arXiv subjects

Yanir Marmor

Publications and source records attributed to Yanir Marmor.

7 recordsLinked to original sources

arXiv2026

VoxKnesset: A Large-Scale Longitudinal Hebrew Speech Dataset for Aging Speaker Modeling

Speech processing systems face a fundamental challenge: the human voice changes with age, yet few datasets support rigorous longitudinal evaluation. We introduce VoxKnesset, an open-access dataset of ~2,300 hours of Hebrew parliamentary speech spanning 2009-2025, comprising 393 speakers with recording spans of up to 15 years. Each segment includes aligned transcripts and verified demographic metadata from official parliamentary records. We benchmark modern speech embeddings (WavLM-Large, ECAPA-TDNN, Wav2Vec2-XLSR-1B) on age prediction and speaker verification under longitudinal conditions. Speaker verification EER rises from 2.15\% to 4.58\% over 15 years for the strongest model, and cross-sectionally trained age regressors fail to capture within-speaker aging, while longitudinally trained models recover a meaningful temporal signal. We publicly release the dataset and pipeline to support aging-robust speech systems and Hebrew speech processing.

eess.AS↗

arXiv2025

HPP-Voice: A Large-Scale Evaluation of Speech Embeddings for Multi-Phenotypic Classification

Human speech contains paralinguistic cues that reflect a speaker's physiological and neurological state, potentially enabling non-invasive detection of various medical phenotypes. We introduce the Human Phenotype Project Voice corpus (HPP-Voice): a dataset of 7,188 recordings in which Hebrew-speaking adults count for 30 seconds, with each speaker linked to up to 15 potentially voice-related phenotypes spanning respiratory, sleep, mental health, metabolic, immune, and neurological conditions. We present a systematic comparison of 14 modern speech embedding models, where modern speech embeddings from these 30-second counting tasks outperform MFCCs and demographics for downstream health condition classifications. We found that embedding learned from a speaker identification model can predict objectively measured moderate to severe sleep apnea in males with an AUC of 0.64 $\pm$ 0.03, while MFCC and demographic features led to AUCs of 0.56 $\pm$ 0.02 and 0.57 $\pm$ 0.02, respectively. Additionally, our results reveal gender-specific patterns in model effectiveness across different medical domains. For males, speaker identification and diarization models consistently outperformed speech foundation models for respiratory conditions (e.g., asthma: 0.61 $\pm$ 0.03 vs. 0.56 $\pm$ 0.02) and sleep-related conditions (insomnia: 0.65 $\pm$ 0.04 vs. 0.59 $\pm$ 0.05). For females, speaker diarization models performed best for smoking status (0.61 $\pm$ 0.02 vs 0.55 $\pm$ 0.02), while Hebrew-specific models performed best (0.59 $\pm$ 0.02 vs. 0.58 $\pm$ 0.02) in classifying anxiety compared to speech foundation models. Our findings provide evidence that a simple counting task can support large-scale, multi-phenotypic voice screening and highlight which embedding families generalize best to specific conditions, insights that can guide future vocal biomarker research and clinical deployment.

eess.AS↗

arXiv2024

Non-verbal information in spontaneous speech -- towards a new framework of analysis

Non-verbal signals in speech are encoded by prosody and carry information that ranges from conversation action to attitude and emotion. Despite its importance, the principles that govern prosodic structure are not yet adequately understood. This paper offers an analytical schema and a technological proof-of-concept for the categorization of prosodic signals and their association with meaning. The schema interprets surface-representations of multi-layered prosodic events. As a first step towards implementation, we present a classification process that disentangles prosodic phenomena of three orders. It relies on fine-tuning a pre-trained speech recognition model, enabling the simultaneous multi-class/multi-label detection. It generalizes over a large variety of spontaneous data, performing on a par with, or superior to, human annotation. In addition to a standardized formalization of prosody, disentangling prosodic patterns can direct a theory of communication and speech organization. A welcome by-product is an interpretation of prosody that will enhance speech- and language-related technologies.

cs.SD↗

arXiv2023

ivrit.ai: A Comprehensive Dataset of Hebrew Speech for AI Research and Development

We introduce "ivrit.ai", a comprehensive Hebrew speech dataset, addressing the distinct lack of extensive, high-quality resources for advancing Automated Speech Recognition (ASR) technology in Hebrew. With over 3,300 speech hours and a over a thousand diverse speakers, ivrit.ai offers a substantial compilation of Hebrew speech across various contexts. It is delivered in three forms to cater to varying research needs: raw unprocessed audio; data post-Voice Activity Detection, and partially transcribed data. The dataset stands out for its legal accessibility, permitting use at no cost, thereby serving as a crucial resource for researchers, developers, and commercial entities. ivrit.ai opens up numerous applications, offering vast potential to enhance AI capabilities in Hebrew. Future efforts aim to expand ivrit.ai further, thereby advancing Hebrew's standing in AI research and technology.

eess.AS↗

arXiv2023

Assessing individual risk and the latent transmission of COVID-19 in a population with an interaction-driven temporal model

Interaction-driven modeling of diseases over real-world contact data has been shown to promote the understanding of the spread of diseases in communities. This temporal modeling follows the path-preserving order and timing of the contacts, which are essential for accurate modeling. Yet, other important aspects were overlooked. Various airborne pathogens differ in the duration of exposure needed for infection. Also, from the individual perspective, Covid-19 progression differs between individuals, and its severity is statistically correlated with age. Here, we enrich an interaction-driven model of Covid-19 and similar airborne viral diseases with (a) meetings duration and (b) personal disease progression. The enriched model enables predicting outcomes at both the population and the individual levels. It further allows predicting individual risk of engaging in social interactions as a function of the virus characteristics and its prevalence in the population. We further showed that the enigmatic nature of asymptomatic transmission stems from the latent effect of the network density on this transmission and that asymptomatic transmission has a substantial impact only in sparse communities.

stat.AP↗

arXiv2022

Exploring the effects of activity-preserving time dilation on the dynamic interplay of airborne contagion processes and temporal networks using an interaction-driven model

Contacts' temporal ordering and dynamics are crucial for understanding the transmission of infectious diseases. We introduce an interaction-driven model of an airborne disease over contact networks. We demonstrate our interaction-driven contagion model, instantiated for COVID-19, over history-maintaining random temporal networks and real-world contacts. We use it to evaluate temporal, spatiotemporal, and spatial social distancing policies. We find that a spatial distancing policy is mainly beneficial at the early stages of a disease. We then continue to evaluate temporal social distancing, that is, timeline dilation that maintains the activity potential. We expand our model to consider the exposure to viral load, which we correlate with meetings' duration. Using real-life contact data, we demonstrate the beneficial effect of timeline dilation on overall infection rates. Our results demonstrate that given the same transmission level, there is a decrease in the disease's infection rate and overall prevalence under timeline dilation conditions. We further show that slow-spreading pathogens (i.e., require more prolonged exposure to infect) spread roughly at the same rate as fast-spreading ones in highly active communities. This is surprising since slower pathogens follow paths that include longer meetings, while faster pathogens can potentially follow paths that include shorter meetings, which are more common. Our results demonstrate that the temporal dynamics of a community have a more significant effect on the spread of the disease than the characteristics of the spreading processes.

cs.SI↗

arXiv2021

Image Animation with Keypoint Mask

Motion transfer is the task of synthesizing future video frames of a single source image according to the motion from a given driving video. In order to solve it, we face the challenging complexity of motion representation and the unknown relations between the driving video and the source image. Despite its difficulty, this problem attracted great interests from researches at the recent years, with gradual improvements. The goal is often thought as the decoupling of motion and appearance, which is may be solved by extracting the motion from keypoint movement. We chose to tackle the generic, unsupervised setting, where we need to apply animation to any arbitrary object, without any domain specific model for the structure of the input. In this work, we extract the structure from a keypoint heatmap, without an explicit motion representation. Then, the structures from the image and the video are extracted to warp the image according to the video, by a deep generator. We suggest two variants of the structure from different steps in the keypoint module, and show superior qualitative pose and quantitative scores.

cs.CV↗