Výsledky vyhledávání - "Vipperla, Ravichander"

Report

Expressive Machine Dubbing Through Phrase-level Cross-lingual Prosody Transfer

Autor: Swiatkowski, Jakub, Wang, Duo, Babianski, Mikolaj, Coccia, Giuseppe, Tobing, Patrick Lumban, Vipperla, Ravichander, Klimkov, Viacheslav, Pollet, Vincent

Speech generation for machine dubbing adds complexity to conventional Text-To-Speech solutions as the generated output is required to match the expressiveness, emotion and speaking rate of the source content. Capturing and transferring details and va

Externí odkaz: http://arxiv.org/abs/2306.11662

Zobrazit plný text záznamu

Report

Cross-lingual Prosody Transfer for Expressive Machine Dubbing

Autor: Swiatkowski, Jakub, Wang, Duo, Babianski, Mikolaj, Tobing, Patrick Lumban, Vipperla, Ravichander, Pollet, Vincent

Prosody transfer is well-studied in the context of expressive speech synthesis. Cross-lingual prosody transfer, however, is challenging and has been under-explored to date. In this paper, we present a novel solution to learn prosody representations t

Externí odkaz: http://arxiv.org/abs/2306.11658

Zobrazit plný text záznamu

Report

CN-Celeb: multi-genre speaker recognition

Autor: Li, Lantian, Liu, Ruiqi, Kang, Jiawen, Fan, Yue, Cui, Hao, Cai, Yunqi, Vipperla, Ravichander, Zheng, Thomas Fang, Wang, Dong

Research on speaker recognition is extending to address the vulnerability in the wild conditions, among which genre mismatch is perhaps the most challenging, for instance, enrollment with reading speech while testing with conversational or singing au

Externí odkaz: http://arxiv.org/abs/2012.12468

Zobrazit plný text záznamu

Report

Bunched LPCNet : Vocoder for Low-cost Neural Text-To-Speech Systems

Autor: Vipperla, Ravichander, Park, Sangjun, Choo, Kihyun, Ishtiaq, Samin, Min, Kyoungbo, Bhattacharya, Sourav, Mehrotra, Abhinav, Ramos, Alberto Gil C. P., Lane, Nicholas D.

LPCNet is an efficient vocoder that combines linear prediction and deep neural network modules to keep the computational complexity low. In this work, we present two techniques to further reduce it's complexity, aiming for a low-cost LPCNet vocoder-b

Externí odkaz: http://arxiv.org/abs/2008.04574

Zobrazit plný text záznamu

Report

Iterative Compression of End-to-End ASR Model using AutoML

Autor: Mehrotra, Abhinav, Dudziak, Łukasz, Yeo, Jinsu, Lee, Young-yoon, Vipperla, Ravichander, Abdelfattah, Mohamed S., Bhattacharya, Sourav, Ishtiaq, Samin, Ramos, Alberto Gil C. P., Lee, SangJeong, Kim, Daehyun, Lane, Nicholas D.

Publikováno v: INTERSPEECH 2020

Increasing demand for on-device Automatic Speech Recognition (ASR) systems has resulted in renewed interests in developing automatic model compression techniques. Past research have shown that AutoML-based Low Rank Factorization (LRF) technique, when

Externí odkaz: http://arxiv.org/abs/2008.02897

Zobrazit plný text záznamu

Report

ShrinkML: End-to-End ASR Model Compression Using Reinforcement Learning

Autor: Dudziak, Łukasz, Abdelfattah, Mohamed S., Vipperla, Ravichander, Laskaridis, Stefanos, Lane, Nicholas D.

End-to-end automatic speech recognition (ASR) models are increasingly large and complex to achieve the best possible accuracy. In this paper, we build an AutoML system that uses reinforcement learning (RL) to optimize the per-layer compression ratios

Externí odkaz: http://arxiv.org/abs/1907.03540

Zobrazit plný text záznamu