111 citations · 391 across the 44 of their papers we have counts for
6 papers · 1 filter
Sequence-to-Sequence ASR Optimization via Reinforcement Learning
Andros Tjandra, Sakriani Sakti, Satoshi Nakamura
Despite the success of sequence-to-sequence approaches in automatic speech recognition (ASR) systems, the models still suffer from several problems, mainly due to the mismatch betw…
Attention-based Wav2Text with Feature Transfer Learning
Andros Tjandra, Sakriani Sakti, Satoshi Nakamura
Conventional automatic speech recognition (ASR) typically performs multi-level pattern recognition tasks that map the acoustic speech waveform into a hierarchy of speech units. But…
Listening while Speaking: Speech Chain by Deep Learning
Andros Tjandra, Sakriani Sakti, Satoshi Nakamura
Despite the close relationship between speech perception and production, research in automatic speech recognition (ASR) and text-to-speech synthesis (TTS) has progressed more or le…
Gated Recurrent Neural Tensor Network
Andros Tjandra, Sakriani Sakti, Ruli Manurung +2
Recurrent Neural Networks (RNNs), which are a powerful scheme for modeling temporal and sequential data need to capture long-term dependencies on datasets and represent them in hid…
Compressing Recurrent Neural Network with Tensor Train
Andros Tjandra, Sakriani Sakti, Satoshi Nakamura
Recurrent Neural Network (RNN) are a popular choice for modeling temporal and sequential tasks and achieve many state-of-the-art performance on various complex problems. However, m…
Local Monotonic Attention Mechanism for End-to-End Speech and Language Processing
Andros Tjandra, Sakriani Sakti, Satoshi Nakamura
Recently, encoder-decoder neural networks have shown impressive performance on many sequence-related tasks. The architecture commonly uses an attentional mechanism which allows the…