Zobrazeno 1 - 10
of 13
pro vyhledávání: '"Anumanchipalli, Gopala Krishna"'
Articulatory trajectories like electromagnetic articulography (EMA) provide a low-dimensional representation of the vocal tract filter and have been used as natural, grounded features for speech synthesis. Differentiable digital signal processing (DD
Externí odkaz:
http://arxiv.org/abs/2409.02451
Autor:
Zhou, Xuanru, Kashyap, Anshul, Li, Steve, Sharma, Ayati, Morin, Brittany, Baquirin, David, Vonk, Jet, Ezzes, Zoe, Miller, Zachary, Tempini, Maria Luisa Gorno, Lian, Jiachen, Anumanchipalli, Gopala Krishna
Dysfluent speech detection is the bottleneck for disordered speech analysis and spoken language learning. Current state-of-the-art models are governed by rule-based systems which lack efficiency and robustness, and are sensitive to template design. I
Externí odkaz:
http://arxiv.org/abs/2408.15297
Autor:
Wu, Peter, Kaveh, Ryan, Nautiyal, Raghav, Zhang, Christine, Guo, Albert, Kachinthaya, Anvitha, Mishra, Tavish, Yu, Bohan, Black, Alan W, Muller, Rikky, Anumanchipalli, Gopala Krishna
Electrodes for decoding speech from electromyography (EMG) are typically placed on the face, requiring adhesives that are inconvenient and skin-irritating if used regularly. We explore a different device form factor, where dry electrodes are placed a
Externí odkaz:
http://arxiv.org/abs/2407.21345
Autor:
Netzorg, Robin, Cote, Alyssa, Koshin, Sumi, Garoute, Klo Vivienne, Anumanchipalli, Gopala Krishna
As experts in voice modification, trans-feminine gender-affirming voice teachers have unique perspectives on voice that confound current understandings of speaker identity. To demonstrate this, we present the Versatile Voice Dataset (VVD), a collecti
Externí odkaz:
http://arxiv.org/abs/2407.07235
Autor:
Lian, Jiachen, Feng, Carly, Farooqi, Naasir, Li, Steve, Kashyap, Anshul, Cho, Cheol Jun, Wu, Peter, Netzorg, Robbie, Li, Tingle, Anumanchipalli, Gopala Krishna
Dysfluent speech modeling requires time-accurate and silence-aware transcription at both the word-level and phonetic-level. However, current research in dysfluency modeling primarily focuses on either transcription or detection, and the performance o
Externí odkaz:
http://arxiv.org/abs/2312.12810
Perceptual modification of voice is an elusive goal. While non-experts can modify an image or sentence perceptually with available tools, it is not clear how to similarly modify speech along perceptual axes. Voice conversion does make it possible to
Externí odkaz:
http://arxiv.org/abs/2312.08494
In this paper, we propose a novel unsupervised text-to-speech (UTTS) framework which does not require text-audio pairs for the TTS acoustic modeling (AM). UTTS is a multi-speaker speech synthesizer that supports zero-shot voice cloning, it is develop
Externí odkaz:
http://arxiv.org/abs/2206.02512
Disentangling content and speaking style information is essential for zero-shot non-parallel voice conversion (VC). Our previous study investigated a novel framework with disentangled sequential variational autoencoder (DSVAE) as the backbone for inf
Externí odkaz:
http://arxiv.org/abs/2205.05227
Most of the research on data-driven speech representation learning has focused on raw audios in an end-to-end manner, paying little attention to their internal phonological or gestural structure. This work, investigating the speech representations de
Externí odkaz:
http://arxiv.org/abs/2204.00465
Publikováno v:
2013 IEEE International Conference on Acoustics, Speech & Signal Processing; 2013, p6915-6919, 5p