Search

Your search keyword '"Heydari, Mojtaba"' showing total 376 results
Start Over Author "Heydari, Mojtaba"
376 results on '"Heydari, Mojtaba"'

3. SingFake: Singing Voice Deepfake Detection

Author

Zang, Yongyi, Zhang, You, Heydari, Mojtaba, and Duan, Zhiyao

Subjects
Computer Science - Sound, Computer Science - Artificial Intelligence, Electrical Engineering and Systems Science - Audio and Speech Processing
Abstract

The rise of singing voice synthesis presents critical challenges to artists and industry stakeholders over unauthorized voice usage. Unlike synthesized speech, synthesized singing voices are typically released in songs containing strong background music that may hide synthesis artifacts. Additionally, singing voices present different acoustic and linguistic characteristics from speech utterances. These unique properties make singing voice deepfake detection a relevant but significantly different problem from synthetic speech detection. In this work, we propose the singing voice deepfake detection task. We first present SingFake, the first curated in-the-wild dataset consisting of 28.93 hours of bonafide and 29.40 hours of deepfake song clips in five languages from 40 singers. We provide a train/validation/test split where the test sets include various scenarios. We then use SingFake to evaluate four state-of-the-art speech countermeasure systems trained on speech utterances. We find these systems lag significantly behind their performance on speech test data. When trained on SingFake, either using separated vocal tracks or song mixtures, these systems show substantial improvement. However, our evaluations also identify challenges associated with unseen singers, communication codecs, languages, and musical contexts, calling for dedicated research into singing voice deepfake detection. The SingFake dataset and related resources are available at https://www.singfake.org/., Comment: Accepted at ICASSP 2024

Published
2023

4. SingNet: A Real-time Singing Voice Beat and Downbeat Tracking System

Author

Heydari, Mojtaba, Wang, Ju-Chiang, and Duan, Zhiyao

Subjects
Electrical Engineering and Systems Science - Audio and Speech Processing
Abstract

Singing voice beat and downbeat tracking posses several applications in automatic music production, analysis and manipulation. Among them, some require real-time processing, such as live performance processing and auto-accompaniment for singing inputs. This task is challenging owing to the non-trivial rhythmic and harmonic patterns in singing signals. For real-time processing, it introduces further constraints such as inaccessibility to future data and the impossibility to correct the previous results that are inconsistent with the latter ones. In this paper, we introduce the first system that tracks the beats and downbeats of singing voices in real-time. Specifically, we propose a novel dynamic particle filtering approach that incorporates offline historical data to correct the online inference by using a variable number of particles. We evaluate the performance on two datasets: GTZAN with the separated vocal tracks, and an in-house dataset with the original vocal stems. Experimental result demonstrates that our proposed approach outperforms the baseline by 3-5%., Comment: Accepted for 2023 International Conference on Acoustics, Speech, and Signal Processing (ICASSP-2023)

Published
2023

8. Singing Beat Tracking With Self-supervised Front-end and Linear Transformers

Author

Heydari, Mojtaba and Duan, Zhiyao

Subjects
Electrical Engineering and Systems Science - Audio and Speech Processing
Abstract

Tracking beats of singing voices without the presence of musical accompaniment can find many applications in music production, automatic song arrangement, and social media interaction. Its main challenge is the lack of strong rhythmic and harmonic patterns that are important for music rhythmic analysis in general. Even for human listeners, this can be a challenging task. As a result, existing music beat tracking systems fail to deliver satisfactory performance on singing voices. In this paper, we propose singing beat tracking as a novel task, and propose the first approach to solving this task. Our approach leverages semantic information of singing voices by employing pre-trained self-supervised WavLM and DistilHuBERT speech representations as the front-end and uses a self-attention encoder layer to predict beats. To train and test the system, we obtain separated singing voices and their beat annotations using source separation and beat tracking on complete songs, followed by manual corrections. Experiments on the 741 separated vocal tracks of the GTZAN dataset show that the proposed system outperforms several state-of-the-art music beat tracking methods by a large margin in terms of beat tracking accuracy. Ablation studies also confirm the advantages of pre-trained self-supervised speech representations over generic spectral features., Comment: 23rd International Society for Music Information Retrieval Conference (ISMIR 2022)

Published
2022

9. A Novel 1D State Space for Efficient Music Rhythmic Analysis

Author

Heydari, Mojtaba, McCallum, Matthew, Ehmann, Andreas, and Duan, Zhiyao

Subjects
Computer Science - Sound, Computer Science - Information Retrieval, Electrical Engineering and Systems Science - Audio and Speech Processing, Electrical Engineering and Systems Science - Signal Processing
Abstract

Inferring music time structures has a broad range of applications in music production, processing and analysis. Scholars have proposed various methods to analyze different aspects of time structures, such as beat, downbeat, tempo and meter. Many state-of-the-art (SOFA) methods, however, are computationally expensive. This makes them inapplicable in real-world industrial settings where the scale of the music collections can be millions. This paper proposes a new state space and a semi-Markov model for music time structure analysis. The proposed approach turns the commonly used 2D state spaces into a 1D model through a jump-back reward strategy. It reduces the state spaces size drastically. We then utilize the proposed method for causal, joint beat, downbeat, tempo, and meter tracking, and compare it against several previous methods. The proposed method delivers similar performance with the SOFA joint causal models with a much smaller state space and a more than 30 times speedup., Comment: International Conference on Acoustics, Speech and Signal Processing (ICASSP), May. 2022

Published
2021

10. Learning Sparse Analytic Filters for Piano Transcription

Author

Cwitkowitz, Frank, Heydari, Mojtaba, and Duan, Zhiyao

Subjects
Electrical Engineering and Systems Science - Audio and Speech Processing, Computer Science - Machine Learning, Computer Science - Sound, Electrical Engineering and Systems Science - Signal Processing
Abstract

In recent years, filterbank learning has become an increasingly popular strategy for various audio-related machine learning tasks. This is partly due to its ability to discover task-specific audio characteristics which can be leveraged in downstream processing. It is also a natural extension of the nearly ubiquitous deep learning methods employed to tackle a diverse array of audio applications. In this work, several variations of a frontend filterbank learning module are investigated for piano transcription, a challenging low-level music information retrieval task. We build upon a standard piano transcription model, modifying only the feature extraction stage. The filterbank module is designed such that its complex filters are unconstrained 1D convolutional kernels with long receptive fields. Additional variations employ the Hilbert transform to render the filters intrinsically analytic and apply variational dropout to promote filterbank sparsity. Transcription results are compared across all experiments, and we offer visualization and analysis of the filterbanks., Comment: Sound and Music Computing Conference (SMC) 2022

Published
2021

11. BeatNet: CRNN and Particle Filtering for Online Joint Beat Downbeat and Meter Tracking

Author

Heydari, Mojtaba, Cwitkowitz, Frank, and Duan, Zhiyao

Subjects
Electrical Engineering and Systems Science - Audio and Speech Processing, Computer Science - Artificial Intelligence, Computer Science - Information Retrieval, Computer Science - Machine Learning, Computer Science - Sound, Electrical Engineering and Systems Science - Signal Processing
Abstract

The online estimation of rhythmic information, such as beat positions, downbeat positions, and meter, is critical for many real-time music applications. Musical rhythm comprises complex hierarchical relationships across time, rendering its analysis intrinsically challenging and at times subjective. Furthermore, systems which attempt to estimate rhythmic information in real-time must be causal and must produce estimates quickly and efficiently. In this work, we introduce an online system for joint beat, downbeat, and meter tracking, which utilizes causal convolutional and recurrent layers, followed by a pair of sequential Monte Carlo particle filters applied during inference. The proposed system does not need to be primed with a time signature in order to perform downbeat tracking, and is instead able to estimate meter and adjust the predictions over time. Additionally, we propose an information gate strategy to significantly decrease the computational cost of particle filtering during the inference step, making the system much faster than previous sampling-based methods. Experiments on the GTZAN dataset, which is unseen during training, show that the system outperforms various online beat and downbeat tracking systems and achieves comparable performance to a baseline offline joint method., Comment: 22nd International Society for Music Information Retrieval (ISMIR) Conference Paper, Fall 2021. 8 Pages (Total), 3 Figures, 2 Tables, 1 Algorithm

Published
2021

19. Don't look back: an online beat tracking method using RNN and enhanced particle filtering

Author

Heydari, Mojtaba and Duan, Zhiyao

Subjects
Electrical Engineering and Systems Science - Audio and Speech Processing, Computer Science - Sound
Abstract

Online beat tracking (OBT) has always been a challenging task. Due to the inaccessibility of future data and the need to make inference in real-time. We propose Do not Look back! (DLB), a novel approach optimized for efficiency when performing OBT. DLB feeds the activations of a unidirectional RNN into an enhanced Monte-Carlo localization model to infer beat positions. Most preexisting OBT methods either apply some offline approaches to a moving window containing past data to make predictions about future beat positions or must be primed with past data at startup to initialize. Meanwhile, our proposed method only uses activation of the current time frame to infer beat positions. As such, without waiting at the beginning to receive a chunk, it provides an immediate beat tracking response, which is critical for many OBT applications. DLB significantly improves beat tracking accuracy over state-of-the-art OBT methods, yielding a similar performance to offline methods., Comment: IEEE International Conference on Acoustics, Speech and Signal Processing, (ICASSP 2021). (ACCEPTED)

Published
2020

22. Occlusion therapy for amblyopia, a historical report from 9th century Persian scholar, Ali ibn Sahl ibn Rabban al-Tabari (838–870 CE).

Author

Tajik, Narges, Talebnejad, Mohammad Reza, and Heydari, Mojtaba

Subjects
HISTORY of medicine, MUSLIM scholars, MEDIEVAL civilization, ISLAMIC civilization, IRANIAN history
Abstract

Introduction: This study reevaluates the historical origins of occlusion therapy for amblyopia, focusing on the contributions of the 9th-century Islamic scholar, Ali ibn Sahl ibn Rabban al-Tabari (838–870 CE). Methods: The investigation delved into al-Tabari's writings, particularly "Firdous al-Hikma," to extract insights into his approach to addressing reduced vision in one eye.Additionally, the study examined subsequent advancements in occlusion therapy by scholars such as Thabit ibn Qurrah and Rhazes, building upon al-Tabari'sfoundational work. Results: Al-Tabari's reports contain significant insights into occlusion therapy for amblyopia, predating commonly attributed origins of the treatment. Within "Firdous al-Hikma," he outlines methods for addressing reduced vision, advocating for the covering of the healthier eye to promote the function of the weaker eye. These findings highlight the pioneering efforts of al-Tabari and his contemporaries in the Islamic civilization and challenge the conventional narrative surrounding the history of occlusion therapy. Subsequent advancements by scholars such as Thabit ibn Qurrah and Rhazes expanded upon al-Tabari's work, advocating for similar therapeutic approaches within the Islamic civilization. Their contributions further solidified the practice of occlusion therapy, laying the groundwork for its continued evolution and refinement in subsequent centuries. Discussion: Al-Tabari's contributions to occlusion therapy underscore the rich heritage of scientific inquiry in theIslamic civilization during the medieval period. This historical perspective sheds light on the diverse contributions to medical knowledge and practice outside of Western contexts and emphasizes the importance of recognizing and honoring these contributions in the broader history of medicine. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

25. Effect of low dose honey on the apoptosis and inflammation gene expression in corneal limbal stem cells and keratocytes and its efficacy as an ophthalmic formulation in the treatment of dry eye: in-vitro and clinical study.

Author

Sanie-Jahromi, Fatemeh, Khaki, Mehdi, Heydari, Mojtaba, Nowroozzadeh, Mohammad Hossein, Akbarizadeh, Amin Reza, Daneshamouz, Saeid, NejatyJahromy, Yaser, Nejabat, Maryam, Mahmoudi, Ahmad, Zareei, Athar, and Nejabat, Mahmood

Published
2024
Full Text
View/download PDF

30. List of contributors

Author

Abia, Rocio, primary, Abouloifa, H., additional, Adriana, Morales-Martínez, additional, Aggarwal, Diwakar, additional, Aggarwal, Vaishali, additional, Alicia, Sánchez-Mendoza, additional, Andreadou, Ioanna, additional, Angeles-Lo´pez, Quetzalli D., additional, Argüelles, Sandro, additional, Asehraou, A., additional, Audi, Namaa, additional, Ayala, Antonio, additional, Ayoub, Nehad M., additional, Badiu, Diana, additional, Badria, Farid A., additional, Barbouti, Alexandra, additional, Batanero, Eva, additional, Batarseh, Yazan S., additional, Baumann, Leslie S., additional, Ben Salah, R., additional, Bermudez, Beatriz, additional, Blanco, Santos, additional, Borras-Linares, Isabel, additional, Brasca, M., additional, Brenes, Manuel, additional, Perez-Calabuig, Ana M., additional, Cancilla, John C., additional, Cano, Mercedes, additional, Carbone, Fabrizio, additional, Carrera-González, María Pilar, additional, Casas, Rosa, additional, Ceccanti, Mauro, additional, Chaldakov, George N., additional, Covas, María-Isabel, additional, Culeddu, Nicola, additional, Cumaoğlu, Ahmet, additional, Curiel, José Antonio, additional, Damiano, Fabrizio, additional, de Castro, Antonio, additional, de Felipe, Félix López, additional, de la Torre, Rafael, additional, de las Rivas, Blanca, additional, Deiana, Pierfrancesco, additional, Dekanski, Dragana, additional, Dettori, Sandro, additional, Di Stefano, Vita, additional, Domínguez-Vías, German, additional, Dore, Antonio, additional, D’hallewin, G., additional, El Sayed, Khalid A., additional, Elgazar, Abdullah A., additional, Emanuelli, Tatiana, additional, Ferraguti, Giampiero, additional, Filigheddu, Maria Rosaria, additional, Fiore, Marco, additional, Fitó, Montserrat, additional, Francisca, Pérez-Severiano, additional, Fujiwara, Yoko, additional, Galaris, Dimitrios, additional, García, Pedro, additional, Ghabbour, N., additional, Giudetti, Anna Maria, additional, Gnoni, Antonio, additional, Gnoni, Gabriele Vincenzo, additional, Goulas, Vlasios, additional, Greco, Antonio, additional, Guclu, Gamze, additional, Haghbeen, Kamahldin, additional, Handjani, Farhad, additional, Heydari, Mojtaba, additional, Hosseini Mazinani, Mehdi, additional, Ishikawa, Tomoko, additional, Iuliano, Luigi, additional, Joel, Jiménez-Gómez, additional, Joshi, Asavari, additional, Juan, M. Emília, additional, Jugreet, Bibi Sharmeen, additional, Kaddoumi, Amal, additional, Kailis, Stanley George, additional, Kanavaros, Panagiotis, additional, Karboune, S., additional, Kelebek, Hasim, additional, Kitsoulis, Panagiotis, additional, Kouka, Paraskevi, additional, Kouretas, Demetrios, additional, Ktari, N., additional, Kumar, Gaurav, additional, Kumar, Manoj, additional, Landete, José María, additional, Lauretti, Elisabetta, additional, Lemus-Conejo, Ana, additional, Lombardo, Luca, additional, Longo, Serena, additional, Pradana-Lopez, Sandra, additional, Lopez, Sergio, additional, Lopez-Millan, Belen, additional, López-López, Antonio, additional, Lozano-Sánchez, Jesús, additional, Madar, Zecharia, additional, Mahomoodally, Mohamad Fawzi, additional, Mañas, Mariano, additional, Martinez-Victoria, Emilio, additional, Martinez-Burgos, Maria Alba, additional, Martínez-Martos, José Manuel, additional, Masre, Siti Fathiah, additional, Medina, Eduardo, additional, Medina, Rafael, additional, Menendez, Javier A., additional, Millan-Linares, Maria C., additional, Mittal, Sonam, additional, Mohammadnejad, Parvin, additional, Molinu, Maria Giovanna, additional, Montaño, Alfredo, additional, Montserrat-de la Paz, Sergio, additional, Muñoz, Mario, additional, Muñoz, Rosario, additional, Muriana, Francisco J.G., additional, Nenadis, N., additional, Nychas, G.-J.E., additional, Ortega-García, Francisca, additional, Ortega-Gomez, Almudena, additional, Pacheco, Yolanda M., additional, Panagou, E.Z., additional, Papoti, V.T., additional, Pariente, Jose Antonio, additional, Parvizi, Mohammad Mahdi, additional, Pathak, Kaveri, additional, Peinado, M. Ángeles, additional, Peragón, Juan, additional, Petrella, Carla, additional, Čabarkapa-Pirkovic, Andrea, additional, Planas, Joana M., additional, Plastina, Pierluigi, additional, Praticò, Domenico, additional, Prieto, Isabel, additional, Rajendram, Rajkumar, additional, Ralli, Massimo, additional, Ramírez-Expósito, María Jesús, additional, Ramírez-Sánchez, Manuel, additional, Rasouli, Hassan, additional, Al Rihani, Sweilem B., additional, Rodríguez, Héctor, additional, Rodríguez-López, Paloma, additional, Rokni, Y., additional, Romero, Concepción, additional, Rosillo, Maria A., additional, Ruiz-Barba, José Luis, additional, Saalaoui, E., additional, Sacanella, Emilio, additional, Sadeer, Nabeelah Bibi, additional, Sak, Katrin, additional, Saki, Maryam, additional, Salimonti, Amelia, additional, Sánchez, Antonio-Higinio, additional, Santona, Mario, additional, Segarra, Ana Belén, additional, Segura-Carretero, Antonio, additional, Selli, Serkan, additional, Sergio, Montes, additional, Sethi, Gautam, additional, Seyedebrahimi, Seyede Sanaz, additional, Shahbaz, Mana, additional, Sharma, Dhvani, additional, Soares, Mario J, additional, Spremo-Potparević, Biljana, additional, Stark, Aliza Hannah, additional, Suroowan, Shanoo, additional, Suvarna, Vasanti, additional, Tahiri, Iasim, additional, Tarani, Luigi, additional, Tassou, C.C., additional, Topalović, Dijana, additional, Torrecilla, José S., additional, Tseti, Ioulia, additional, Tsimidou, M.Z., additional, Tsoumani, Maria, additional, Tuli, Hardeep Singh, additional, Varela, Lourdes M., additional, Veskoukis, Aristidis S., additional, Villalba, Mayte, additional, Weisberg, Edmund M., additional, Yago, Maria Dolores, additional, Yang, Euitaek, additional, Yerer, Mükerrem Betül, additional, Zanwar, Anand, additional, Zelasco, Samanta, additional, and Živković, Lada, additional

Published
2021
Full Text
View/download PDF

35. Contributors

Author

Ahmad, Jamiu Busari, primary, Aisa, Haji Akber, additional, Ajao, Abdulwakeel Ayokun-nun, additional, Ajayi, Ebenezer Idowu O., additional, Aladodo, Raliat Abimbola, additional, Bédard, Alexandra, additional, Behl, Tapan, additional, Bertinato, Jesse, additional, Bljajić, Kristina, additional, Bozidarka, Zaric L., additional, Branislava, Ilinčić, additional, Calderón-Cortés, Elizabeth, additional, Chaubey, Pramila, additional, Cheah, Mark C.C., additional, Cheng, Zhen, additional, Cortés-Rojo, Christian, additional, Dâmaso, Ana R., additional, Daneshfard, Babak, additional, de Piano, Aline, additional, Dong, Yuesheng, additional, Edita, Stokic, additional, El-Darra, Nada, additional, Erejuwa, Omotayo O., additional, Gamboa-Gómez, Claudia I., additional, Gao, Yanhua, additional, Germán-Díaz, Marta, additional, Goh, George B.B., additional, González-Stuart, Armando E., additional, Grammatiki, Maria, additional, Granado-Casas, Minerva, additional, Grover, Madhuri, additional, Guadarrama-López, Ana Laura, additional, Guerrero-Romero, Fernando, additional, Gupta, Jyoti, additional, Harbige, Laurence Steven, additional, Hashempur, Mohammad Hashem, additional, Hasimun, Patonah, additional, Henriksen, Erik J., additional, Heydari, Mojtaba, additional, Ho, Suleen, additional, Hosseini, Shabnam, additional, Hosseinpour-Niazi, Somayeh, additional, Hosseinzadeh, Hossein, additional, Isenovic, Esma R., additional, Jane, Monica, additional, Johnston, Carol S., additional, Kaur, Loveleen, additional, Keim, Ary Prihardhyanto, additional, Ketut Adnyana, I., additional, Kiakubu, Oluwaseun Tope, additional, Kotsa, Kalliopi, additional, Liu, Liu, additional, Ma, Qingling, additional, Madende, Moses, additional, Makkar, Rashita, additional, Martínez-Carrillo, Beatriz Elina, additional, Masquio, Deborah C.L., additional, Masuda, J., additional, Matsuoka, K., additional, Mauricio, Didac, additional, McCullough, Arthur J., additional, McKay, Jenny, additional, Menini, Stefano, additional, Mirmiran, Parvin, additional, Modo, Emmanuel Uchechukwu, additional, Molehin, Olorunfemi Raphael, additional, Montoya-Pérez, Rocío, additional, Moreno-Villares, José Manuel, additional, Mosavat, Seyed Hamdollah, additional, Murali, Raju, additional, Nurain, Ismaila Olarewaju, additional, Obradovic, Milan, additional, Orhan, Didem Deliorman, additional, Orhan, Nilufer, additional, Ostovar, Mohadeseh, additional, Pal, Sebely, additional, Pesce, Carlo, additional, Pinheiro, Marcelo Maia, additional, Pinheiro, Felipe Moura Maia, additional, Pinto, Donato, additional, Pradeep, Seetur R., additional, Raafat, Karim, additional, Razavi, Bibi Marjan, additional, Richard, Caroline, additional, Rivera, José O., additional, Rodríguez-Morán, Martha, additional, Rodríguez-Orozco, Alain Raimundo, additional, Saavedra-Molina, Alfredo, additional, Sabiu, Saheed, additional, Saleh, Fatima A., additional, Sangave, Preeti C., additional, Schwabl, Herbert, additional, Shah, Karan, additional, Shams, Mesbah, additional, Sharma, Shivali, additional, Shimizu, F., additional, Simental-Mendía, Luis E., additional, Singh, Ashish K., additional, Srinivasan, Subramani, additional, Srinivasan, Krishnapura, additional, Sujarwo, Wawan, additional, Sun, Wenlong, additional, Suvarna, Vasanti, additional, Sweazea, Karen L., additional, Takada, A., additional, Tang, Dan, additional, Valdés-Ramos, Roxana, additional, Vennos, Cécile, additional, Vinothkumar, Veerasamy, additional, Wei, Yuanyuan, additional, Xin, Xuelei, additional, Xing, Yan, additional, Yili, Abulimiti, additional, Zhang, Bowei, additional, Zhang, Taojing, additional, Zoran, Stosic, additional, and Zovko Končić, Marijana, additional

Published
2019
Full Text
View/download PDF

42. Serum androgens and prolactin levels in patients with keratoconus.

Author

Jamali, Hossein, Heydari, Mojtaba, Masihpour, Nasrin, Khosravi, Amir, Zare, Mousa, Shams, Mesbah, and Omrani, Gholamhossein Ranjbar

Subjects
*KERATOCONUS, *ANDROGENS, *PROLACTIN, *SEX hormones, *LUTEINIZING hormone
Abstract

There is growing evidence for the involvement of sex hormones in the pathogenesis of keratoconus. This study aimed to evaluate serum androgen and prolactin levels in patients suffering from keratoconus. One hundred and two subjects were enrolled in the keratoconus (76 patients) and control (26 subjects) groups in a cross-sectional survey. Topographic evaluation of the cornea was undertaken for all enrolled participants. Serum testosterone, dehydroepiandrosterone sulphate (DHEAS), prolactin (PRL), luteinising hormone (LH), and follicle-stimulating hormone (FSH) were measured in all subjects. There was no significant difference in demographic characteristics between the study groups. Significantly higher mean serum levels of DHEAS (3.71 ± 2.23 vs. 2.53 ± 1.77 µg/mL; P = 0.009) and T (6.18 ± 3.80 vs. 1.57 ± 1.76 ng/mL; P < 0.001) were observed in men with keratoconus compared to controls. In females, there were also higher mean levels of DHEAS (2.40 ± 1.57 vs. 2.18 ± 0.72 µg/mL; P = 0.355) and T (0.78 ± 0.96 vs. 0.32 ± 0.13 ng/mL; P < 0.001) in patients with keratoconus but only T level reached the statistically significant level of difference. Also, the mean serum PRL level was significantly higher in women with keratoconus compared to control (13.33 ± 17.85 vs. 4.63 ± 3.10 ng/mL; P < 0.001). There was no significant difference between serum FSH and LH levels between study groups. In patients with keratoconus, serum PRL in females and serum androgen levels in both genders are elevated. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

47. Anti-anxiety Properties of Selected Medicinal Plants

Author

Khan, Asmatullah, primary, Akram, Muhammad, additional, Thiruvengadam, Muthu, additional, Daniyal, Muhammad, additional, Zakki, Shahbaz Ahmad, additional, Munir, Naveed, additional, Zainab, Rida, additional, Heydari, Mojtaba, additional, Mosavat, Seyed Hamdollah, additional, Rebezov, Maksim, additional, and Shariati, Mohammad Ali, additional

Published
2022
Full Text
View/download PDF

48. Crocin as a vision supplement.

Author

Heydari, Mojtaba, zare, Mousa, Badie, Mohammad Reza, Watson, Ronald Ross, Talebnejad, Mohammad Reza, and Afarid, Mehrdad

Subjects
*CROCIN, *MACULAR degeneration, *DIABETIC retinopathy, *RETINAL degeneration, *EYE diseases
Abstract

Crocin is a natural ingredient of saffron (Crocus sativus L.) flower that has shown potential for application as a supplement in eye health and preserving vision. Crocin has been examined for its potential to treat various eye diseases such as glaucoma, macular dystrophies, diabetic retinopathy, and age-related macular degeneration. This review briefly discusses the role of crocin in different eye diseases. The underlying pathophysiological pathways involved in the effect of crocin on ophthalmic diseases are also reviewed. Preclinical evidence shows the cytoprotective, antioxidative, anti-inflammatory, and blood-flow enhancing effects of crocin in retinal tissue. Crocin also affects the retinal pathologies by activating PI3K/Akt and inhibiting NF-κB signalling pathways. Clinical evidence suggests that crocin improves outcomes in patients with retinal degenerations, retinal dystrophies, and glaucoma. Overall, crocin can be suggested as a potential vision supplement in healthy populations and patients with eye diseases. However, more clinical studies with larger sample sizes and longer follow-up durations are needed to confirm the current evidence. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

49. ESL Writers' Performance in Exam and Non-Exam Academic Writing Settings.

Author

Marefat, Fahimeh and Heydari, Mojtaba

Subjects
ACADEMIC discourse, WRITING processes, LINGUISTIC analysis, PERFORMANCES, AUTHORS, INTERNATIONAL English Language Testing System
Abstract

With the growing access to new types of reference tools, today's L2 writers have a plethora of choices when completing an academic writing assignment. Such resources are absent in most high-stakes academic writing exams, making the two situations dissimilar. Aimed to compare the performances of ESL writers in Exam and Non-exam (real-life) academic writing situations, the present study recruited seven ESL university students who had previously taken an IELTS test. The students completed two analogous writing tasks: an exam-setting and a Non-exam writing test which aimed to simulate the real-life setting. Coh-Metrix analysis of the linguistic features of syntactic complexity, lexical sophistication, and text cohesion of the writings suggested that the students improved the textual quality of their writings in real-life academic writing situation. In addition, FACETS analysis of the quality of the writings, as assessed by the human raters, showed that the students did not benefit equally from the merits of the real-life settings compared to the Exam settings. The findings suggest that the students spent different amounts of time and used different types of queries to consult with external resources. Students' background training and writing strategies can highly affect their performance in real-life academic writing compared to the writing exams, warning against the validity of such tests. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

50. A Novel 1d State Space for Efficient Music Rhythmic Analysis

Author

Heydari, Mojtaba, McCallum, Matthew, Ehmann, Andreas, and Zhiyao Duan

Subjects
Signal Processing (eess.SP), FOS: Computer and information sciences, Sound (cs.SD), Audio and Speech Processing (eess.AS), State space, semi-Markov process, jump- back reward, inference optimization, music time structure analysis, FOS: Electrical engineering, electronic engineering, information engineering, Electrical Engineering and Systems Science - Signal Processing, Information Retrieval (cs.IR), Computer Science - Sound, Computer Science - Information Retrieval, Electrical Engineering and Systems Science - Audio and Speech Processing
Abstract

Inferring music time structures has a broad range of applications in music production, processing and analysis. Scholars have proposed various methods to analyze different aspects of time structures, such as beat, downbeat, tempo and meter. Many state-of-the-art (SOFA) methods, however, are computationally expensive. This makes them inapplicable in real-world industrial settings where the scale of the music collections can be millions. This paper proposes a new state space and a semi-Markov model for music time structure analysis. The proposed approach turns the commonly used 2D state spaces into a 1D model through a jump-back reward strategy. It reduces the state spaces size drastically. We then utilize the proposed method for causal, joint beat, downbeat, tempo, and meter tracking, and compare it against several previous methods. The proposed method delivers similar performance with the SOFA joint causal models with a much smaller state space and a more than 30 times speedup., Git Repo: https://github.com/mjhydri/1D-StateSpace

Published
2022
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results