Zobrazeno 1 - 10
of 344
pro vyhledávání: '"Black, Alan W"'
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:
Cho, Cheol Jun, Mohamed, Abdelrahman, Li, Shang-Wen, Black, Alan W, Anumanchipalli, Gopala K.
Data-driven unit discovery in self-supervised learning (SSL) of speech has embarked on a new era of spoken language processing. Yet, the discovered units often remain in phonetic space and the units beyond phonemes are largely underexplored. Here, we
Externí odkaz:
http://arxiv.org/abs/2310.10803
Self-Supervised Learning (SSL) based models of speech have shown remarkable performance on a range of downstream tasks. These state-of-the-art models have remained blackboxes, but many recent studies have begun "probing" models like HuBERT, to correl
Externí odkaz:
http://arxiv.org/abs/2310.10788
Autor:
Wu, Peter, Li, Tingle, Lu, Yijing, Zhang, Yubin, Lian, Jiachen, Black, Alan W, Goldstein, Louis, Watanabe, Shinji, Anumanchipalli, Gopala K.
In this paper, we study articulatory synthesis, a speech synthesis method using human vocal tract information that offers a way to develop efficient, generalizable and interpretable synthesizers. While recent advances have enabled intelligible articu
Externí odkaz:
http://arxiv.org/abs/2307.02471
Autor:
Wu, Peter, Chen, Li-Wei, Cho, Cheol Jun, Watanabe, Shinji, Goldstein, Louis, Black, Alan W, Anumanchipalli, Gopala K.
To build speech processing methods that can handle speech as naturally as humans, researchers have explored multiple ways of building an invertible mapping from speech to an interpretable space. The articulatory space is a promising inversion target,
Externí odkaz:
http://arxiv.org/abs/2302.06774
Autor:
Lian, Jiachen, Black, Alan W, Lu, Yijing, Goldstein, Louis, Watanabe, Shinji, Anumanchipalli, Gopala K.
Articulatory representation learning is the fundamental research in modeling neural speech production system. Our previous work has established a deep paradigm to decompose the articulatory kinematics data into gestures, which explicitly model the ph
Externí odkaz:
http://arxiv.org/abs/2210.16498
Estimation of fundamental frequency (F0) in voiced segments of speech signals, also known as pitch tracking, plays a crucial role in pitch synchronous speech analysis, speech synthesis, and speech manipulation. In this paper, we capitalize on the hig
Externí odkaz:
http://arxiv.org/abs/2210.15272
Autor:
Arora, Siddhant, Dalmia, Siddharth, Yan, Brian, Metze, Florian, Black, Alan W, Watanabe, Shinji
End-to-end spoken language understanding (SLU) systems are gaining popularity over cascaded approaches due to their simplicity and ability to avoid error propagation. However, these systems model sequence labeling as a sequence prediction task causin
Externí odkaz:
http://arxiv.org/abs/2210.15734
Autor:
Yan, Brian, Dalmia, Siddharth, Higuchi, Yosuke, Neubig, Graham, Metze, Florian, Black, Alan W, Watanabe, Shinji
Connectionist Temporal Classification (CTC) is a widely used approach for automatic speech recognition (ASR) that performs conditionally independent monotonic alignment. However for translation, CTC exhibits clear limitations due to the contextual an
Externí odkaz:
http://arxiv.org/abs/2210.05200
In the articulatory synthesis task, speech is synthesized from input features containing information about the physical behavior of the human vocal tract. This task provides a promising direction for speech synthesis research, as the articulatory spa
Externí odkaz:
http://arxiv.org/abs/2209.06337