A. Lerner

Followers

Following

Co-authors

Public Views

I am a faculty member at the Open University of Israel, the Mathematics and Computer science Department. I'm an interdisciplinary dreamer, eager to combine knowledge from different aspects. I'm fascinated by the discoveries that lie behind speaking in dialogues and free conversations, by following the flow of prosody and acoustic features.

less

Jonathan Bowen

London South Bank University

Andy Chow

City University of Hong Kong

Shamim Ripon

East West University

Peter Breuer

Rossitza Goleva

New Bulgarian University

Dileep Kumar G

Adama Science and Technology University

Mozmin Ahmed

North Eastern Regional Institute of Science and Technology

Antonella Ferrara

University of Pavia

José A . Jiménez-Moscoso

Universidad Nacional de Colombia (National University of Colombia)

Carlos Westphall

Universidade Federal de Santa Catarina - UFSC (Federal University of Santa Catarina)

Interests

Uploads

Papers by A. Lerner

Toward Explainable Automatic Classification of Children's Speech Disorders

Early and adequate diagnosis of speech disorders can contribute to the quality of the treatment a... more Early and adequate diagnosis of speech disorders can contribute to the quality of the treatment and thus to treatment success rates. Using acoustic analysis of the speech of children with speech disorders may aid therapists in the diagnostic process by identifying the acoustic characteristics that are unique to a specific disorder and that distinguish it from normal speech development. The purpose of this work is to investigate the feasibility of the automatic detection of speech disorders based on children’s voices. In this preliminary study, using a dataset of utterance recordings of 24 children whose mother tongue is Hebrew, we propose an automatic system that may facilitate accurate speech assessment by therapists by providing a preliminary diagnosis and explainable insights about the model’s predictions. We built a serial, two-step network that is both powerful and possibly interpretable. The first step can model the complex relations between acoustic features and the speech di...

Prosodic Plot of Dialogues: A Conceptual Framework to Trace Speakers' Role

by A. Lerner and Vered Silber-Varod

In this paper we present a proof-of-concept study which aims to model a conceptual framework to a... more In this paper we present a proof-of-concept study which aims to model a conceptual framework to analyze structures of dialogues. We demonstrate our approach on a specific research question – how speaker’s role is realized along the dialogue? To this end, we use a unified set of Map Task dialogues that are unique in the sense that each speaker participated twice – once as a follower and once as a leader, with the same interlocutor playing the other role. This pairwise setting enables to compare prosodic differences in three facets: Role, Speaker, and Session. For this POC, we analyze a basic set of prosodic features: Talk proportions, pitch, and intensity. To create comparable methodological framework for dialogues, we created three plots of the three prosodic features, in ten equal sized intervals along the session. We used a simple distance measure between the resulting ten-dimensional vectors of each facet for each feature. The prosodic plots of these dialogues reveal the interact...

“Talk to me with left, right, and angles”: Lexical entrainment in spoken Hebrew dialogue

by Vered Silber-Varod and A. Lerner

It has been well-documented for several languages that human interlocutors tend to adapt their li... more It has been well-documented for several languages that human interlocutors tend to adapt their linguistic productions to become more similar to each other. This behavior, known as entrainment, affects lexical choice as well, both with regard to specific words, such as referring expressions, and overall style. We offer what we believe to be the first investigation of such lexical entrainment in Hebrew. Using two existing measures, we analyze Hebrew speakers interacting in a Map Task, a popular experimental setup, and find rich evidence of lexical entrainment. Analyzing speaker pairs by the combination of their genders as well as speakers by their individual gender, we find no clear pattern of differences. We do, however, find that speakers in a position of less power entrain more than those with greater power, which matches theoretical accounts. Overall, our results mostly accord with those for American English, with a lack of entrainment on hedge words being the main difference.

Download

Tracing changes over the course of the conversation: A case study on filled pauses rates

10th International Conference on Speech Prosody 2020, 2020

In this paper, we suggest methods to trace the flow of the use of filled pauses over the course o... more In this paper, we suggest methods to trace the flow of the use of filled pauses over the course of the conversation. Beyond using a normalized time with respect to each session's duration, we calculated the accumulative number of filled pauses and the accumulative number of words per speaker, whenever the speaker has expressed a filled pause or a new word. We then computed the ratio between these values at each such point in time, resulting in relative filled pauses use. The output produces a visualization of the global contour slopes that represents each speaker and the dynamics between the two speakers, in terms of the relative filled pauses use. The dialogues are taken from MaTaCOp, the Hebrew map-task corpus, in which each speaker participated twice, once as a leader and once as a follower. Findings suggest that there are significant differences between two different speakers in the same session. We did not find a difference in the use of filled pauses between the same speaker in different roles. Moreover, the use of filled pauses shows convergence. These findings strengthen previous studies on the influence of sociolinguistic variables on the use of Filled Pauses.

Modelling the dynamics of acoustic gaps between speakers during business-to-business sales calls

Int. J. Big Data Intell., 2020

The Influence of the Interlocutor’s Gender on the Speaker’s Role Identification

by A. Lerner and Vered Silber-Varod

Speech and Computer

Is It a Filler or a Pause? A Quantitative Analysis of Filled Pauses in Hebrew

by A. Lerner and Vered Silber-Varod

Speech and Computer

MMM: multi-channel TDMA with MPR capabilities for MANETs

Download

FairE9: fair file distribution over mesh-only peer-to-peer

Peer-to-peer (P2P) networks are in the spotlight due to the wide-spreading file-sharing applicati... more Peer-to-peer (P2P) networks are in the spotlight due to the wide-spreading file-sharing applications. Many file-distributing algorithms have been suggested and implemented. The various solutions need to cope with a heterogeneous and unstable environment, where peers can arrive and depart at a high rate (churn). Sometimes cooperation cannot be assumed. These issues make the structured attitude less practical. Even some of

Analysis of silences in unbalanced dialogues : the effect of genre and role

This study examines the diversity of silences in unbalanced dialogues, i.e. dialogues between spe... more This study examines the diversity of silences in unbalanced dialogues, i.e. dialogues between speakers with different participation levels: responder and reporter. We examined two genres: therapeutic sessions and private dialogues that are based on this responder-reporter structure. When looking at silences versus speech ratios, we found no differences between the genres nor between the roles. However, when grouping the silences by their types: Pauses (intra-speaker silences), gaps (interspeakers’ silences) and silences that occur in the vicinity of speech overlaps, we found that the silence duration of pauses are role dependent in both genres, while the silence duration of gaps were found genre dependent, but not role dependent. Moreover, speech rate was not found genre dependent. It seems that although silences in unbalanced dialogues vary considerably, genre and speaker’s role are influential.

Download

Compass enhanced ORRP for wireless sensor networks

Data routing in wireless sensor networks has attracted much research interest in recent years. Or... more Data routing in wireless sensor networks has attracted much research interest in recent years. Orthogonal Rendezvous Routing Protocol (ORRP) [1] was recently proposed and analyzed for use in wireless mesh networks. The protocol is based on a simple idea that two pairs of orthogonal lines in a plane intersect with a high probability and it utilizes the directional antennas for

Profit maximizing in auctions of public goods

A profit-maximizing auctioneer can provide a public good to a group of agents. Each group member ... more A profit-maximizing auctioneer can provide a public good to a group of agents. Each group member has a private value for the good being provided to the group. We investigate an auction mechanism where the auctioneer provides the good to the group, only if the sum of their bids exceeds a reserve price declared previously by the auctioneer. For the two-bidder case with private values drawn from a uniform distribution we characterize the continuously differentiable symmetric equilibrium bidding functions for the agents, and find the optimal reserve price for the auctioneer when such functions are used by the bidders. We also examine another interesting family of equilibrium bidding functions for this case, with a discrete number of possible bids, and show the relation (in the limit) to the differentiable bidding functions.

Download

A link allocation protocol for mobile multi-hop radio networks

ABSTRACT We present a distributed algorithm for assignment of transmission rights in a mobile mul... more ABSTRACT We present a distributed algorithm for assignment of transmission rights in a mobile multi-hop radio network. The proposed algorithm assigns a timeslot to each link forming a short cyclic TDMA. The resulting assignment allows collision free spatial reuse of the radio channel. The algorithm supports continuous slot assignment adaptation to topological changes while maintaining the collision free property. The adaptation process, which is an integral part of the link assignment algorithm, requires the participation of only the immediate neighbors of the change causing node. The adaptation to topological changes is accomplished in linear time and implemented in the order of their occurence in the network.

A pie allocation among sharing groups

This paper deals with a pie allocation problem to users, who are divided intosharing groups, that... more This paper deals with a pie allocation problem to users, who are divided intosharing groups, that are not necessarily disjoint. The pie is allocated among the groups, rather than the users. The portion of a sharing group is a public good for its members, that is, all of them can enjoy it. A non-cooperative game for allocating the pie and

Download

Entrainment in spoken Hebrew dialogues

by A. Lerner, Vered Silber-Varod, Andreas Weise, and Julia Hirschberg

Journal of Phonetics

The Influence of the Interlocutor’s Gender on the Speaker’s Role Identification

Speech and Computer

Speech prosody as a biosignal for physical pain detection

Speech Prosody 2016, 2016

Obtaining an objective assessment of pain is an important challenge for clinicians. The purpose o... more Obtaining an objective assessment of pain is an important challenge for clinicians. The purpose of this study is to examine the connections between subjective reports of pain and measureable biosignals of human speech prosody, as a step towards coping with this challenge. Patients reporting pain were voice-recorded to attain reports on different levels of pain. Recording was done in the patients' natural environment at the medical center. Features were extracted from the voice-recordings, including features that were exclusively developed for this study. A machine-learning based classification process was performed in order to distinguish between samples with "no significant pain" and with "significant pain" reported. This classification process distinguished well between the two categories. Moreover, features developed during this study improved classification results in comparison to classification based solely on knownfeatures. Results indicate that there is evidence of a connection between measureable biosignal parameters of speech and the simultaneous self-reported pain level. This finding might be useful for developing future methods to more objective assessment of pain.

Download

Automatic Speaker's Role Classification With a Bottom-up Acoustic Feature Selection

GLU 2017 International Workshop on Grounding Language Understanding

The objective of the current study is to automatically identify the role played by the speaker in... more The objective of the current study is to automatically identify the role played by the speaker in a dialogue. By using machine learning procedures over acoustic feature, we wish to automatically trace the footprints of this information through the speech signal. The acoustic feature set was selected from a large statistic-based feature sets including 1,583 dimension features. The analysis is carried out on interactive dialogues of a Map Task setting. The paper first describes the methodology of choosing the 100 most effective attributes among the 1,583 features that were extracted, and then presents the classification results test of the same speaker in two different roles, and a gender-based classification. Results show an average of a 71% classification rate of the role the same speaker played, 65% for all women together and 65% for all men together.

Download

Is It a Filler or a Pause? A Quantitative Analysis of Filled Pauses in Hebrew

by A. Lerner and Vered Silber-Varod

Speech and Computer

Likelihood of persistent carriage of carbapenem-resistant Acinetobacter baumannii on readmission in previously identified carriers

Infection Control & Hospital Epidemiology

Patients with carbapenem-resistant Acinetobacter baumannii-positive clinical cultures during a pr... more Patients with carbapenem-resistant Acinetobacter baumannii-positive clinical cultures during a prior hospitalization were screened using high sensitivity methods upon first readmission. Of 38 patients, 31.6% screened positive; 42% screened positive within 2 months from discharge, and 14% screened positive more than 5 months from discharge. Carriage was persistent up to 285 days.

Toward Explainable Automatic Classification of Children's Speech Disorders