Phoneme boundary estimation using bidirectional recurrent neural networks and its applications

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Deep learning in neural networks: An overview (2014, background): “Bi-directional RNNs (BRNNs) (Schuster, 1999; Schuster & Paliwal, 1997) are designed for input sequences whose starts and ends are known in advance, such as spoken sentences to be labeled by their phonemes; compare Fukada, Schuster, and Sagisaka (1999).”
Framewise phoneme classification with bidirectional LSTM and other neural network architectures (2005, unknown): “BRNNs have given improved results in sequence learning tasks, notably protein structure prediction (PSP) (Baldi et al., 2001; Chen and Chaudhari, 2004) and speech processing (Schuster, 1999; Fukada et al., 1999).”
Supervised Sequence Labelling with Recurrent Neural Networks (2012, background): “, 2001; Chen and Chaudhari, 2004) and speech processing (Schuster, 1999; Fukada et al., 1999), and we find that they consistently outperform unidirectional RNNs at sequence labelling.”
Framewise phoneme classification with bidirectional LSTM networks (2005, unknown): “Bidirectional recurrent neural nets (BRNNs) have given significantly improved results in sequence learning tasks, notably protein structure prediction (PSP) [1], [6] and speech processing [21], [9].”
A Novel Connectionist System for Unconstrained Handwriting Recognition (2009, methodology): “BRNNs have outperformed standard RNNs in several sequence learning tasks, notably protein structure prediction [43] and speech processing [41], [44].”