Now showing items 1-20 of 20

    • A Regression Model of Recurrent Deep Neural Networks for Noise Robust Estimation of the Fundamental Frequency Contour of Speech 

      Kato, Akihiro; Kinnunen, Tomi (ISCA, 2018)
      The fundamental frequency (F0) contour of speech is a key aspect to represent speech prosody that finds use in speech and spoken language analysis such as voice conversion and speech synthesis as well as speaker and language ...
    • Age-Related Voice Disguise and its Impact in Speaker Verification Accuracy 

      Gonzalez Hautamäki, Rosa; Sahidullah, Md; Kinnunen, Tomi; Hautamäki, Ville (ISCA (the International Speech Communication Association), 2016)
      This study focuses in the impact of age-related intentional voice modification, or age disguise, on the performance of automatic speaker verification (ASV) systems. The data collected for this study includes 60 native ...
    • The ASVspoof 2017 Challenge: Assessing the Limits of Replay Spoofing Attack Detection 

      Kinnunen, Tomi; Sahidullah, Md; Delgado, Hector; Todisco, Massimiliano; Evans, Nicholas; Yamagishi, Junichi; Lee, Kong Aik (ISCA (the International Speech Communication Association), 2017)
      The ASVspoof initiative was created to promote the development of countermeasures which aim to protect automatic speaker verification (ASV) from spoofing attacks. The first community-led, common evaluation held in 2015 ...
    • Classifiers for Synthetic Speech Detection: A Comparison 

      Hanilci, Cemal; Kinnunen, Tomi; Sahidullah, Md; Sizov, Aleksandr (ISCA (the International Speech Communication Association), 2015)
      Automatic speaker verification (ASV) systems are highly vulnerable against spoofing attacks, also known as imposture. With recent developments in speech synthesis and voice conversion technology, it has become important ...
    • A Comparison of Features for Synthetic Speech Detection 

      Sahidullah, Md; Kinnunen, Tomi; Hanilci, Cemal (ISCA (the International Speech Communication Association), 2015)
      The performance of biometric systems based on automatic speaker recognition technology is severely degraded due to spoofing attacks with synthetic speech generated using different voice conversion (VC) and speech synthesis ...
    • Discriminative multi-domain PLDA for speaker verification 

      Sholokhov, Alexey; Kinnunen, Tomi; Cumani, Sandro (Institute of Electrical and Electronics Engineers (IEEE), 2016)
      Domain mismatch occurs when data from application-specific target domain is related to, but cannot be viewed as iid samples from the source domain used for training speaker models. Another problem occurs when several ...
    • Effects of Gender Information in Text-Independent and Text-Dependent Speaker Verification 

      Kanervisto, Anssi; Sahidullah, Md; Vestman, Ville; Hautamäki, Ville; Kinnunen, Tomi (Institute of Electrical and Electronics Engineers (IEEE), 2017)
      It is well-known that for speaker recognition task, gender-dependent acoustic modeling performs better than gender-independent modeling. The practice is to use the gender ground-truth and to train gender-dependent models. ...
    • HAPPY Team Entry to NIST OpenSAD Challenge: A Fusion of Short-Term Unsupervised and Segment i-Vector Based Speech Activity Detectors 

      Kinnunen, Tomi; Sholokhov, Alexey; Khoury, Elie; Thomsen, Dennis; Sahidullah, Md; Tan, Zheng-Hua (ISCA (the International Speech Communication Association), 2016)
      Speech activity detection (SAD), the task of locating speech segments from a given recording, remains challenging under acoustically degraded conditions. In 2015, National Institute of Standards and Technology (NIST) ...
    • Improving Speaker Verification Performance in Presence of Spoofing Attacks Using Out-of-Domain Spoofed Data 

      Sarkar, Archintya; Sahidullah, Md; Tan, Zheng-Hua; Kinnunen, Tomi (ISCA (the International Speech Communication Association), 2017)
      Automatic speaker verification (ASV) systems are vulnerable to spoofing attacks using speech generated by voice conversion and speech synthesis techniques. Commonly, a countermeasure (CM) system is integrated with an ASV ...
    • Integrated Spoofing Countermeasures and Automatic Speaker Verification: an Evaluation on ASVspoof 2015 

      Sahidullah, Md; Delgado, Hector; Todisco, Massimiliano; Yu, Hong; Kinnunen, Tomi; Evans, Nicholas; Tan, Zheng-Hua (ISCA (the International Speech Communication Association), 2016)
      It is well known that automatic speaker verification (ASV) systems can be vulnerable to spoofing. The community has responded to the threat by developing dedicated countermeasures aimed at detecting spoofing attacks. ...
    • Introduction to voice presentation attack detection and recent advances 

      Sahidullah, Md; Delgado, Hector; Todisco, Massimiliano; Kinnunen, Tomi; Evans, Nicholas; Yamagishi, Junichi; Lee, Kong-Aik (Springer International Publishing, 2019)
      Over the past few years significant progress has been made in the field of presentation attack detection (PAD) for automatic speaker recognition (ASV). This includes the development of new speech corpora, standard evaluation ...
    • Local spectral variability features for speaker verification 

      Sahidullah, Md; Kinnunen, Tomi (Elsevier BV, 2015)
      Speaker verification techniques neglect the short-time variation in the feature space even though it contains speaker related attributes. We propose a simple method to capture and characterize this spectral variation through ...
    • RedDots Replayed: A New Replay Spoofing Attack Corpus for Text-Dependent Speaker Verification Research 

      Kinnunen, Tomi; Sahidullah, Md; Falcone, Mauro; Costantini, Luca; Gonzalez-Hautamäki, Rosa; Thomsen, Dennis; Sarkar, Archintya; Tan, Zheng-Hua; Delgado, Hector; Todisco, Massimiliano; Evans, Nicholas; Hautamäki, Ville; Lee, Kong Aik (Institute of Electrical and Electronics Engineers (IEEE), 2017)
      This paper describes a new database for the assessment of automatic speaker verification (ASV) vulnerabilities to spoofing attacks. In contrast to other recent data collection efforts, the new database has been designed ...
    • Robust Speaker Recognition with Combined Use of Acoustic and Throat Microphone Speech 

      Sahidullah, Md; Gonzalez Hautamäki, Rosa; Lehmann, Thomsen Dennis Alexander; Kinnunen, Tomi; Tan, Zheng-Hua; Hautamäki, Ville; Parts, Robert; Pitkänen, Martti (ISCA (the International Speech Communication Association), 2016)
      Accuracy of automatic speaker recognition (ASV) systems degrades severely in the presence of background noise. In this paper, we study the use of additional side information provided by a body-conducted sensor, throat ...
    • Robust Voice Liveness Detection and Speaker Verification Using Throat Microphones 

      Sahidullah, Md; Thomsen, Dennis Alexander Lehmann; Gonzalez Hautamäki, Rosa; Kinnunen, Tomi; Tan, Zheng-Hua; Parts, Robert; Pitkänen, Martti (Institute of Electrical and Electronics Engineers (IEEE), 2017)
      While having a wide range of applications, automatic speaker verification (ASV) systems are vulnerable to spoofing attacks, in particular, replay attacks that are effective and easy to implement. Most prior work on detecting ...
    • Speaker Recognition For Speech Under Face Cover 

      Saeidi, Rahim; Niemi, Tuija; Karppelin, Hanna; Pohjalainen, Jouni; Kinnunen, Tomi; Alku, Paavo (ISCA (the International Speech Communication Association), 2015)
      Speech under face cover constitute a case that is increasingly met by forensic speech experts. Wearing face cover mostly happens when an individual strives to conceal his or her identity. Based on the material of face cover ...
    • Speaker recognition from whispered speech: a tutorial survey and an application of time-varying linear prediction 

      Vestman, Ville; Gowda, Dhananjaya; Sahidullah, Md; Alku, Paavo; Kinnunen, Tomi (Elsevier BV, 2018)
      From the available biometric technologies, automatic speaker recognition is one of the most convenient and accessible ones due to abundance of mobile devices equipped with a microphone, allowing users to be authenticated ...
    • Time-Varying Autoregressions for Speaker Verification in Reverberant Conditions 

      Vestman, Ville; Gowda, Dhananjaya; Sahidullah, Md; Alku, Paavo; Kinnunen, Tomi (ISCA (the International Speech Communication Association), 2017)
      Automatic speaker verification (ASV) systems are vulnerable to spoofing attacks using speech generated by voice conversion and speech synthesis techniques. Commonly, a countermeasure (CM) system is integrated with an ASV ...
    • Utterance Verification for Text-Dependent Speaker Recognition: a Comparative Assessment Using the RedDots Corpus 

      Kinnunen, Tomi; Sahidullah, Md; Kukanov, Ivan; Delgado, Hector; Todisco, Massimiliano; Sarkar, Achintya; Thomsen, Nicolai Baek; Hautamäki, Ville; Evans, Nicholas; Tan, Zheng-Hua (ISCA (the International Speech Communication Association), 2016)
      Text-dependent automatic speaker verification naturally calls for the simultaneous verification of speaker identity and spoken content. These two tasks can be achieved with automatic speaker verification (ASV) and utterance ...
    • Waveform to Single Sinusoid Regression to Estimate the F0 Contour from Noisy Speech Using Recurrent Deep Neural Networks 

      Kato, Akihiro; Kinnunen, Tomi (International Speech Communication Association, 2018)
      The fundamental frequency (F0) represents pitch in speech that determines prosodic characteristics of speech and is needed in various tasks for speech analysis and synthesis. Despite decades of research on this topic, F0 ...