PIETRO LAFACE

Download the vcard Photo

Former faculty

+39 0110907004 / 7004 (DAUIN)

Personal web site

Research groups SRG - Speech Recognition Group
Research projects

Funded by competitive calls

  • CONSORTIUM AGREEMENT DIVINES - DIAGNOSTIC AND INTRINSIC VARIABILITIES IN NATURAL SPEECH, (2004-) - Responsabile Scientifico

    UE-funded research

    View project record on CORDIS

    Abstract

    When one considers human performance as our target, universal automatic recognition of speech is far from a solved problem. This seems to be related by a large amount to feature extraction, modelling and adaptability weaknesses, as discussed in recognized publications. Strikingly, these weaknesses remain fully in the case of clean speech in known conditions, emphasizing deficiencies in dealing with intrinsic speech variabilities and extracting information form the signal itself. This has however been partly hidden by the more pressing problem of making state-of-the-art systems usable in real noisy situations, under constrained tasks, with the implicit target of reaching 'clean speech' performance, with deserved success.The goal of DIVINES is to develop some new knowledge towards renewed feature extraction and modelling techniques that would have better capacities, particularly in handling speech intrinsic variabilities. First, human and machine performance and the effect of intrinsic variabilities will be compared based on a diagnostic procedure. The outcomes of this analysis will then be exploited to target feature extraction, acoustic and lexical modelling. Compatibility with techniques dealing with noise and integration within current systems are also part of the objectives.The project is relevant to the 'multimodal interfaces' objective as it concerns more accurate and adaptable recognition of spoken language. This is central to the concept of multimodal man-machine interaction where the speech understanding service is likely to remain an independent component in a modular design. Advances in this field could be decisive in realizing the vision of natural interactivity.

    Countries

    • Canada
    • Belgio
    • Germania
    • Italia
    • Francia

    Institutes/Companies

    • THE ROYAL INSTITUTION FOR THE ADVANCEMENT OF LEARNING (MCGILL UNIVERSITY)
    • BABEL TECHNOLOGIES S.A.
    • CARL VON OSSIETZKY UNIVERSITAET OLDENBURG
    • LOQUENDO SPA
    • UNIVERSITE D'AVIGNON ET DU PAYS-VAUCLUSE
    • POLITECNICO DI TORINO
    • INSTITUT EURECOM
    • FRANCE TELECOM SA
  • BBFOR2 - BAYESIAN BIOMETRICS FOR FORENSICS, (2010-2013) - Responsabile Scientifico

    UE-funded research - VII PQ - People

    View project record on CORDIS

    Abstract

    With various forms of biometric technologies becoming available, there is a growing need for scientists who are able to assess the merits of these technologies when applied to forensics. The Marie Curie ITN `Bayesian Biometrics for Forensics,' or BBfor2, will provide a training infrastructure that will educate Early Stage Researchers in the core biometric technologies of speaker, face and fingerprint recognition, as well as the forensic aspects of these technologies. According to modern interpretation of evidence in court, biometric evidence must be presented as likelihood ratios. The calibration of likelihood ratios of individual behavioural and physical biometrics and of combinations of biometric modalities, including measures of the quality of the traces, is a unifying topic in all research projects in this Network. The training of ESRs will be realized as individual PhD projects at various research labs, including a forensic institute. Apart from training at their host institute and secondments with other network partners, the ESRs will receive training in dedicated Summer Schools on Biometric Signal Processing, Bayesian Techniques in Forensic Applications and Legal Issues in Forensic Applications. The Network combines 8 European Universities and a leading Forensic Institute; it is augmented by a biometric industrial and a research institute, where secondments of the ESRs will take place.

    Countries

    • Paesi Bassi
    • Regno Unito
    • Svizzera
    • Italia
    • Svezia
    • Spagna
    • Belgio

    Institutes/Companies

    • UNIVERSITEIT TWENTE
    • UNIVERSITY OF YORK
    • FONDATION DE L'INSTITUT DE RECHERCHE IDIAP
    • POLITECNICO DI TORINO
    • HOGSKOLAN I HALMSTAD
    • UNIVERSIDAD AUTONOMA DE MADRID
    • KATHOLIEKE UNIVERSITEIT LEUVEN
    • Netherlands Forensic Institute

    Departments

    • Dipartimento di Automatica Informatica
  • DIVINES - DIAGNOSTIC AND INTRINSIC VARIABILITIES IN NATURAL SPEECH, (2004-2007) - Responsabile Scientifico

    UE-funded research

    View project record on CORDIS

    Abstract

    When one considers human performance as our target, universal automatic recognition of speech is far from a solved problem. This seems to be related by a large amount to feature extraction, modelling and adaptability weaknesses, as discussed in recognized publications. Strikingly, these weaknesses remain fully in the case of clean speech in known conditions, emphasizing deficiencies in dealing with intrinsic speech variabilities and extracting information form the signal itself. This has however been partly hidden by the more pressing problem of making state-of-the-art systems usable in real noisy situations, under constrained tasks, with the implicit target of reaching 'clean speech' performance, with deserved success.The goal of DIVINES is to develop some new knowledge towards renewed feature extraction and modelling techniques that would have better capacities, particularly in handling speech intrinsic variabilities. First, human and machine performance and the effect of intrinsic variabilities will be compared based on a diagnostic procedure. The outcomes of this analysis will then be exploited to target feature extraction, acoustic and lexical modelling. Compatibility with techniques dealing with noise and integration within current systems are also part of the objectives.The project is relevant to the 'multimodal interfaces' objective as it concerns more accurate and adaptable recognition of spoken language. This is central to the concept of multimodal man-machine interaction where the speech understanding service is likely to remain an independent component in a modular design. Advances in this field could be decisive in realizing the vision of natural interactivity.

    Countries

    • Canada
    • Belgio
    • Germania
    • Italia
    • Francia

    Institutes/Companies

    • THE ROYAL INSTITUTION FOR THE ADVANCEMENT OF LEARNING (MCGILL UNIVERSITY)
    • BABEL TECHNOLOGIES S.A.
    • CARL VON OSSIETZKY UNIVERSITAET OLDENBURG
    • LOQUENDO SPA
    • UNIVERSITE D'AVIGNON ET DU PAYS-VAUCLUSE
    • POLITECNICO DI TORINO
    • INSTITUT EURECOM
    • FRANCE TELECOM SA

    Departments

    • Dipartimento di Automatica Informatica

Funded by commercial contracts

  • Speaker recognition using DNN for exploiting phonetic information, (2017-2017) - Responsabile Scientifico

    Commercial Research

    Countries

    • ITALIA
    • STATI UNITI D'AMERICA

    Institutes/Companies

    • NUANCE COMMUNICATIONS, INC.

    Departments

  • Speaker recognition using DNN for exploiting phonetic information, (2016-2016) - Responsabile Scientifico

    Commercial Research

    Countries

    • ITALIA
    • STATI UNITI D'AMERICA

    Institutes/Companies

    • NUANCE COMMUNICATIONS, INC.

    Departments