261 citations · 682 across the 43 of their papers we have counts for
4 papers · 2 filters
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…
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…