Zobrazeno 1 - 10
of 452
pro vyhledávání: '"Fujita, Yuya"'
Non-autoregressive (NAR) models for automatic speech recognition (ASR) aim to achieve high accuracy and fast inference by simplifying the autoregressive (AR) generation process of conventional models. Connectionist temporal classification (CTC) is on
Externí odkaz:
http://arxiv.org/abs/2403.19207
Recently, the usefulness of self-supervised representation learning (SSRL) methods has been confirmed in various downstream tasks. Many of these models, as exemplified by HuBERT and WavLM, use pseudo-labels generated from spectral features or the mod
Externí odkaz:
http://arxiv.org/abs/2310.03975
Recent works in end-to-end speech-to-text translation (ST) have proposed multi-tasking methods with soft parameter sharing which leverage machine translation (MT) data via secondary encoders that map text inputs to an eventual cross-modal representat
Externí odkaz:
http://arxiv.org/abs/2309.15826
Autor:
Chang, Xuankai, Yan, Brian, Choi, Kwanghee, Jung, Jeeweon, Lu, Yichen, Maiti, Soumi, Sharma, Roshan, Shi, Jiatong, Tian, Jinchuan, Watanabe, Shinji, Fujita, Yuya, Maekaku, Takashi, Guo, Pengcheng, Cheng, Yao-Fei, Denisov, Pavel, Saijo, Kohei, Wang, Hsiu-Hsuan
Speech signals, typically sampled at rates in the tens of thousands per second, contain redundancies, evoking inefficiencies in sequence modeling. High-dimensional speech features such as spectrograms are often used as the input for the subsequent mo
Externí odkaz:
http://arxiv.org/abs/2309.15800
Self-supervised learning (SSL) of speech has shown impressive results in speech-related tasks, particularly in automatic speech recognition (ASR). While most methods employ the output of intermediate layers of the SSL model as real-valued features fo
Externí odkaz:
http://arxiv.org/abs/2305.18108
The black-box nature of end-to-end speech translation (E2E ST) systems makes it difficult to understand how source language inputs are being mapped to the target language. To solve this problem, we would like to simultaneously generate automatic spee
Externí odkaz:
http://arxiv.org/abs/2211.05967
This work presents our end-to-end (E2E) automatic speech recognition (ASR) model targetting at robust speech recognition, called Integraded speech Recognition with enhanced speech Input for Self-supervised learning representation (IRIS). Compared wit
Externí odkaz:
http://arxiv.org/abs/2204.00540
Autor:
Fukuma, Ryohei, Yanagisawa, Takufumi, Nishimoto, Shinji, Sugano, Hidenori, Tamura, Kentaro, Yamamoto, Shota, Iimura, Yasushi, Fujita, Yuya, Oshino, Satoru, Tani, Naoki, Koide-Majima, Naoko, Kamitani, Yukiyasu, Kishima, Haruhiko
Neural representations of visual perception are affected by mental imagery and attention. Although attention is known to modulate neural representations, it is unknown how imagery changes neural representations when imagined and perceived images sema
Externí odkaz:
http://arxiv.org/abs/2112.01223
Autor:
Higuchi, Yosuke, Chen, Nanxin, Fujita, Yuya, Inaguma, Hirofumi, Komatsu, Tatsuya, Lee, Jaesong, Nozaki, Jumon, Wang, Tianzi, Watanabe, Shinji
Non-autoregressive (NAR) models simultaneously generate multiple outputs in a sequence, which significantly reduces the inference speed at the cost of accuracy drop compared to autoregressive baselines. Showing great potential for real-time applicati
Externí odkaz:
http://arxiv.org/abs/2110.05249
Non-autoregressive (NAR) modeling has gained more and more attention in speech processing. With recent state-of-the-art attention-based automatic speech recognition (ASR) structure, NAR can realize promising real-time factor (RTF) improvement with on
Externí odkaz:
http://arxiv.org/abs/2107.09428