Hoppa till huvudinnehållet
Till KTH:s startsida

Publikationer av Shivam Mehta

Refereegranskade

Artiklar

Konferensbidrag

[2]
S. Mehta et al., "Fake it to make it : Using synthetic data to remedy the data shortage in joint multimodal speech-and-gesture synthesis," i Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024, s. 1952-1964.
[3]
S. Mehta et al., "MATCHA-TTS: A FAST TTS ARCHITECTURE WITH CONDITIONAL FLOW MATCHING," i 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024 - Proceedings, 2024, s. 11341-11345.
[4]
A. Deichler et al., "Difusion-Based Co-Speech Gesture Generation Using Joint Text and Audio Representation," i PROCEEDINGS OF THE 25TH INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION, ICMI 2023, 2023, s. 755-762.
[5]
S. Mehta et al., "OverFlow : Putting flows on top of neural transducers for better TTS," i Interspeech 2023, 2023, s. 4279-4283.
[6]
H. Lameris et al., "Prosody-Controllable Spontaneous TTS with Neural HMMs," i International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2023.
[7]
S. Mehta et al., "Neural HMMs are all you need (for high-quality attention-free TTS)," i 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022, s. 7457-7461.
[8]
B. Moell et al., "Speech Data Augmentation for Improving Phoneme Transcriptions of Aphasic Speech Using Wav2Vec 2.0 for the PSST Challenge," i The RaPID4 Workshop : Resources and ProcessIng of linguistic, para-linguistic and extra-linguistic Data from people with various forms of cognitive/psychiatric/developmental impairments, 2022, s. 62-70.

Icke refereegranskade

Konferensbidrag

[9]
H. Lameris et al., "Spontaneous Neural HMM TTS with Prosodic Feature Modification," i Proceedings of Fonetik 2022, 2022.
Senaste synkning med DiVA:
2024-11-17 02:07:30