Shivam Mehta

About Shivam Mehta

Shivam Mehta, With an exceptional h-index of 5 and a recent h-index of 5 (since 2020), a distinguished researcher at Kungliga Tekniska högskolan, specializes in the field of Probabilistic Machine Learning, Deep Learning, Speech Synthesis, Generative Models.

His recent articles reflect a diverse array of research interests and contributions to the field:

Fake it to make it: Using synthetic data to remedy the data shortage in joint multimodal speech-and-gesture synthesis

Unified speech and gesture synthesis using flow matching

OverFlow: Putting flows on top of neural transducers for better TTS

Diffusion-based co-speech gesture generation using joint text and audio representation

Matcha-TTS: A fast TTS architecture with conditional flow matching

Stuck in the MOS pit: A critical analysis of MOS test methodology in TTS evaluation

Diff-TTSG: Denoising probabilistic integrated speech and gesture synthesis

Prosody-controllable spontaneous TTS with neural HMMs

Shivam Mehta Information

University

Position

___

Citations(all)

55

Citations(since 2020)

54

Cited By

1

hIndex(all)

5

hIndex(since 2020)

5

i10Index(all)

1

i10Index(since 2020)

1

Email

University Profile Page

Google Scholar

Shivam Mehta Skills & Research Interests

Probabilistic Machine Learning

Deep Learning

Speech Synthesis

Generative Models

Top articles of Shivam Mehta

Fake it to make it: Using synthetic data to remedy the data shortage in joint multimodal speech-and-gesture synthesis

arXiv preprint arXiv:2404.19622

2024/4/30

Unified speech and gesture synthesis using flow matching

2024/4/14

OverFlow: Putting flows on top of neural transducers for better TTS

Proc. INTERSPEECH 2023

2023

Diffusion-based co-speech gesture generation using joint text and audio representation

2023/10/9

Matcha-TTS: A fast TTS architecture with conditional flow matching

2024/4/14

Stuck in the MOS pit: A critical analysis of MOS test methodology in TTS evaluation

2023/6/15

Diff-TTSG: Denoising probabilistic integrated speech and gesture synthesis

arXiv preprint arXiv:2306.09417

2023/6/15

Prosody-controllable spontaneous TTS with neural HMMs

2023/6/4

Stereotypical nationality representations in HRI: perspectives from international young adults

Frontiers in Robotics and AI

2023

Neural HMMs are all you need (for high-quality attention-free TTS)

2022/5/23

Shivam Mehta
Shivam Mehta

H-Index: 1

Gustav Eje Henter
Gustav Eje Henter

H-Index: 15

Learning fast with fewer data samples using Neural HMMs

2022

Shivam Mehta
Shivam Mehta

H-Index: 1

Gustav Eje Henter
Gustav Eje Henter

H-Index: 15

Speech data augmentation for improving phoneme transcriptions of aphasic speech using wav2vec 2.0 for the psst challenge

2022/6

Spontaneous Neural HMM TTS with Prosodic Feature Modification

2022

Finding the Blank with Sequence Labeling for English Learning

2020/10/27

Shivam Mehta
Shivam Mehta

H-Index: 1

Ivan Smetannikov
Ivan Smetannikov

H-Index: 4

See List of Professors in Shivam Mehta University(Kungliga Tekniska högskolan)

Co-Authors

academic-engine