Publications
- Paolo Sani, Edgar Andres Suarez Guarnizo, Kishor Kayyar Lakshminarayana, and Christian Dittmar
RT-PAD-VC—Creative Applications of Neural Voice Conversion as an Audio Effect
In a demonstration at Digital Audio Effects (DAFx) conference at Ancona, Italy, 2025.@inproceedings{sani25_rtpadvc_dafx, title = {RT-PAD-VC--Creative Applications of Neural Voice Conversion as an Audio Effect}, author = {Paolo Sani and Edgar Andres Suarez Guarnizo and Kishor Kayyar Lakshminarayana and Christian Dittmar}, year = {2025}, url = {https://dafx25.dii.univpm.it/wp-content/uploads/2025/07/DAFx25_paper_85.pdf}, booktitle = {a demonstration at Digital Audio Effects {(DAFx)} conference at Ancona, Italy} } - Frank Zalkow, Paolo Sani, Kishor Kayyar Lakshminarayana, Emanuël A. P. Habets, Nicola Pia, and Christian Dittmar
Bridging the Training–Inference Gap in TTS: Training Strategies for Robust Generative Postprocessing for Low-Resource Speakers
In Proc. Interspeech Conf.: 2470–2474, 2025. DOI@inproceedings{zalkow25_genpostproc_interspeech, title = {{Bridging the Training–Inference Gap in TTS: Training Strategies for Robust Generative Postprocessing for Low-Resource Speakers}}, author = {{Frank Zalkow and Paolo Sani and Kishor {Kayyar Lakshminarayana} and Emanuël A. P. Habets and Nicola Pia and Christian Dittmar}}, year = {{2025}}, booktitle = interspeech, pages = {{2470--2474}}, doi = {{10.21437/Interspeech.2025-854}}, issn = {{2958-1796}}, } - Anna Leschanowsky, Kishor Kayyar Lakshminarayana, Anjana Rajasekhar, Lyonel Behringer, Ibrahim Kilinc, Guillaume Fuchs, and Emanuël A. P. Habets
Benchmarking Neural Speech Codec Intelligibility with SITool
In Proc. Interspeech Conf.: 5488–5492, 2025. DOI@inproceedings{leschanowsky25_sitool_interspeech, title = {{Benchmarking Neural Speech Codec Intelligibility with SITool}}, author = {{Anna Leschanowsky and Kishor {Kayyar Lakshminarayana} and Anjana Rajasekhar and Lyonel Behringer and Ibrahim Kilinc and Guillaume Fuchs and Emanuël A. P. Habets}}, year = {{2025}}, booktitle = interspeech, pages = {{5488--5492}}, doi = {{10.21437/Interspeech.2025-984}}, issn = {{2958-1796}}, } - Kishor Kayyar Lakshminarayana, Frank Zalkow, Christian Dittmar, Nicola Pia, and Emanuël Habets
Low-Resource Text-to-Speech Synthesis Using Noise-Augmented Training of ForwardTacotron
In Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP): 1–5, 2025. DOI@inproceedings{kayyar25_lowres_icassp, author={Kishor {Kayyar Lakshminarayana} and Frank Zalkow and Christian Dittmar and Nicola Pia and Emanuël Habets}, booktitle=icassp, title={Low-Resource Text-to-Speech Synthesis Using Noise-Augmented Training of ForwardTacotron}, year={2025}, volume={}, number={}, pages={1-5}, keywords={Training;Adaptation models;Computational modeling;Noise;Natural languages;Data models;Acoustics;Text to speech;Computational efficiency}, doi={10.1109/ICASSP49660.2025.10890686}} - Kishor Kayyar Lakshminarayana, Christian Dittmar, Nicola Pia, and Emanuël Habets
Multi-Speaker Text-to-Speech Using ForwardTacotron with Improved Duration Prediction
In Speech Communication; 15th ITG Conference: 186–190, 2023. DOI@inproceedings{kayyar23_dur_itg, author={Kishor {Kayyar Lakshminarayana} and Christian Dittmar and Nicola Pia and Emanuël Habets}, booktitle={Speech Communication; 15th ITG Conference}, title={Multi-Speaker Text-to-Speech Using ForwardTacotron with Improved Duration Prediction}, year={2023}, volume={}, number={}, pages={186-190}, doi={10.30420/456164036}} - Frank Zalkow, Paolo Sani, Michael Fast, Judith Bauer, Mohammad Joshaghani, Kishor Kayyar Lakshminarayana, Emanuël Habets, and Christian Dittmar
The AudioLabs System for the Blizzard Challenge 2023
In Proc. 18th Blizzard Challenge Workshop: 63–68, 2023. DOI@inproceedings{zalkow23_blizzard, author={Frank Zalkow and Paolo Sani and Michael Fast and Judith Bauer and Mohammad Joshaghani and Kishor {Kayyar Lakshminarayana} and Emanuël Habets and Christian Dittmar}, title={{The AudioLabs System for the Blizzard Challenge 2023}}, year=2023, booktitle={Proc. 18th Blizzard Challenge Workshop}, pages={63--68}, doi={10.21437/Blizzard.2023-8} } - Kishor Kayyar Lakshminarayana, Christian Dittmar, Nicola Pia, and Emanuël Habets
Low-Resource Text-to-Speech Using Specific Data and Noise Augmentation
In Proc. European Signal Processing Conf. (EUSIPCO): 61–65, 2023. DOI@inproceedings{kayyar23_eusipco, author={Kishor {Kayyar Lakshminarayana} and Christian Dittmar and Nicola Pia and Emanuël Habets}, booktitle=eusipco, title={Low-Resource Text-to-Speech Using Specific Data and Noise Augmentation}, year={2023}, pages={61-65}, doi={10.23919/EUSIPCO58844.2023.10289912} } - Kishor Kayyar Lakshminarayana, Christian Dittmar, Nicola Pia, and Emanuel Habets
Subjective Evaluation of Text-to-Speech Models: Comparing Absolute Category Rating and Ranking by Elimination Tests
In Proc. ISCA Speech Synthesis Workshop: 191–196, 2023. DOI@inproceedings{kayyar23_ssw, author={Kishor {Kayyar Lakshminarayana} and Christian Dittmar and Nicola Pia and Emanuel Habets}, title={{Subjective Evaluation of Text-to-Speech Models: Comparing Absolute Category Rating and Ranking by Elimination Tests}}, year=2023, booktitle=ssw, pages={191--196}, doi={10.21437/SSW.2023-30} } - Daniele Mirabilii, Kishor Kayyar Lakshminarayana, Wolfgang Mack, and Emanuel Habets
Data-driven wind speed estimation using multiple microphones
In Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP): 576–580, 2020.@inproceedings{Mirabilii2020a, author={Daniele Mirabilii and Kishor {Kayyar Lakshminarayana} and Wolfgang Mack and Emanuel Habets}, title={Data-driven wind speed estimation using multiple microphones}, booktitle = icassp, year = {2020}, address = {Spain}, pages={ 576--580}, }