SRG - Speech Recognition Group

The Speech Recognition group covers most aspects of the speech, speaker and language recognition: signal processing, acoustic, phonetic and lexical modeling.

Most relevant scientific contributions: large vocabulary automatic speech recognition, speaker and language recognition systems robust to channel variations.

Most relevant applications in the past years:

• Collaboration to the development of the Loquendo ASR speech recognizer
• Collaboration to the development of an automatic Directory Assistance systems for Telecom Italia
• Collaboration to the development of the Nuance speaker recognition system

Skills

• Pattern recognition
• Machine Learning
• Parallel  Computation
• Speech and Language Processing

Projects and publications

• Selected funded research projects
  • SPEAKER RECOGNITION AND DIARIZATION
    CUMANI SANDRO
    2021 - (Current)
  • SPEAKER RECOGNITION AND DIARIZATION
    CUMANI SANDRO
    2023 - 2023 (Completed)
  • SPEAKER RECOGNITION AND DIARIZATION
    CUMANI SANDRO
    2023 - 2023 (Completed)
  • SPEAKER RECOGNITION AND DIARIZATION
    CUMANI SANDRO
    2022 - 2022 (Completed)
  • SPEAKER RECOGNITION AND DIARIZATION
    CUMANI SANDRO
    2020 - 2020 (Completed)
  • SPEAKER RECOGNITION USING DNNS AND HMMS
    CUMANI SANDRO
    2018 - 2018 (Completed)
• Selected recent publications
  At press time

  1. Leveraging confidence models for identifying challenging data subgroups in speech models
     Proceeding
     

     Koudounas, Alkis; Pastor, Eliana; Mazzia, Vittorio; Giollo, Manuel; Gueudre, Thomas; Reale, Elisa; Attanasio, Giuseppe; Cagliero, Luca; Cumani, Sandro; de Alfaro, Luca; Baralis, Elena; Amberti, Daniele
     In: 2024 IEEE International Conference on Acoustics, Speech and Signal Processing Workshop (ICASSPW)
     IEEE
     2024 IEEE International Conference on Acoustics, Speech and Signal Processing Workshop (ICASSPW) (Seoul, Korea) 14-19 April, 2024
     

  2. Description and analysis of the KPT system for NIST Language Recognition Evaluation 2022
     Proceeding
     

     Sarni, Salvatore; Cumani, Sandro; Siniscalchi, Sabato Marco; Bottino, Andrea
     In: Proceedings of 24th INTERSPEECH Conference
     ISCA
     24th INTERSPEECH Conference (Dublin, Ireland) 20th – 24th August 2023
     pp.5 (pp.1-5)

  2024

  1. Towards Comprehensive Subgroup Performance Analysis in Speech Models
     Article
     

     Koudounas, Alkis; Pastor, Eliana; Attanasio, Giuseppe; Mazzia, Vittorio; Giollo, Manuel; Gueudre, Thomas; Reale, Elisa; Cagliero, Luca; Cumani, Sandro; de Alfaro, Luca; Baralis, Elena; Amberti, Daniele
     IEEE/ACM TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING
     IEEE/ACM
     Vol.32 pp.13 (pp.1468-1480) ISSN:2329-9290 DOI:10.1109/taslp.2024.3363447

  2023

  1. From adaptive score normalization to adaptive data normalization for speaker verification systems
     Proceeding
     

     Cumani, Sandro; Sarni, Salvatore
     In: Proceedings of the 24th INTERSPEECH Conference
     ISCA
     INTERSPEECH 2023 (Dublin (IE)) 20th - 24th August 2023
     pp.5 (pp.5296-5300) DOI:10.21437/Interspeech.2023-266

  2. The Distributions of Uncalibrated Speaker Verification Scores: A Generative Model for Domain Mismatch and Trial-Dependent Calibration
     Article
     

     Cumani, S; Sarni, S
     IEEE/ACM TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING
     IEEE
     Vol.31 pp.16 (pp.2204-2219) ISSN:2329-9290 DOI:10.1109/TASLP.2023.3282096

  2022

  1. Impostor Score Statistics as Quality Measures for the Calibration of Speaker Verification Systems
     Proceeding
     

     Cumani, Sandro; Sarni, Salvatore
     In: Titolo volume non avvalorato
     ISCA
     Odyssey 2022: The Speaker and Language Recognition Workshop (Beijing (CN)) 28 June - 1 July 2022
     pp.8 (pp.25-32) DOI:10.21437/Odyssey.2022-4

  2021

  1. A Generative Model for Duration-Dependent Score Calibration
     Proceeding
     

     Cumani, Sandro; Sarni, Salvatore
     In: Proceedings of Interspeech 2021
     ISCA
     Interspeech 2021 (Brno (Repubblica Ceca)) 30 August - 3 September 2021
     pp.5 (pp.4598-4602) DOI:10.21437/Interspeech.2021-114

  2. Tackling Age-Invariant Face Recognition with Non-Linear PLDA and Pairwise SVM
     Article
     

     Negri, Pablo; Cumani, Sandro; Bottino, Andrea
     IEEE ACCESS
     IEEE
     Vol.9 pp.16 (pp.40649-40664) ISSN:2169-3536 DOI:10.1109/ACCESS.2021.3063819

  3. On the Distribution of Speaker Verification Scores: Generative Models for Unsupervised Calibration
     Article
     

     Cumani, S.
     IEEE/ACM TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING
     IEEE
     Vol.29 pp.16 (pp.547-562) ISSN:2329-9290 DOI:10.1109/TASLP.2020.3040103

  4. Increasing Naturalness and Flexibility in Spoken Dialogue Interaction
     Edited by
     

     Marchi, Erik; Siniscalchi, Sabato Marco; Cumani, Sandro; Salerno, Valerio Mario; Li, Haizhou
     LECTURE NOTES IN ELECTRICAL ENGINEERING
     Springer
     Vol.714 pp.453 ISSN:1876-1119 ISBN:9789811593222 DOI:10.1007/978-981-15-9323-9

  2020

  1. Special Issue on Advances in Deep Learning
     Article
     

     Gragnaniello, Diego; Bottino, Andrea; Cumani, Sandro; Kim, Wonjoon
     APPLIED SCIENCES
     MDPI
     Vol.10 pp.6 (pp.3172-3177) ISSN:2076-3417 DOI:10.3390/app10093172

  2019

  1. Normal variance-mean mixtures for unsupervised score calibration
     Proceeding
     

     Cumani, S.
     INTERSPEECH
     In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
     International Speech Communication Association
     20th Annual Conference of the International Speech Communication Association: Crossroads of Speech and Language, INTERSPEECH 2019 (Graz (AUT)) 2019
     Vol.2019 pp.5 (pp.401-405) ISSN:2308-457X DOI:10.21437/Interspeech.2019-1609

  2. Exact memory–constrained UPGMA for large scale speaker clustering
     Article
     

     Cumani, S.; Laface, P.
     PATTERN RECOGNITION
     Elsevier
     Vol.95 pp.12 (pp.235-246) ISSN:0031-3203 DOI:10.1016/j.patcog.2019.06.018

  3. Tied Normal Variance-Mean Mixtures for Linear Score Calibration
     Proceeding
     

     Cumani, Sandro; Laface, Pietro
     In: Proceedings of the 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
     IEEE
     2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (Brighton (UK)) 12-17 May 2019
     pp.5 (pp.6121-6125) ISBN:9781479981311 DOI:10.1109/ICASSP.2019.8683379

  4. Assessing Transfer Learning on Convolutional Neural Networks for patch--based Fingerprint Liveness Detection
     Book chapter
     

     Toosi, Amirhosein; Cumani, Sandro; Bottino, Andrea
     STUDIES IN COMPUTATIONAL INTELLIGENCE
     Computational Intelligence
     Springer
     Vol.829 pp.17 (pp.263-279) ISSN:1860-949X ISBN:9783030164683 DOI:10.1007/978-3-030-16469-0_14

  2018

  1. Analysis of BUT-PT Submission for NIST LRE 2017
     Proceeding
     

     Plchot, Oldřich; Matějka, Pavel; Novotný, Ondřej; Cumani, Sandro; Lozano-Diez, Alicia; Slavíček, Josef; Diez, Mireia; Grézl, František; Glembek, Ondřej; Kamsali, Mounika; Silnova, Anna; Burget, Lukáš; Ondel, Lucas; Kesiraju, Santosh; Rohdin, Johan
     In: Proceedings of Odyssey 2018 The speaker and Language Recognition Workshop
     ISCA
     Odyssey 2018 The speaker and Language Recognition Workshop (Les Sables d’Olonne, Francia) 26 - 29 Giugno 2018
     pp.7 (pp.47-53) DOI:10.21437/Odyssey.2018-7

  2. Scoring heterogeneous speaker vectors using nonlinear transformations and tied PLDa models
     Article
     

     Cumani, Sandro; Laface, Pietro
     IEEE/ACM TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING
     Institute of Electrical and Electronics Engineers Inc.
     Vol.26 pp.15 (pp.995-1009) ISSN:2329-9290 DOI:10.1109/TASLP.2018.2806305

  3. Speaker Recognition Using e–Vectors
     Article
     

     Cumani, Sandro; Laface, Pietro
     IEEE/ACM TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING
     IEEE Signal Processing Society
     Vol.26 pp.13 (pp.736-748) ISSN:2329-9290 DOI:10.1109/TASLP.2018.2791806

  2017

  1. Nuance - Politecnico di Torino’s 2016 NIST Speaker Recognition Evaluation System
     Proceeding
     

     Colibro, Daniele; Vair, Claudio; Dalmasso, Emanuele; Farrell, Kevin; Karvitsky, Gennady; Cumani, Sandro; Laface, Pietro
     INTERSPEECH
     In: Proceedings of Interspeech 2017
     International Speech Communication Association
     Interspeech 2017 (Stoccolma (Svezia)) 20/08/2018 - 24/08/2017
     pp.5 (pp.1338-1342) ISSN:2308-457X DOI:10.21437/Interspeech.2017-797

  2. Feature Fusion for Fingerprint Liveness Detection: a Comparative Study
     Article
     

     Toosi, Amirhosein; Bottino, Andrea; Cumani, Sandro; Negri, Pablo; Sottile, PIETRO LUCA
     IEEE ACCESS
     IEEE
     Vol.5 pp.13 (pp.23695-23709) ISSN:2169-3536 DOI:10.1109/ACCESS.2017.2763419

  3. Joint estimation of PLDA and nonlinear transformations of speaker vectors
     Article
     

     Cumani, Sandro; Laface, Pietro
     IEEE/ACM TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING
     Institute of Electrical and Electronics Engineers Inc.
     Vol.25 pp.11 (pp.1890-1900) ISSN:2329-9290 DOI:10.1109/TASLP.2017.2724198

  4. CNN Patch-Based Voting for Fingerprint Liveness Detection
     Proceeding
     

     Toosi, Amirhosein; Cumani, Sandro; Bottino, Andrea
     In: Proc. of 9th International Joint Conference on Computational Intelligence (IJJCI 2017)
     INSTICC
     9th International Joint Conference on Computational Intelligence (IJJCI 2017) (Funchal, Madeira Portugal) 1-3 November 2017
     pp.8

  5. E--vectors: JFA and i--vectors revisited
     Proceeding
     

     Cumani, Sandro; Laface, Pietro
     In: IEEE International Conference on Acoustics Speech and Signal Processing ICASSP 2017
     IEEE Signal Processing Society
     IEEE International Conference on Acoustics Speech and Signal Processing ICASSP 2017 (New Orleans, USA) March 5-9, 2017
     pp.5 (pp.5435-5439) ISBN:9781509041169

  6. Nonlinear i-vector transformations for PLDA-based speaker recognition
     Article
     

     Cumani, Sandro; Laface, Pietro
     IEEE/ACM TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING
     IEEE Signal Processing Society
     Vol.25 pp.12 (pp.908-919) ISSN:2329-9290 DOI:10.1109/TASLP.2017.2674966

  2016

  1. BAT System Description for NIST LRE 2015
     Proceeding
     

     Plchot, Oldrich; Matejka, Pavel; Fer, Radek; Glembek, Ondrej; Novotny, Ondrej; Pesan, Jan; Vesely, Karel; Ondel, Lucas; Karafiat, Martin; Grezl, Frantisek; Kesiraju, Santosh; Burget, Lukas; Brummer, Niko; Swart, Albert; Cumani, Sandro; Mallidi, Sri Harish; Li, Ruizhi
     In: Odyssey 2016: The Speaker and Language Recognition Workshop
     ISCA (SPAGNA)
     Odyssey 2016: The Speaker and Language Recognition Workshop (Bilbao, Spain) June 21-24
     pp.8 (pp.166-173)

  2. I–vector transformation and scaling for PLDA based speaker recognition
     Proceeding
     

     Cumani, Sandro; Laface, Pietro
     In: Odyssey 2016 - The Speaker and Language Recognition Workshop
     ISCA (SPAGNA)
     Odyssey 2016 - The Speaker and Language Recognition Workshop (Bilbao (Spain)) 21-24 Giugno 2016
     pp.8 (pp.39-46)

  3. Discriminative Multi-Domain PLDA for Speaker Verification
     Proceeding
     

     Sholokhov, Alexey; Kinnunen, Tomi; Cumani, Sandro
     In: ICASSP 2016
     ICASSP 2016 (Shanghai (Cina)) 20 - 25 Mar 2016
     pp.5 (pp.5030-5034) ISBN:9781479999880

  2015

  1. Exploiting i–vector posterior covariances for short–duration language recognition
     Proceeding
     

     Cumani, Sandro; Plchot, Oldrich; Fer, Radek
     In: Proceedings of Interspeech 2015
     ISCA
     Interspeech 2015 (Dresden (Germany)) 6 - 10 Set 2015
     pp.5 (pp.1002-1006)

  2. Fast Scoring of Full Posterior PLDA Models
     Article
     

     Cumani, Sandro
     IEEE/ACM TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING
     Institute of Electrical and Electronics Engineers Inc.
     Vol.23 pp.10 (pp.2036-2045) ISSN:2329-9290 DOI:10.1109/TASLP.2015.2464678

  3. On Multiview Analysis for Fingerprint Liveness Detection
     Proceeding
     

     Toosi, Amirhosein; Cumani, Sandro; Bottino, ANDREA GIUSEPPE
     In: LNCS
     Springer (GERMANIA)
     CIARP 2015 - XX Iberoamerican Congress on Pattern Recognition (Montevideo, Uruguay) November 9-12, 2015
     Vol.LNCS pp.8 (pp.143-150) ISBN:9783319257501 DOI:10.1007/978-3-319-25751-8_18

  4. Speaker recognition by means of acoustic and phonetically informed GMMs
     Proceeding
     

     Cumani, Sandro; Laface, Pietro; Kulsoom, Farzana
     In: INTERSPEECH 2015
     International Speech Communication Association (GERMANIA)
     INTERSPEECH 2015 (Dresden (Germany)) 6-10 September 2015
     Vol.1 pp.5 (pp.200-204)

  5. Memory-aware i-vector extraction by means of subspace factorization
     Proceeding
     

     Cumani, Sandro; Laface, Pietro
     In: Proceedings of ICASSP 2015
     IEEE - INST ELECTRICAL ELECTRONICS ENGINEERS INC (STATI UNITI D'AMERICA)
     40th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2015 (Brisbane (Australia)) April 2015
     pp.5 (pp.4669-4673) ISBN:9781467369961

  2014

  1. FAST SPEAKER RECOGNITION SCORING USING I-VECTOR POSTERIORS AND PROBABILISTIC LINEAR DISCRIMINANT ANALYSIS
     Patent
     

     Cumani, Sandro; Vair, Claudio; Colibro, Daniele Ernesto; Laface, Pietro; Farrell, Kevin R.
     N.US 9373330 B2

  2. Large scale training of Pairwise Support Vector Machines for speaker recognition
     Article
     

     Cumani, Sandro; Laface, Pietro
     IEEE/ACM TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING
     IEEE - INST ELECTRICAL ELECTRONICS ENGINEERS INC
     Vol.22 pp.11 (pp.1590-1600) ISSN:2329-9290 DOI:10.1109/TASLP.2014.2341914

  3. Generative pairwise models for speaker recognition
     Proceeding
     

     Cumani, Sandro; Laface, Pietro
     In: Odyssey 2014: The Speaker and Language Recognition Workshop
     International Speech Communication Association
     Odyssey 2014: The Speaker and Language Recognition Workshop (Joensuu, Finland) 16-19 June 2014
     Vol.1 pp.7 (pp.273-279)

  4. Training pairwise Support Vector Machines with large scale datasets
     Proceeding
     

     Cumani, Sandro; Laface, Pietro
     In: 2014 IEEE International Conference on Acoustics, Speech, and Signal Processing ICASSP 2014
     IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC (STATI UNITI D'AMERICA)
     2014 IEEE International Conference on Acoustics, Speech, and Signal Processing ICASSP 2014 (Florence (Italy)) May 4-9, 2014
     Vol.1 pp.5 (pp.1664-1668)

  5. On the use of i-vector posterior distributions in Probabilistic Linear Discriminant Analysis
     Article
     

     Cumani, Sandro; Plchot, O.; Laface, Pietro
     IEEE/ACM TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING
     IEEE - INST ELECTRICAL ELECTRONICS ENGINEERS INC
     Vol.22 pp.12 (pp.846-857) ISSN:2329-9290 DOI:10.1109/TASLP.2014.2308473

  6. Factorized Sub-Space Estimation for Fast and Memory Effective I-vector Extraction
     Article
     

     Cumani, Sandro; Laface, Pietro
     IEEE/ACM TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING
     IEEE - INST ELECTRICAL ELECTRONICS ENGINEERS INC
     Vol.22 pp.12 (pp.248-259) ISSN:2329-9290 DOI:10.1109/TASLP.2013.2290505

  2013

  1. Method and apparatus for efficient i-vector extraction
     Patent
     

     Cumani, Sandro; Laface, Pietro
     N.US 9406298 B2

  2. Developing A Speaker Identification System For The DARPA RATS Project
     Proceeding
     

     Plchot, O.; Matsoukas, S.; Matejka, P.; Dehak, N.; Ma, J.; Cumani, Sandro; Glembek, O.; Hermansky, H.; Mallidi, S.; Mesgarami, N.; Schwartz, R.; Soufifar, M.; Tan, Z.; Thomas, S.; Zhang, B.; Zhou, X.
     In: Proceedings of ICASSP 2013
     ICASSP 2013 (Vancouver, Canada) 26 Maggio - 31 Maggio 2013
     pp.5 (pp.6768-6772)

  3. Regularized subspace n-gram model for phonotactic iVector extraction
     Proceeding
     

     Soufifar, M.; Burget, L.; Plchot, O.; Cumani, Sandro; Cernocky, J.
     INTERSPEECH
     In: Proceedings of Interspeech 2013
     Interspeech 2013 (Lione) 25 Agosto - 29 Agosto 2013
     pp.5 (pp.74-78) ISSN:2308-457X

  4. Speaker recognition by means of Deep Belief Networks
     Proceeding
     

     Vasilakakis, Vasileios; Cumani, Sandro; Laface, Pietro
     In: BTFS 2013
     BBfor2 (PAESI BASSI)
     Biometric Technologies in Forensic Science (Nijmegen) 14-15 October 2013
     pp.6

  5. Nuance - Politecnico di Torino’s 2012 NIST Speaker Recognition Evaluation System
     Proceeding
     

     Colibro, D.; Vairc, ; Farrell, K.; Krause, N.; Karvitsky, G.; Cumani, Sandro; Laface, Pietro
     INTERSPEECH
     In: Interspeech 2013
     International Speech Communication Association (FRANCIA)
     14th Annual Conference of the International Speech Communication Association (Interspeech 2013). (Lyon (France)) 25-29 Aug 2013
     Vol.1 pp.5 (pp.1996-2000) ISSN:2308-457X

  6. Fast and Memory Effective I-Vector Extraction Using a Factorized Sub-Space
     Proceeding
     

     Cumani, Sandro; Laface, Pietro
     INTERSPEECH
     In: 14th Annual Conference of the International Speech Communication Association (Interspeech 2013).
     International Speech Communication Association (FRANCIA)
     Interspeech 2013 (Lyon (France)) 25-29 Aug
     Vol.1 pp.5 (pp.1599-1603) ISSN:2308-457X

  7. PROBABILISTIC LINEAR DISCRIMINANT ANALYSIS OF I–VECTOR POSTERIOR DISTRIBUTIONS
     Proceeding
     

     Cumani, Sandro; Plchot, O.; Laface, Pietro
     In: Proceedings 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing ICASSP 2013
     IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC (STATI UNITI D'AMERICA)
     2013 IEEE International Conference on Acoustics, Speech, and Signal Processing ICASSP 2013 (Vancouver) 26-31 May 2013
     Vol.1 pp.5 (pp.7644-7648) ISBN:9781479903559

  8. Pairwise Discriminative Speaker Verification in the I-Vector Space
     Article
     

     Cumani, Sandro; Brummer, N.; Burget, L.; Laface, Pietro; Plchot, O.; Vasilakakis, Vasileios
     IEEE TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING
     IEEE Signal Processing Society
     Vol.21 pp.11 (pp.1217-1227) ISSN:1558-7916 DOI:10.1109/TASL.2013.2245655

  9. Memory and computation trade-offs for efficient i-vector extraction
     Article
     

     Cumani, Sandro; Laface, Pietro
     IEEE TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING
     IEEE - INST ELECTRICAL ELECTRONICS ENGINEERS INC
     Vol.21 pp.11 (pp.934-944) ISSN:1558-7916 DOI:10.1109/TASL.2013.2239291

  2012

  1. Description and analysis of the Brno276 system for LRE2011
     Proceeding
     

     Brummer, N.; Cumani, Sandro; Glembek, O.; Karafiat, M.; Matejka, P.; Pesan, J.; Plchot, O.; Soufifar, M.; De Villiers, E.; Cernocky, J.
     In: Proceedings of Odyssey 2012: The Speaker and Language Recognition Workshop
     International Speech Communication Association
     Odyssey 2012: The Speaker and Language Recognition Workshop (Singapore)
     pp.8 (pp.216-223) ISBN:9789810730932

  2. Memory and computation effective approaches for i–vector extraction
     Proceeding
     

     Cumani, Sandro; Laface, Pietro; Vasilakakis, Vasileios
     In: Odyssey 2012: The Speaker and Language Recognition Workshop
     ISCA (SINGAPORE)
     Odyssey 2012: The Speaker and Language Recognition Workshop (Singapore) 25-28 June 2012.
     pp.7 (pp.9-15)

  3. Speaker and Language Recognition Techniques
     Doctoral thesis
     

     Cumani, Sandro
     Politecnico di Torino
     DOI:10.6092/polito/porto/2496928

  4. Discriminative Classifiers for Phonotactic Language Recognition with iVectors
     Proceeding
     

     Soufifar, M.; Cumani, Sandro; Burget, L.; Černocký, J.
     In: Procceedings of the 37th International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2012)
     IEEE
     The 37th International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2012)
     pp.4 (pp.4853-4856) ISBN:9781467300445

  5. Independent Component Analysis and MLLR Transforms for Speaker Identification
     Proceeding
     

     Cumani, Sandro; Plchot, O.; Karafiát, M.
     In: Proceedings of the 37th International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2012)
     IEEE
     The 37th International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2012)
     pp.4 (pp.4365-4368) ISBN:9781467300445

  6. GENDER INDEPENDENT DISCRIMINATIVE SPEAKER RECOGNITION IN I–VECTOR SPACE
     Proceeding
     

     Cumani, Sandro; Glembek, O.; Br¨ummer, N.; De Villiers, E.; Laface, Pietro
     In: ICASSP 2012
     IEEE
     International Conference Acoustics Speech and Signal Processing (Kyoto) 24-30 March 2012
     pp.4 (pp.4361-4364)

  7. Analysis of Large-Scale SVM Training Algorithms for Language and Speaker Recognition
     Article
     

     Cumani, Sandro; Laface, Pietro
     IEEE TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING
     Piscataway, N.J. : IEEE
     Vol.20 pp.12 (pp.1585-1596) ISSN:1558-7916 DOI:10.1109/TASL.2012.2186290

  2011

  1. Comparison of speaker recognition approaches for real applications
     Proceeding
     

     Cumani, Sandro; Batzu, P. D.; Colibro, D.; Vair, C.; Laface, Pietro; Vasilakakis, Vasileios
     In: Proceedings of the 12th Annual Conference of the International Speech Communication Association - INTERSPEECH 2011
     ISCA
     INTERSPEECH 2011 (Firenze) 28-31 August 2011
     pp.4 (pp.2365-2368)

  2. Discriminatively Trained Probabilistic Linear Discriminant Analysis for Speaker Verification
     Proceeding
     

     Burget, L.; Plchot, O.; Cumani, Sandro; Glembek, O.; Matejka, P.; Brummer, N.
     In: Proceedings of 2011 IEEE International Conference on Acoustics, Speech and Signal Processing ICASSP 2011
     IEEE (STATI UNITI D'AMERICA)
     2011 IEEE International Conference on Acoustics, Speech and Signal Processing ICASSP 2011 (Prague (Czech Republic)) May 22-27, 2011
     pp.4 (pp.4832-4835) ISBN:9781457705373

  3. LOQUENDO - POLITECNICO DI TORINO’S 2010 NISTSPEAKER RECOGNITION EVALUATION SYSTEM
     Proceeding
     

     Castaldo, F.; Colibro, D. Vair C.; Cumani, Sandro; Laface, Pietro
     In: Proceedings of 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing ICASSP 2011
     IEEE (STATI UNITI D'AMERICA)
     2011 IEEE International Conference on Acoustics, Speech, and Signal Processing ICASSP 2011 (Prague (Czech Republic)) May 22-27, 2011
     pp.4 (pp.5464-5467) ISBN:9781457705373

  4. FAST DISCRIMINATIVE SPEAKER VERIFICATION IN THE I–VECTOR SPACE
     Proceeding
     

     Cumani, Sandro; Brummer, N.; Burget, L.; Laface, Pietro
     In: Proceedings of 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing ICASSP 2011
     IEEE (STATI UNITI D'AMERICA)
     2011 IEEE International Conference on Acoustics, Speech, and Signal Processing ICASSP 2011 (Prague (Czech Republic)) May 22-27, 2011
     pp.4 (pp.4852-4855) ISBN:9781457705373

  2010

  1. LOQUENDO-POLITECNICO DI TORINO SYSTEM FOR THE 2009 NIST LANGUAGE RECOGNITION EVALUATION
     Proceeding
     

     Castaldo, Fabio; Colibro, D.; Cumani, Sandro; Dalmasso, E.; Laface, Pietro; Vair, C.
     In: Proceedings of 2010 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)
     IEEE (STATI UNITI D'AMERICA)
     2010 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP) (Dallas (USA)) 14-19 Marzo 2010
     Vol.1 pp.4 (pp.5002-5005) ISBN:9781424442966 DOI:10.1109/ICASSP.2010.5495082

  2. Parallel implementation of artificial neural network training
     Proceeding
     

     Scanzio, Stefano; Cumani, Sandro; Gemello, R.; Mana, F.; Laface, Pietro
     In: Proceedings of 2010 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)
     IEEE (STATI UNITI D'AMERICA)
     2010 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP) (Dallas (USA)) 14-19 Marzo 2010
     Vol.1 pp.4 (pp.4902-4905) ISBN:9781424442966 DOI:10.1109/ICASSP.2010.5495108

  3. Comparison of Large–scale SVM Training Algorithms for Language Recognition
     Proceeding
     

     Cumani, Sandro; Castaldo, Fabio; Laface, Pietro; Colibro, D; Vair, C.
     In: Proceedings Odyssey 2010
     ISCA
     Odysssey 2010,The Speaker and Language Recognition Workshop (Brno) 28/06 - 1/07 20010
     

  4. Parallel implementation of Artificial Neural Network training for speech recognition
     Article
     

     Scanzio, S; Cumani, Sandro; Gemello, R; Mana, F; Laface, Pietro
     PATTERN RECOGNITION LETTERS
     Elsevier
     Vol.31 pp.10 (pp.1302-1309) ISSN:0167-8655 DOI:10.1016/j.patrec.2010.02.003

  2009

  1. Language Recognition Using Language Factors
     Proceeding
     

     Castaldo, Fabio; Cumani, Sandro; Laface, Pietro; Colibro, D.
     In: Interspeech 2009
     ISCA
     Interspeech 2009 (Brighton) 6-10/9/2009
     pp.4 (pp.176-179)

  2008

  1. A fast and robust method for the identification of face landmarks in profile images
     Article
     

     Bottino, ANDREA GIUSEPPE; Cumani, Sandro
     WSEAS TRANSACTIONS ON COMPUTERS
     Vol.7, Issue 8 pp.10 (pp.1250-1259) ISSN:1109-2750

  2. Robust Identification of Face Landmarks in Profile Images
     Proceeding
     

     Bottino, ANDREA GIUSEPPE; Cumani, Sandro
     In: Proceeding of CSCC 2008. 12th Conference on Circuits, Systems, Communication and Computers.
     CSCC 2008 (Heraklion, Greece) July 23-25. 2008