Vitalii Brydinskyi

Mr. Vitalii Brydinskyi

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
13 February 2023 in Sensors
Verified
Journal Article
Open access
PDF file
VKVolodymyr Khoma
Volodymyr Khoma
YKYuriy Khoma
Yuriy Khoma
VBVitalii Brydinskyi
Vitalii Brydinskyi
AKAlexander Konovalov
Alexander Konovalov
Diarization is an important task when work with audiodata is executed, as it provides a solution to the problem related to the need of dividing one analyzed call recording into several speech recordings, each of which belongs to one speaker. Diarization systems segment audio recordings by defining the time boundaries of utterances, and typically use unsupervised methods to group utterances belonging to individual speakers, but do not answer the question “who is speaking?” On the other hand, there are biometric systems that identify individuals on the basis of their voices, but such systems are designed with the prerequisite that only one speaker is present in the analyzed audio recording. However, some applications involve the need to identify multiple speakers that interact freely in an audio recording. This paper proposes two architectures of speaker identification systems based on a combination of diarization and identification methods, which operate on the basis of segment-level or group-level classification. The open-source PyAnnote framework was used to develop the system. The performance of the speaker identification system was verified through the application of the AMI Corpus open-source audio database, which contains 100 h of annotated and transcribed audio and video data. The research method consisted of four experiments to select the best-performing supervised diarization algorithms on the basis of PyAnnote. The first experiment was designed to investigate how the selection of the distance function between vector embedding affects the reliability of identification of a speaker’s utterance in a segment-level classification architecture. The second experiment examines the architecture of cluster-centroid (group-level) classification, i.e., the selection of the best clustering and classification methods. The third experiment investigates the impact of different segmentation algorithms on the accuracy of identifying speaker utterances, and the fourth examines embedding window sizes. Experimental results demonstrated that the group-level approach offered better identification results were compared to the segment-level approach, and the latter had the advantage of real-time processing.

6 February 2024 in Applied Sciences
Verified
Journal Article
Open access
PDF file
VBVitalii Brydinskyi
Vitalii Brydinskyi
YKYuriy Khoma
Yuriy Khoma
DSDmytro Sabodashko
Dmytro Sabodashko
Michal PodporaMichal Podpora
Michal Podpora
VKVolodymyr Khoma
Volodymyr Khoma
MKMaryna Kostiak
Maryna Kostiak
This research presents an extensive comparative analysis of a selection of popular deep speaker embedding models, namely WavLM, TitaNet, ECAPA, and PyAnnote, applied in speaker verification tasks. The study employs a specially curated dataset, specifically designed to mirror the real-world operating conditions of voice models as accurately as possible. This dataset includes short, non-English statements gathered from interviews on a popular online video platform. The dataset features a wide range of speakers, with 33 males and 17 females, making a total of 50 unique voices. These speakers vary in age from 20 to 70 years old. This variety helps in thoroughly testing speaker verification models. This dataset is especially useful for research on speaker verification with short recordings. It consists of 10 clips for each person, each clip being no longer than 10 s, adding up to 500 recordings in total. The total length of all recordings is about 1 h and 30 min, which averages to roughly 100 s for each speaker. This dataset is a valuable tool for research in speaker verification, particularly for studies involving short audio clips. The performance of these models is evaluated using common biometric metrics such as false acceptance rate (FAR), false rejection rate (FRR), equal error rate (EER) and detection cost function (DCF). The results reveal that the TitaNet and ECAPA models stand out by presenting the lowest EER (1.91% and 1.71%, respectively) and thus exhibiting higher discriminative features, ensuring, on the one hand, a reduction in intra-class distance (the same speaker), and, on the other hand, maximizing the distance between different speaker embeddings. This analysis also highlights the ECAPA model’s advantageous balance of performance and efficiency, achieving an inference time of 69.43 milliseconds, slightly longer than the PyAnnote models. This study not only compares the performance of models but also provides a comparative analysis of respective model embeddings, offering insights into their strengths and weaknesses. The presented findings serve as a foundation for guiding future research in speaker verification, especially in the context of short audio samples or limited data. This may be particularly relevant for applications requiring quick and accurate speaker identification from short voice clips.

20 March 2024
Verified
Report
Closed access
IZIllia Zaiets
Illia Zaiets
VBVitalii Brydinskyi
Vitalii Brydinskyi
DSDmytro Sabodashko
Dmytro Sabodashko
YKYurii Khoma
Yurii Khoma
KRKhrystyna Ruda
Khrystyna Ruda
This paper explores the use of diarization systems which employ advanced machine learning algorithms for the precise detection and separation of different speakers in audio recordings for the implementation of an intruder detection system. Several state-of-the-art diarization models including Nvidia’s NeMo, Pyannote, and SpeechBrain are compared. The performance of these models is evaluated using typical metrics used for the diarization systems, such as Diarization Error Rate (DER) and Jaccard Error Rate (JER). The diarization system was tested on various audio conditions, including noisy environment, clean environment, low amount of speakers, and high amount of speakers. The findings reveal that Pyannote delivers superior performance in terms of diarization accuracy, and thus was used for implementation of the intruder detection system. This system was further evaluated on a custom dataset based on Ukrainian podcasts, and it was found that the system performed with 100% recall and 93.75% precision, meaning that the system has not missed any criminal from the dataset, but could sometimes falsely detect a non-criminal as a criminal. This system proves to be effective and flexible in intruder detection tasks in audio files with different file sizes and different amounts of speakers that are present in these audio files.

29 December 2022 in Information Technology: Computer Science, Software Engineering and Cyber Security
Verified
Journal Article
Closed access
PDF file
VBVitalii Brydinskyi
Vitalii Brydinskyi
У галузі машинного навчання одним із основних напрямків є опрацювання та розпізнавання мовлення. Серед важливих завдань роботи з аудіоданими є діаризація. Діаризація визначає часові межі в аудіозаписі, що належать окремим мовцям, тобто образно кажучи, вирішує задачу «коли хто говорить?». Проте відомі комерційні та відкриті засоби діаризації використовують кластеризацію сегментів, але не відповідають на питання «хто саме зараз говорить?». Існують системи, які ідентифікують мовця, але такі системи розраховані на те, що у аудіозапису присутній є лише один мовець. Тому актуальним завданням є створення системи діаризації, яка уможливлює ідентифікацію багатьох мовців, які довільним чином змінюються у аудіозаписах. У даному дослідженні запропоновано дві архітектури систем ідентифікації мовців на основі діаризації, які працюють відповідно на засадах по-сегментного та по-кластерного аналізу. Для побудови системи використано бібліотеку PyAnnote, що є у відкритому доступі. Верифікація роботи системи ідентифікації мовців здійснювалася на відкритій базі аудіозаписів AMI Corpus, у якому зібрано 100 годин анотованих та транскрибованих аудіо- та відеоданих. Розглянуто різні метрики оцінювання точності діаризації та, враховуючи специфіку розробленої системи, обґрунтовано доцільність застосування такої оцінки як F-Міра ідентифікації. Описано методику проведення досліджень, яка передбачала проведення трьох експериментів. Перший експеримент націлений на дослідження архітектури системи ідентифікації, що базується на по-сегментному аналізі, а другий експеримент – на дослідження архітектури, що застосовує по-кластерний аналіз. Третій експеримент стосується визначення оптимальної тривалості навчальної вибірки для класифікаторів системи ідентифікації. Результати експериментів показали, що по-кластерний підхід показав кращі результати ідентифікації порівняно із по-сегментним підходом. Також встановлено, що оптимальною тривалістю вибірки аудіоданих для тренування класифікатора під кожного конкретного мовця становить 20 секунд.