Title | ||
---|---|---|
Bidirectional Quaternion Long Short-Term Memory Recurrent Neural Networks For Speech Recognition |
Abstract | ||
---|---|---|
Recurrent neural networks (RNN) are at the core of modern automatic speech recognition (ASR) systems. In particular, long short-term memory (LSTM) recurrent neural networks have achieved state-of-the-art results in many speech recognition tasks, due to their efficient representation of long and short term dependencies in sequences of inter-dependent features. Nonetheless, internal dependencies within the element composing multidimensional features are weakly considered by traditional real-valued representations. We propose a novel quaternion long short-term memory (QLTM) recurrent neural network that takes into account both the external relations between the features composing a sequence, and these internal latent structural dependencies with the quaternion algebra. QLSTMs are compared to LSTMs during a memory copy-task and a realistic application of speech recognition on the Wall Street Journal (WSJ) dataset. QLSTM reaches better performances during the two experiments with up to 2:8 times less learning parameters, leading to a more expressive representation of the information. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/ICASSP.2019.8683583 | 2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP) |
Keywords | Field | DocType |
Quaternion long-short term memory, recurrent neural networks, speech recognition | Pattern recognition,Computer science,Quaternion,Long short term memory,Recurrent neural network,Quaternion algebra,Speech recognition,Artificial intelligence | Conference |
ISSN | Citations | PageRank |
1520-6149 | 0 | 0.34 |
References | Authors | |
0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Titouan Parcollet | 1 | 16 | 9.23 |
Mohamed Morchid | 2 | 84 | 22.79 |
georges linar es | 3 | 136 | 29.55 |
Renato De Mori | 4 | 960 | 161.75 |