased for shorter periods, then decreased for 8-hour application of 210 ºC. The shear modulus of the samples was decreased with application of treatment combinations. Most of the Poisson’s ratios were not affected by heat treatment.

Keywords: black pine, elastic constants, heat treatment, wood

Procedia PDF Downloads 151

Authors: A. Albar, D. B. Granato, U. Schwingenschlogl

Abstract:

Tin monoxide (SnO) has promising properties to be applied as a p-type semiconductor in transparent electronics. To this end, it is necessary to understand the behavior of defects in order to control them. We use density functional theory to study native defects of SnO under tensile and compressive strain. We show that Sn vacancies are more stable under tension and less stable under compression, irrespectively of the charge state. In contrast, O vacancies behave differently for different charge. It turns out that the most stable defect under compression is the +1 charged O vacancy in a Sn-rich environment and the charge neutral O interstitial in an O-rich environment. Therefore, compression can be used to transform SnO from an n-type into un-doped semiconductor.

Keywords: native defects, ab-initio, point defect, tension, compression, semiconductor

Procedia PDF Downloads 390

Authors: Anna Kula, Raja K. Mishra, Marek Niewczas

Abstract:

Deformation behavior of Mg-Gd solid solutions have been studied by a combination of measurements of mechanical response, texture and dislocation substructure. Increase in Gd content strongly influences the work-hardening behavior and flow characteristics in tension and compression. Adiabatic instabilities have been observed in all alloys at 4K under both tension and compression. The frequency and the amplitude of adiabatic stress oscillations increase with Gd content. Profuse mechanical twinning has been observed under compression, resulting in a texture dominated by basal component parallel to the compression axis. Under tension, twining is less active and the texture evolution is affected mostly by slip. Increasing Gd concentration leads to the reduction of the tension and compression asymmetry due to weakening of the texture and stabilizing more homogenous twinning and slip, involving basal and non-basal slip systems.

Keywords: Mg-Gd alloys, mechanical properties, work hardening, twinning

Procedia PDF Downloads 533

Authors: Monica Puri Sikka, Subrato Ghosh Arunangshu Mukhopadhyay

Abstract:

Appropriate compression bandaging is important for compression therapeutic medical diseases. The high compression approach employed for treating venous leg ulcers should be used correctly so that sufficient (but not excessive) pressure is applied. Bandages used to treat venous disease by compression should achieve and sustain effective levels and gradients of pressure and minimise the risk of pressure trauma. To maintain graduated compression on the limb the bandage needs to be applied at same tension for each layer from ankle to the knee. In this paper the geometry for various bandaging procedures is used to wrap each layer of bandage by marking the relaxed length of the bandage. The relaxed length is calculated depending on the stretch, average circumference of the limb on which it is to be applied and the bandaging technique to be used. This paper aims at developing a scientific approach while applying the bandage to reduce the inter operator variability in applying same tension on each successive layer of bandage.

Keywords: bandaging, compression, inter operator variability, graduated, relaxed length, stretch

Procedia PDF Downloads 493

Authors: Esha Banerjee, Atul Kumar Ojha, Girish Nath Jha

Abstract:

This study aims to develop an intonation labeled database for Hindi. Although no single standard for prosody labeling exists in Hindi, researchers in the past have employed perceptual and statistical methods in literature to draw inferences about the behavior of prosody patterns in Hindi. Based on such existing research and largely agreed upon intonational theories in Hindi, this study attempts to develop a manually annotated prosodic corpus of Hindi speech data, which can be used for training speech models for natural-sounding speech in the future. 100 sentences ( 500 words) each for declarative and interrogative types have been labeled using Praat.

Keywords: speech dataset, Hindi, intonation, labeled corpus

Procedia PDF Downloads 191

Authors: John Trihatmoko, Luky Handoko

Abstract:

A series of experimental program was undertaken to study the effect of curing temperature on the unconfined compression strength of bagasse ash (BA) - calcium carbide residue (CCR) stabilized organic clay (OC). A preliminary experiment was performed to get the physical properties of OC, and to get the optimum water content (OMC), the standard compaction test was done. The stabilizing agents used in this research was (40% BA + 60% CCR) . Then to obtain the best binder proportion, unconfined compression test was undertaken for OC + 3, 6, 9, 12 and 15% of binder with 7, 14, 21, 28 and 56 days curing period. The best quantity of the binder was found on 9%. Finally, to study the effect of curing temperature, the unconfined compression test was performed on OC + 9% binder with 7, 14, 21, 28 and 56 days curing time with 20O, 25O, 30O, 40O, and 50O C curing temperature. The result indicates that unconfined compression strength (UCS) of treated OC improve according to the increase of curing temperature at the same curing time. The improvement of UCS is probably due to the degree of cementation and pozzolanic reactions.

Keywords: curing temperature, organic clay, bagasse ash, calcium carbide residue, unconfined compression strength

Procedia PDF Downloads 121

Authors: Yunbin Deng

Abstract:

Most existing applications of automatic speech recognition relies on cooperative subjects at a short distance to a microphone. Standoff speech recognition using microphone arrays can extend the subject to sensor distance somewhat, but it is still limited to only a few feet. As such, most deployed applications of standoff speech recognitions are limited to indoor use at short range. Moreover, these applications require air passway between the subject and the sensor to achieve reasonable signal to noise ratio. This study reports long range (50 feet) automatic speech recognition experiments using a Laser Doppler Vibrometer (LDV) sensor. This study shows that the LDV sensor modality can extend the speech acquisition standoff distance far beyond microphone arrays to hundreds of feet. In addition, LDV enables 'listening' through the windows for uncooperative subjects. This enables new capabilities in automatic audio and speech intelligence, surveillance, and reconnaissance (ISR) for law enforcement, homeland security and counter terrorism applications. The Polytec LDV model OFV-505 is used in this study. To investigate the impact of different vibrating materials, five parallel LDV speech corpora, each consisting of 630 speakers, are collected from the vibrations of a glass window, a metal plate, a plastic box, a wood slate, and a concrete wall. These are the common materials the application could encounter in a daily life. These data were compared with the microphone counterpart to manifest the impact of various materials on the spectrum of the LDV speech signal. State of the art deep neural network modeling approaches is used to conduct continuous speaker independent speech recognition on these LDV speech datasets. Preliminary phoneme recognition results using time-delay neural network, bi-directional long short term memory, and model fusion shows great promise of using LDV for long range speech recognition. To author’s best knowledge, this is the first time an LDV is reported for long distance speech recognition application.

Keywords: covert speech acquisition, distant speech recognition, DSR, laser Doppler vibrometer, LDV, speech intelligence surveillance and reconnaissance, ISR

Procedia PDF Downloads 175

Authors: Ericson O. Alieto, Aprillete C. Devanadera

Abstract:

The main objective of the study is to determine the dominant speech acts in five commemorative speeches of President Duterte. This study employed Speech Act Theory and Discourse analysis to determine how the speech acts features connote the pragmatic meaning of Duterte’s speeches. Identifying the speech acts is significant in elucidating the underlying message or the pragmatic meaning of the speeches. From the 713 sentences or utterances from the speeches, assertive with 208 occurrences from the corpus or 29% is the dominant speech acts. It was followed by expressive with 177 or 25% occurrences, directive accounts for 152 or 15% occurrences. While commisive accounts for 104 or 15% occurrences and declarative got the lowest percentage of occurrences with 72 or 10% only. These sentences when uttered by Duterte carry a certain power of language to move or influence people. Thus, the present study shows the fundamental message perceived by the listeners. Moreover, the frequent use of assertive and expressive not only explains the pragmatic message of the speeches but also reflects the personality of President Duterte.

Keywords: commemorative speech, discourse analysis, duterte, pragmatics

Procedia PDF Downloads 281

Authors: M. Kiran Reddy, K. Sreenivasa Rao

Abstract:

The conventional Hidden Markov Model (HMM)-based speech synthesis system (HTS) uses only a pulse excitation model, which significantly differs from natural excitation signal. Hence, buzziness can be perceived in the speech generated using HTS. This paper proposes an efficient excitation modeling method that can significantly reduce the buzziness, and improve the quality of HMM-based speech synthesis. The proposed approach models the pitch-synchronous residual frames extracted from the residual excitation signal. Each pitch synchronous residual frame is parameterized using 30 wavelet coefficients. These 30 wavelet coefficients are found to accurately capture the perceptually important information present in the residual waveform. In synthesis phase, the residual frames are reconstructed from the generated wavelet coefficients and are pitch-synchronously overlap-added to generate the excitation signal. The proposed excitation modeling method is integrated into HMM-based speech synthesis system. Evaluation results indicate that the speech synthesized by the proposed excitation model is significantly better than the speech generated using state-of-the-art excitation modeling methods.

Keywords: excitation modeling, hidden Markov models, pitch-synchronous frames, speech synthesis, wavelet coefficients

Procedia PDF Downloads 243

Authors: Veerakumar Arumugam, Rajesh Mishra, Jiri Militky, Jana Salacova

Abstract:

The thermo-physiological comfort and compression properties of knitted spacer fabrics have been evaluated by varying the different spacer fabric parameters. Air permeability and water vapor transmission of the fabrics were measured using the Textest FX-3300 air permeability tester and PERMETEST. Then thermal behavior of fabrics was obtained by Thermal conductivity analyzer and overall moisture management capacity was evaluated by moisture management tester. Spacer Fabrics compression properties were also tested using Kawabata Evaluation System (KES-FB3). In the KES testing, the compression resilience, work of compression, linearity of compression and other parameters were calculated from the pressure-thickness curves. Analysis of Variance (ANOVA) was performed using new statistical software named QC expert trilobite and Darwin in order to compare the influence of different fabric parameters on thermo-physiological and compression behavior of samples. This study established that the raw materials, type of spacer yarn, density, thickness and tightness of surface layer have significant influence on both thermal conductivity and work of compression in spacer fabrics. The parameter which mainly influence on the water vapor permeability of these fabrics is the properties of raw material i.e. the wetting and wicking properties of fibers. The Pearson correlation between moisture capacity of the fabrics and water vapour permeability was found using statistical software named QC expert trilobite and Darwin. These findings are important requirements for the further designing of clothing for extreme environmental conditions.

Keywords: 3D spacer fabrics, thermal conductivity, moisture management, work of compression (WC), resilience of compression (RC)

Procedia PDF Downloads 534

Authors: Tadesse Anberbir, Bankole Felix, Tomio Takara

Abstract:

In the development of a text-to-speech synthesizer, automatic derivation of correct pronunciation from the grapheme form of a text is a central problem. Particularly deriving phonological features which are not shown in orthography is challenging. In the Amharic language, geminates and epenthetic vowels are very crucial for proper pronunciation, but neither is shown in orthography. In this paper, to proposed and integrated a morphological analyzer into an Amharic Text-to-Speech system, mainly to predict geminates and epenthetic vowel positions and prepared a duration modeling method. Amharic Text-to-Speech system (AmhTTS) is a parametric and rule-based system that adopts a cepstral method and uses a source filter model for speech production and a Log Magnitude Approximation (LMA) filter as the vocal tract filter. The naturalness of the system after employing the duration modeling was evaluated by sentence listening test, and we achieved an average Mean Opinion Score (MOS) 3.4 (68%), which is moderate. By modeling the duration of geminates and controlling the locations of epenthetic vowel, we are able to synthesize good quality speech. Our system is mainly suitable to be customized for other Ethiopian languages with limited resources.

Keywords: amharic, gemination, Speech synthesis, morphology, epenthesis

Procedia PDF Downloads 79

Authors: Dzhavidan Zeinalov, Bugra Sen, Firangiz Aslanova

Abstract:

Most text-to-speech models cannot operate well in low-resource languages and require a great amount of high-quality training data to be considered good enough. Yet, with the improvements made in ASR systems, it is now much easier than ever to collect data for the design of custom text-to-speech models. In this work, our work on using the ASR model to collect data to build a viable text-to-speech system for one of the leading financial institutions of Azerbaijan will be outlined. NVIDIA’s implementation of the Tacotron 2 model was utilized along with the HiFiGAN vocoder. As for the training, the model was first trained with high-quality audio data collected from the Internet, then fine-tuned on the bank’s single speaker call center data. The results were then evaluated by 50 different listeners and got a mean opinion score of 4.17, displaying that our method is indeed viable. With this, we have successfully designed the first text-to-speech model in Azerbaijani and publicly shared 12 hours of audiobook data for everyone to use.

Keywords: Azerbaijani language, HiFiGAN, Tacotron 2, text-to-speech, transfer learning, whisper

Procedia PDF Downloads 38

Authors: Edemealem Desalegn Kingawa, Kafte Tasew Timkete, Mekashaw Girmaw Abebe, Terefe Feyisa, Abiyot Bitew Mihretie, Senait Teklemarkos Haile

Abstract:

Currently, hate speech is a growing challenge for society, individuals, policymakers, and researchers, as social media platforms make it easy to anonymously create and grow online friends and followers and provide an online forum for debate about specific issues of community life, culture, politics, and others. Despite this, research on identifying and detecting hate speech is not satisfactory performance, and this is why future research on this issue is constantly called for. This paper provides a systematic review of the literature in this field, with a focus on approaches like word embedding techniques, machine learning, deep learning technologies, hate speech terminology, and other state-of-the-art technologies with challenges. In this paper, we have made a systematic review of the last six years of literature from Research Gate and Google Scholar. Furthermore, limitations, along with algorithm selection and use challenges, data collection, and cleaning challenges, and future research directions, are discussed in detail.

Keywords: Amharic hate speech, deep learning approach, hate speech detection review, Afaan Oromo hate speech detection

Procedia PDF Downloads 169

Authors: Tadesse Anberbir, Felix Bankole, Tomio Takara, Girma Mamo

Abstract:

In the development of a text-to-speech synthesizer, automatic derivation of correct pronunciation from the grapheme form of a text is a central problem. Particularly deriving phonological features which are not shown in orthography is challenging. In the Amharic language, geminates and epenthetic vowels are very crucial for proper pronunciation but neither is shown in orthography. In this paper, we proposed and integrated a morphological analyzer into an Amharic Text-to-Speech system, mainly to predict geminates and epenthetic vowel positions, and prepared a duration modeling method. Amharic Text-to-Speech system (AmhTTS) is a parametric and rule-based system that adopts a cepstral method and uses a source filter model for speech production and a Log Magnitude Approximation (LMA) filter as the vocal tract filter. The naturalness of the system after employing the duration modeling was evaluated by sentence listening test and we achieved an average Mean Opinion Score (MOS) 3.4 (68%) which is moderate. By modeling the duration of geminates and controlling the locations of epenthetic vowel, we are able to synthesize good quality speech. Our system is mainly suitable to be customized for other Ethiopian languages with limited resources.

Keywords: Amharic, gemination, speech synthesis, morphology, epenthesis

Procedia PDF Downloads 78

Authors: Sadiq Aminu, Ahmed Lamido

Abstract:

This research studies Barack Obama’s second inaugural speech using Halliday’s Systemic Functional Grammar (SFG). SFG is a text grammar which describes how language is used, so that the meaning of the text can be better understood. The primary source of data in this research work is Barack Obama’s second inaugural speech which was obtained from the internet. The analysis of the speech was based on the ideational and textual metafunctions of Systemic Functional Grammar. Specifically, the researcher analyses the Process Types and Participants (ideational) and the Theme/Rheme (textual). It was found that material process (process of doing) was the most frequently used ‘Process type’ and ‘We’ which refers to the people of America was the frequently used ‘Theme’. Application of the SFG theory, therefore, gives a better meaning to Barack Obama’s speech.

Keywords: ideational, metafunction, rheme, textual, theme

Procedia PDF Downloads 151

Authors: John Lorenzo Bautista, Yoon-Joong Kim

Abstract:

This paper presents the development of a Filipino speech recognition tool using the HTK System. The system was trained from a subset of the Filipino Speech Corpus developed by the DSP Laboratory of the University of the Philippines-Diliman. The speech corpus was both used in training and testing the system by estimating the parameters for phonetic HMM-based (Hidden-Markov Model) acoustic models. Experiments on different mixture-weights were incorporated in the study. The phoneme-level word-based recognition of a 5-state HMM resulted in an average accuracy rate of 80.13 for a single-Gaussian mixture model, 81.13 after implementing a phoneme-alignment, and 87.19 for the increased Gaussian-mixture weight model. The highest accuracy rate of 88.70% was obtained from a 5-state model with 6 Gaussian mixtures.

Keywords: Filipino language, Hidden Markov Model, HTK system, speech recognition

Procedia PDF Downloads 476

Authors: João Rato, Nuno Costa

Abstract:

The human verbal communication is a two-way process which requires a mutual understanding that will result in some considerations. This kind of communication, also called dialogue, besides the supposed human agents it can also be performed between human agents and machines. The interaction between Men and Machines, by means of a natural language, has an important role concerning the improvement of the communication between each other. Aiming at knowing the performance of some speech recognition systems, this document shows the results of the accomplished tests according to the Word Error Rate evaluation method. Besides that, it is also given a set of information linked to the systems of Man-Machine communication. After this work has been made, conclusions were drawn regarding the Speech Recognition Systems, among which it can be mentioned their poor performance concerning the voice interpretation in noisy environments.

Keywords: automatic speech recognition, man-machine conversation, speech recognition, spoken dialogue systems, word error rate

Procedia PDF Downloads 317