Learning Online Alignments With Continuous Rewards Policy Gradient
2016 · Yuping Luo, Chung-Cheng Chiu, Navdeep Jaitly, et al.
Abstract
Sequence-to-sequence models with soft attention had significant success in machine translation, speech recognition, and question answering. Though capable and easy to use, they require that the entirety of the input sequence is available at the beginning of inference, an assumption that is not valid for instantaneous translation and speech recognition. To address this problem, we present a new method for solving sequence-to-sequence problems using hard online alignments instead of soft offline alignments. The online alignments model is able to start producing outputs without the need to first process the entire input sequence. A highly accurate online sequence-to-sequence model is useful because it can be used to build an accurate voice-based instantaneous translator. Our model uses hard binary stochastic decisions to select the timesteps at which outputs will be produced. The model is trained to produce these stochastic decisions using a standard policy gradient method. In our experim
Authors
(none)
Tags
Stats
Related papers
- An Online Sequence-to-sequence Model For Noisy Speech Recognition (2017)0.00
- Incremental Text To Speech For Neural Sequence-to-sequence Models Using Reinforcement Learning (2020)5.24
- Pseudo-convolutional Policy Gradient For Sequence-to-sequence Lip-reading (2020)12.17
- Effect Of Choice Of Probability Distribution, Randomness, And Search Methods For Alignment Modeling In Sequence-to-sequence Text-to-speech Synthesis Using Hard Alignment (2019)5.84
- Alignatt: Using Attention-based Audio-translation Alignments As A Guide For Simultaneous Speech Translation (2023)3.58
- Minimum Latency Training Strategies For Streaming Sequence-to-sequence ASR (2020)10.07
- High Performance Sequence-to-sequence Model For Streaming Speech Recognition (2020)3.58
- Robust Sequence-to-sequence Acoustic Modeling With Stepwise Monotonic Attention For Neural TTS (2019)11.49