Dr Anton Ragni

BEng, MEng, PhD

School of Computer Science

Senior Lecturer in Speech and Language Technologies

Seminar Organiser

Member of the Speech and Hearing (SpandH) research group

Anton Ragni profile photo
Profile picture of Anton Ragni profile photo
a.ragni@sheffield.ac.uk
+44 114 222 1925

Full contact details

Dr Anton Ragni
School of Computer Science
Regent Court (DCS)
211 Portobello
91直播
S1 4DP
Profile

Dr Anton Ragni is a Senior Lecturer in Speech and Language Processing in the School of Computer Science at the University of 91直播.

He graduated with BEng and MEng degrees in Information Technology from the University of Tartu, Estonia, in 2005 and 2007 respectively. He was awarded his PhD from the University of Cambridge in 2013.

From 2005 to 2008, he underwent graduate training at the Nordic Graduate School of Language Technology and from 2007 to 2008, he was an intern in the Speech Technology Group, Toshiba Research Europe Ltd, UK. From 2013 to 2018 and from 2018 to 2019, he was a Research Associate and Senior Research Associate, respectively, in Speech Processing at the University of Cambridge.

His current research interest focuses on machine learning approaches for speech and language processing.

Research interests

Dr Anton Ragni's research interests include:

  • Core automatic speech recognition
  • Efficient and expressive speech synthesis
  • Spoken Language Translation
  • Information Retrieval
  • Conversation Modelling
Publications

Books

  • Young S, Evermann G, Gales M, Hain T, Kershaw D, Xunying L, Moore G, Odell J, Ollason D, Povey D , Ragni A et al () The HTK Book (for HTK Version 3.5, documentation alpha version). Cambridge University Engineering Department: Cambridge University Engineering Department. RIS download Bibtex download

Journal articles

  • Sun W, Tu Z & Ragni A (2024) . ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), abs/2310.12765, 12667-12671. RIS download Bibtex download
  • Flynn R & Ragni A (2024) Self-Train Before You Transcribe.. CoRR, abs/2406.12937. RIS download Bibtex download
  • Ma Y, 脴land A, Ragni A, Sette BMD, Saitis C, Donahue C, Lin C, Plachouras C, Benetos E, Quinton E , Shatri E et al (2024) Foundation Models for Music: A Survey.. CoRR, abs/2408.14340. RIS download Bibtex download
  • Ma Y, Yuan R, Li Y, Zhang G, Chen X, Yin H, Lin C, Benetos E, Ragni A, Gyenge N , Liu R et al (2023) On the Effectiveness of Speech Self-supervised Learning for Music.. CoRR, abs/2307.05161. RIS download Bibtex download
  • Ragni A, Gales MJF, Rose O, Knill KM, Kastanos A, Li Q & Ness PM (2022) . IEEE/ACM Transactions on Audio, Speech, and Language Processing, 30, 1319-1329. RIS download Bibtex download
  • Li Y, Zhang G, Yang B, Lin C, Wang S, Ragni A & Fu J (2022) HERB: Measuring Hierarchical Regional Bias in Pre-trained Language Models.. CoRR, abs/2211.02882. RIS download Bibtex download
  • Chen X, Liu X, Wang Y, Ragni A, Wong JHM & Gales MJF (2019) . IEEE/ACM Transactions on Audio, Speech, and Language Processing, 27(9), 1444-1454. RIS download Bibtex download
  • Wu C, Gales MJF, Ragni A, Karanasou P & Sim KC (2018) . IEEE/ACM Transactions on Audio, Speech, and Language Processing, 26(2), 256-265. RIS download Bibtex download
  • Ragni A, Li Q, Gales MJF & Wang Y (2018) Confidence Estimation and Deletion Prediction Using Bidirectional Recurrent Neural Networks.. CoRR, abs/1810.13025. RIS download Bibtex download
  • Shi-Xiong Zhang , Ragni A & Gales MJF (2010) . IEEE Signal Processing Letters, 17(11), 945-948. RIS download Bibtex download
  • Jacobsen SA & Ragni A () Continuous representations of intents for dialogue systems. RIS download Bibtex download
  • Wang Z & Ragni A () Approximate Fixed-Points in Recurrent Neural Networks. RIS download Bibtex download

Chapters

  • Nair S, Ragni A, Klejch O, Galu拧膷谩kov谩 P & Oard D (2020) , Information Retrieval Technology (pp. 145-157). Springer International Publishing RIS download Bibtex download

Conference proceedings papers

  • Mogridge R, Close G, Sutherland R, Hain T, Barker J, Goetze S & Ragni A (2024) . ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Vol. 2024 (pp 306-310). Seoul, Korea, 14 April 2024 - 14 April 2024. RIS download Bibtex download
  • Li Y, Yuan R, Zhang G, Ma Y, Chen X, Yin H, Xiao C, Lin C, Ragni A, Benetos E , Gyenge N et al (2024) MERT: ACOUSTIC MUSIC UNDERSTANDING MODEL WITH LARGE-SCALE SELF-SUPERVISED TRAINING. 12th International Conference on Learning Representations, ICLR 2024 RIS download Bibtex download
  • Sun W, Tu Z & Ragni A (2024) Energy-Based Models for Speech Synthesis.. ICASSP (pp 12667-12671) RIS download Bibtex download
  • Mogridge R, Close G, Sutherland R, Hain T, Barker J, Goetze S & Ragni A (2024) Non-Intrusive Speech Intelligibility Prediction for Hearing-Impaired Users Using Intermediate ASR Features and Human Memory Models.. ICASSP (pp 306-310) RIS download Bibtex download
  • Nomo Sudro P, Ragni A & Hain T (2023) . 2023 31st European Signal Processing Conference (EUSIPCO) Proceedings (pp 271-275). Helsinki, Finland, 4 September 2023 - 4 September 2023. RIS download Bibtex download
  • Flynn R & Ragni A (2023) . INTERSPEECH 2023, Vol. 2023-August (pp 1359-1363) RIS download Bibtex download
  • Mogridge R, Close G, Sutherland R, Goetze S & Ragni A (2023) Pre-Trained Intermediate ASR Features and Human Memory Simulation for Non-Intrusive Speech Intelligibility Prediction in the Clarity Prediction Challenge 2. he 4th Clarity Workshop on Machine Learning Challenges for Hearing Aids (Clarity-2023). https://claritychallenge.org/clarity2023-workshop/results.html, 19 August 2023 - 19 August 2023. RIS download Bibtex download
  • Nicholls D, Knill K, Gales MJF, Ragni A & Ricketts P (2023) Speak & Improve: L2 English Speaking Practice Tool. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, Vol. 2023-August (pp 3669-3670) RIS download Bibtex download
  • Ma Y, Yuan R, Li Y, Zhang G, Lin C, Chen X, Ragni A, Yin H, Benetos E, Gyenge N , Liu R et al (2023) On the Effectiveness of Speech Self-Supervised Learning for Music.. ISMIR (pp 457-465) RIS download Bibtex download
  • Yuan R, Ma Y, Li Y, Zhang G, Chen X, Yin H, Zhuo L, Liu Y, Huang J, Tian Z , Deng B et al (2023) MARBLE: Music Audio Representation Benchmark for Universal Evaluation. Advances in Neural Information Processing Systems, Vol. 36 RIS download Bibtex download
  • Flynn R & Ragni A (2023) Leveraging Cross-Utterance Context For ASR Decoding.. INTERSPEECH (pp 1359-1363) RIS download Bibtex download
  • Li Y, Yuan R, Zhang G, MA Y, Lin C, Chen X, Ragni A, Yin H, Hu Z, He H , Benetos E et al (2022) LV-49: MAP-Music2Vec: A Simple and Effective Baseline for Self-Supervised Music Audio Representation Learning. 23rd International Society for Music Information Retrieval Conference (ISMIR 2022). Bengaluru, India, 4 December 2022 - 4 December 2022. RIS download Bibtex download
  • Li Y, Zhang G, Yang B, Lin C, Ragni A, Wang S & Fu J (2022) HERB: Measuring Hierarchical Regional Bias in Pre-trained Language Models. 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing - Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022 (pp 334-346) RIS download Bibtex download
  • Kastanos A, Ragni A & Gales MJF (2020) . ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 4 May 2020 - 8 May 2020. RIS download Bibtex download
  • Li Q, Ness PM, Ragni A & Gales MJF (2019) . ICASSP 2019 (pp 6755-6759), 12 May 2019 - 17 May 2019. RIS download Bibtex download
  • Oard DW, Carpuat M, Galusc谩kov谩 P, Barrow J, Nair S, Niu X, Shing H-C, Xu W, Zotkina E, McKeown KR , Muresan S et al (2019) Surprise Languages: Rapid-Response Cross-Language IR.. EVIA@NTCIR RIS download Bibtex download
  • Li Q, Ness P, Ragni A & Gales MJF (2019) Bi-directional Lattice Recurrent Neural Networks for Confidence Estimation.. ICASSP (pp 6755-6759) RIS download Bibtex download
  • Wang Y, Wong JHM, Gales MJF, Knill KM & Ragni A (2018) . 2018 IEEE Spoken Language Technology Workshop (SLT). Athens, Greece, 18 December 2018 - 21 December 2018. RIS download Bibtex download
  • Wang Y, Chen X, Gales MJF, Ragni A & Wong JHM (2018) . 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Calgary, AB, Canada, 15 April 2018 - 20 April 2018. RIS download Bibtex download
  • Chen O, Ragni A, Gales M & Chen X (2018) . Proceedings of Interspeech 2018 (pp 3338-3342). Hyderabad, India, 2 September 2018 - 6 September 2018. RIS download Bibtex download
  • Knill K, Gales M, Kyriakopoulos K, Malinin A, Ragni A, Wang Y & Caines A (2018) . Interspeech 2018 (pp 1641-1645). Hyderabad, India, 2 September 2018 - 6 September 2018. RIS download Bibtex download
  • Ragni A & Gales M (2018) . Interspeech 2018 (pp 2217-2221). Hyderabad, India, 2 September 2018 - 6 September 2018. RIS download Bibtex download
  • Ragni A, Li Q, Gales MJF & Wang Y (2018) . 2018 IEEE Spoken Language Technology Workshop (SLT), 18 December 2018 - 21 December 2018. RIS download Bibtex download
  • Chen X, Liu X, Ragni A, Wang Y & Gales MJF (2017) . 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU). Okinawa, Japan, 16 December 2017 - 20 December 2017. RIS download Bibtex download
  • Chen X, Ragni A, Liu X & Gales MJF (2017) . Proceedings of Interspeech 2017 (pp 269-273). Stockholm, Sweden, 20 August 2017 - 24 August 2017. RIS download Bibtex download
  • Knill KM, Gales MJF, Kyriakopoulos K, Ragni A & Wang Y (2017) . Proceedings of Interspeech 2017 (pp 2774-2778). Stockholm, Sweden, 20 August 2017 - 24 August 2017. RIS download Bibtex download
  • Gales MJF, Knill KM & Ragni A (2017) . Speech and Computer : 19th International Conference, SPECOM 2017 (pp 3-19). Hatfield, UK, 12 September 2017 - 16 September 2017. RIS download Bibtex download
  • Malinin A, Ragni A, Knill K & Gales M (2017) . Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2 : Short Papers). Vancouver, Canada, 30 July 2017 - 4 August 2017. RIS download Bibtex download
  • Ragni A, Wu C, Gales MJF, Vasilakes J & Knill KM (2017) . 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp 4830-4834). New Orleans, LA, USA, 5 March 2017 - 9 March 2017. RIS download Bibtex download
  • Ragni A, Saunders D, Zahemszky P, Vasilakes J, Gales MJF & Knill KM (2017) . 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp 5770-5774). New Orleans, LA, USA, 5 March 2017 - 9 March 2017. RIS download Bibtex download
  • Chen X, Ragni A, Vasilakes J, Liu X, Knill K & Gales MJF (2017) . 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp 5775-5779). New Orleans, LA, USA, 5 March 2017 - 9 March 2017. RIS download Bibtex download
  • Ragni A, Dakin E, Chen X, Gales MJF & Knill KM (2016) . Interspeech 2016. San Francisco, CA, USA, 8 September 2016 - 12 September 2016. RIS download Bibtex download
  • Yang J, Ragni A, Gales MJF & Knill KM (2016) . Interspeech 2016. San Francisco, CA, USA, 8 September 2016 - 12 September 2016. RIS download Bibtex download
  • Yang J, Zhang C, Ragni A, Gales MJF & Woodland PC (2016) . 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Shanghai, China, 20 March 2016 - 25 March 2016. RIS download Bibtex download
  • Mendels G, Cooper E, Soto V, Hirschberg J, Gales MJF, Knill KM, Ragni A & Wang H (2015) Improving speech recognition and keyword search for low resource languages using web data. INTERSPEECH 2015 : 16th Annual Conference of the International Speech Communication Association (pp 829-833). Dresden, Germany, 6 September 2015 - 10 September 2015. RIS download Bibtex download
  • Wang H, Ragni A, Gales MJF, Knill KM, Woodland PC & Zhang C (2015) Joint decoding of tandem and hybrid systems for improved keyword spotting on low resource languages. INTERSPEECH 2015 : 16th Annual Conference of the International Speech Communication Association (pp 3660-3664). Dresden, Germany, 6 September 2015 - 10 September 2015. RIS download Bibtex download
  • Gales MJF, Knill KM & Ragni A (2015) . 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Brisbane, QLD, Australia, 19 April 2015 - 24 April 2015. RIS download Bibtex download
  • Ragni A, Gales MJF & Knill KM (2015) . 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp 4634-4638). Brisbane, QLD, Australia, 19 April 2015 - 24 April 2015. RIS download Bibtex download
  • van Dalen RC, Yang J, Wang H, Ragni A, Zhang C & Gales MJF (2015) . 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), 13 December 2015 - 17 December 2015. RIS download Bibtex download
  • Cui J, Kingsbury B, Ramabhadran B, Sethy A, Audhkhasi K, Cui X, Kislal E, Mangu L, Nussbaum-Thom M, Picheny M , Tuske Z et al (2015) . 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), 13 December 2015 - 17 December 2015. RIS download Bibtex download
  • Knill KM, Gales MJF, Ragni A & Rath SP (2014) Language independent and unsupervised acoustic models for speech recognition and keyword spotting. INTERSPEECH 2014 : 15th Annual Conference of the International Speech Communication Association. Singapore, 14 September 2014 - 18 September 2014. RIS download Bibtex download
  • Rath SP, Knill KM, Ragni A & Gales MJF (2014) Combining tandem and hybrid systems for improved speech recognition and keyword spotting on low resource languages. INTERSPEECH 2014 : 15th Annual Conference of the International Speech Communication Association (pp 835-839). Singapore, 14 September 2014 - 18 September 2014. RIS download Bibtex download
  • Ragni A, Knill KM, Rath SP & Gales MJF (2014) Data augmentation for low resource languages. INTERSPEECH 2014 : 15th Annual Conference of the International Speech Communication Association (pp 810-814). Singapore, 14 September 2014 - 18 September 2014. RIS download Bibtex download
  • Yoshioka T, Ragni A & Gales MJF (2014) . 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp 6344-6348). Florence, Italy, 4 May 2014 - 9 May 2014. RIS download Bibtex download
  • Gales MJF, Knill KM, Ragni A & Rath SP (2014) Speech recognition and keyword spotting for low-resource languages: Babel project research at CUED.. SLTU (pp 16-23) RIS download Bibtex download
  • van Dalen RC, Ragni A & Gales MJF (2013) . 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, 26 May 2013 - 31 May 2013. RIS download Bibtex download
  • Roupakia Z, Ragni A & Gales M (2012) Rapid nonlinear speaker adaptation for large-vocabulary continuous speech recognition. 13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012, Vol. 2 (pp 1782-1785) RIS download Bibtex download
  • Gales MJF, Ragni A, Zhang A & Dalen RCV (2012) Structured discriminative models for speech recognition.. MLSLP RIS download Bibtex download
  • Ragni A & Gales MJF (2012) . 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 25 March 2012 - 30 March 2012. RIS download Bibtex download
  • Ragni A & Gales MJF (2011) . 2011 IEEE Workshop on Automatic Speech Recognition & Understanding, 11 December 2011 - 15 December 2011. RIS download Bibtex download
  • Ragni A & Gales MJF (2011) . 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 22 May 2011 - 27 May 2011. RIS download Bibtex download
  • Gales MJF, Ragni A, AlDamarki H & Gautier C (2009) . 2009 IEEE Workshop on Automatic Speech Recognition & Understanding, 13 November 2009 - 17 December 2009. RIS download Bibtex download
  • Ragni A (2007) Initial Experiments with Estonian Speech Recognition.. NODALIDA (pp 249-252) RIS download Bibtex download
  • Flynn R & Ragni A () . Interspeech 2024 (pp 217-221) RIS download Bibtex download
  • Mogridge R & Ragni A () . Interspeech 2024 (pp 2360-2364) RIS download Bibtex download
  • Leung W-Z, Cross M, Ragni A & Goetze S () Training data augmentation for dysarthric automatic speech recognition by text-to-dysarthric-speech synthesis. Proceedings of Interspeech 2024. Kos island, Greece, 1 September 2024 - 1 September 2024. RIS download Bibtex download
  • Malinin A, Knill K, Ragni A, Wang Y & Gales M () . 7th ISCA Workshop on Speech and Language Technology in Education RIS download Bibtex download
  • Roupakia Z, Ragni A & Gales MJF () . Interspeech 2012 RIS download Bibtex download

Preprints

  • Cross M & Ragni A (2024) What happens to diffusion model likelihood when your model is conditional?, arXiv. RIS download Bibtex download
  • Ma Y, 脴land A, Ragni A, Del Sette BM, Saitis C, Donahue C, Lin C, Plachouras C, Benetos E, Shatri E , Morreale F et al (2024) , arXiv. RIS download Bibtex download
  • Flynn R & Ragni A (2024) , arXiv. RIS download Bibtex download
  • Leung W-Z, Cross M, Ragni A & Goetze S (2024) , arXiv. RIS download Bibtex download
  • Mogridge R, Close G, Sutherland R, Hain T, Barker J, Goetze S & Ragni A (2024) , arXiv. RIS download Bibtex download
  • Flynn R & Ragni A (2023) . RIS download Bibtex download
  • Sun W, Tu Z & Ragni A (2023) , arXiv. RIS download Bibtex download
  • Ma Y, Yuan R, Li Y, Zhang G, Chen X, Yin H, Lin C, Benetos E, Ragni A, Gyenge N , Liu R et al (2023) , arXiv. RIS download Bibtex download
  • Flynn R & Ragni A (2023) , arXiv. RIS download Bibtex download
  • Yuan R, Ma Y, Li Y, Zhang G, Chen X, Yin H, Zhuo L, Liu Y, Huang J, Tian Z , Deng B et al (2023) , arXiv. RIS download Bibtex download
  • Li Y, Yuan R, Zhang G, Ma Y, Chen X, Yin H, Lin C, Ragni A, Benetos E, Gyenge N , Dannenberg RB et al (2023) MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training.. RIS download Bibtex download
  • Li Y, Yuan R, Zhang G, Ma Y, Lin C, Chen X, Ragni A, Yin H, Hu Z, He H , Benetos E et al (2022) . RIS download Bibtex download
  • Li Y, Zhang G, Yang B, Lin C, Wang S, Ragni A & Fu J (2022) , arXiv. RIS download Bibtex download
  • Wang Z & Ragni A (2021) , arXiv. RIS download Bibtex download
  • Jacobsen SA & Ragni A (2021) , arXiv. RIS download Bibtex download
  • Kastanos A, Ragni A & Gales M (2019) , arXiv. RIS download Bibtex download
  • Li Q, Ness P, Ragni A & Gales M (2018) , arXiv. RIS download Bibtex download
  • Ragni A, Li Q, Gales M & Wang Y (2018) , arXiv. RIS download Bibtex download
  • Wang Y, Chen X, Gales M, Ragni A & Wong J (2018) , arXiv. RIS download Bibtex download
  • Chen X, Liu X, Ragni A, Wang Y & Gales M (2017) , arXiv. RIS download Bibtex download
  • Chen X, Liu X, Ragni A, Wang Y & Gales MJF (2017) Future Word Contexts in Neural Network Language Models.. RIS download Bibtex download
Grants

Research Grants

  • , EPSRC, 06/2021 - 11/2023, 拢218,290, as PI
  • Automatic voice conversion for transforming professional adult voice actors to artificial child voice actors, Innovate UK, 01/2021 - 01/2023, 拢173,605, as Co-PI
Professional activities and memberships

He is a member of IEEE, ISCA and a regular reviewer of major speech and machine learning journals and conferences.

Since 2016, he has been an Officer of ISCA Special Interest Group on Machine Learning in Speech and Language Processing. He received the Best Student Paper Award at the IEEE Workshop on Automatic Speech Recognition and Understanding for his paper 鈥淕enerative kernels for noise robust ASR鈥 co-authored with M. J. F. Gales in 2011.