Yamini Sinha, M. Sc.
Yamini Sinha
Fachgebiet Mobile Dialogsysteme
curriculum vitae
| 10/2021 | PhD student at Mobile Dialogue Systems |
| 11/2020 - 09/2021 with breaks | Research assistant and tutor |
| 10/2017 - 09/2021 | Master of Science in Electrical Engineering and Information Technology at OVGU Magdeburg; Title of the diploma thesis: Evaluating and combining several cloud-based transcription services for the generation of automatic transcripts for German conversational speech. |
|
09/2016 - 12/2016 |
Validation Engineer at SanDisk India |
|
01/2016 - 08/2016 |
Internship at Maven Silicon, Bangalore, India VLSI design and verification |
| 10/2016 | Bachelor of Technology at Sikkim Manipal Institute of Technology, India. |
| 06/2012 | Higher Secondary school examination at NRI Junior College, Hyderabad, India. |
Research interests
Speaker anonymization, speech processing, human-computer interaction, automatic speech recognition
2024
Buchbeitrag
Safeguarding speech content style - enhancing privacy beyond speaker identity
Sinha, Yamini; Raivakhovskyi, Mykola; Schubert, Martha; Siegert, Ingo
In: 4th Symposium on Security and Privacy in Speech Communication - Kos, Greece, 6 September 2024 - International Speech Communication Association ; Siegert, Ingo, S. 92-101 [Symposium: 4th Symposium on Security and Privacy in Speech Communication, Kos, Greece, 6 September 2024]
Speech recognition errors in ASR engines and their impact on linguistic analysis in psychotherapies
Schubert, Martha; Sinha, Yamini; Krüger, Julia; Siegert, Ingo
In: Elektronische Sprachsignalverarbeitung 2024 / Rue , Mitch - Dresden : TUDpress ; Rue, Mitch, S. 203-210 - (Studientexte zur Sprachkommunikation; 107) [Konferenz: 35. Konferenz „Elektronische Sprachsignalverarbeitung”, Regensburg, 6.-8. März 2024]
Evaluation of audio deepfakes - systematic review
Sinha, Yamini; Hintz, Jan; Siegert, Ingo
In: Elektronische Sprachsignalverarbeitung 2024 / Rue , Mitch - Dresden : TUDpress ; Rue, Mitch, S. 181-187 - (Studientexte zur Sprachkommunikation; 107) [Konferenz: 35. Konferenz „Elektronische Sprachsignalverarbeitung”, Regensburg, 6.-8. März 2024]
Anonymising elderly and pathological speech - voice conversion using DDSP and query-by-example
Ghosh, Suhita; Jouaiti, Melanie; Das, Arnab; Sinha, Yamini; Polzehl, Tim; Siegert, Ingo; Stober, Sebastian
In: Interspeech 2024 - International Speech and Communication Association, S. 4438-4442 [Konferenz: Interspeech 2024, Kos, Greece, 1-5 September 2024]
2023
Anderes Material
Evaluating state-of-the-art speech recognition systems with focus on low resource languages
Sinha, Yamini; Silber-Varod, Yered; Siegert, Ingo
In: KM Conference 2023 - International Institute for Applied Knowledge Management , 2023, S. 41
Buchbeitrag
Presenting a German dataset of wake words - first analyses and comparison of different solutions for speech-based activation techniques
Busch, Matthias; Sinha, Yamini; Hintz, Jan; Wendemuth, Andreas; Siegert, Ingo
In: DAGA 2023 - Berlin : Deutsche Gesellschaft für Akustik e.V., S. 1478-1481
Impact of pathological speech on speaker anonymization - a proof of concept
Hintz, Jan; Sinha, Yamini; Bayerl, Sebastian P.; Riedhammer, Korbinian; Siegert, Ingo
In: DAGA 2023 - Berlin : Deutsche Gesellschaft für Akustik e.V., S. 1470-1473
Improving voice conversion for dissimilar speakers using perceptual losses
Gosh, Suhita; Sinha, Yamini; Siegert, Ingo; Stober, Sebastian
In: DAGA 2023 , 2023 - Berlin : Deutsche Gesellschaft für Akustik e.V., S. 1358-1361 [Tagung: 49. Jahrestagung für Akustik, DAGA 2023, Hamburg, 06. - 09. März 2023]
Anonymization of stuttered speech - removing speaker information while preserving the utterance
Hintz, Jan; Bayerl, Sebastian; Sinha, Yamini; Ghosh, Suhita; Schubert, Martha; Stober, Sebastian; Riedhammer, Korbinian; Siegert, Ingo
In: 3rd Symposium on Security and Privacy in Speech Communication - Internatinal Speech Communication Association ; Siegert, Ingo . - 2023, S. 41-45 [Symposium: 3rd Symposium on Security and Privacy in Speech Communication, Dublin, Ireland, 19 August 2023]
Begutachteter Zeitschriftenartikel
Emo-StarGAN - a semi-supervised any-to-many non-parallel emotion-preserving voice conversion
Ghosh, Suhita; Das, Arnab; Sinha, Yamini; Siegert, Ingo; Polzehl, Tim; Stober, Sebastian
In: Interspeech 2023 - International Speech and Communication Association ; Harte, Naomi, S. 2093-2097 [Konferenz: INTERSPEECH 2023, Dublin, Ireland, 20-24 August 2023]
2022
Buchbeitrag
Why Eli Roth should not use TTS-Systems for anonymization
Sinha, Yamini; Hintz, Jan; Busch, Matthias; Polzehl, Tim; Haase, Matthias; Wendemuth, Andreas; Siegert, Ingo
In: 2nd Symposium on Security and Privacy in Speech Communication - Incheon, Korea, 23-24 September 2022 - Internatinal Speech Communication Association ; Siegert, Ingo, S. 17-22
DyCoDa - a multi-modal data collection of multi-user remote survival game recordings
Dresvyanskiy, Denis; Sinha, Yamini; Busch, Matthias; Siegert, Ingo; Karpov, Alexey; Minker, Wolfgang
In: Konferenz: 24th International Conference on Speech and Computer, SPECOM 2022, Gurugram, India, November 14-16, 2022, Speech and Computer - Cham: Springer International Publishing; Prasanna, S. R. Mahadeva . - 2022, S. 163-177 - (Lecture notes in computer science; volume 13721)
Improving the accuracy for voice-assistant conversations in German by combining different online ASR-API outputs
Sinha, Yamini; Siegert, Ingo
In: Konferenz: Human Perspectives on Spoken Human-Machine Interaction, Freiburg im Breisgau (online), 15.-17. November 2021, Proceedings of the conference Human Perspectives on Spoken Human-Machine Interaction - Freiburg: FRIAS, Freiburg Institute for Advanced Studies, Albert-Ludwigs-Universität; Warchhold, Sarah *1994-* . - 2022, S. 11-16
Emotion preservation for one-shot speaker anonymization using McAdams
Sinha, Yamini; Wendemuth, Andreas; Siegert, Ingo
In: Konferenz: 33. Konferenz "Elektronische Sprachsignalverarbeitung", Sonderborg, 2.-4. März 2022, Elektronische Sprachsignalverarbeitung 2022 - Dresden: TUDpress; Weston, Heather . - 2022, S. 235-242 - (Studientexte zur Sprachkommunikation; 103)
Performance and quality evaluation of a McAdams speaker anonymization for spontaneous German speech
Sinha, Yamini; Siegert, Ingo
In: Fortschritte der Akustik - DAGA 2022 - Berlin: Deutsche Gesellschaft für Akustik e.V. (DEGA) . - 2022, S. 1185-1188
Voice Privacy - leveraging multi-scale blocks with ECAPA-TDNN SE-Res2NeXt extension for speaker anonymization
Khamsehashari, Razieh; Sinha, Yamini; Hintz, Jan; Ghosh, Suhita; Polzehl, Tim; Franzreb, Carlos; Stober, Sebastian; Siegert, Ingo
In: 2nd Symposium on Security and Privacy in Speech Communication - Incheon, Korea, 23-24 September 2022 - Internatinal Speech Communication Association ; Siegert, Ingo, S. 43-48 [Symposium: 2nd Symposium on Security and Privacy in Speech Communication, Incheon, Korea, 23-24 September 2022]
Artikel in Kongressband
Public interactions with voice assistant - discussion of different one-shot solutions to preserve speaker privacy
Siegert, Ingo; Sinha, Yamini; Winkelmann, Gino; Jokisch, Oliver; Wendemuth, Andreas
In: Proceedings of the LREC 2022 Joint Workshop on Legal and Ethical Issues in Human Language Technologies and Multilingual De-Identification of Sensitive Language Resources (LEGAL - MDLR 2022) - Paris : European Language Resources Association (ELRA) ; Rigault, Mickaël, S. 44-47
2021
Begutachteter Zeitschriftenartikel
A cross-language study of speech recognition systems for English, German, and Hebrew
Silber Varod, Vered; Siegert, Ingo; Jokisch, Oliver; Sinha, Yamini; Geri, Nitza
In: The Online Journal of Applied Knowledge Management - [Erscheinungsort nicht ermittelbar] : [Verlag nicht ermittelbar], Bd. 9 (2021), Heft 1, insges. 15 S.
2020
Buchbeitrag
Recognition performance of selected speech recognition APIs - a longitudinal study
Siegert, Ingo; Sinha, Yamini; Jokisch, Oliver; Wendemuth, Andreas
In: Speech and Computer - Cham : Springer ; Karpov, Alexey . - 2020, S. 520-529 - ( Lecture notes in computer science; 12335)
