Efficient Weight factorization for Multilingual Speech Recognition
| Autor: | Ngoc-Quan Pham, Sebastian Stüker, Tuan-Nam Nguyen, Alex Waibel |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
FOS: Computer and information sciences
Sound (cs.SD) Computer Science - Computation and Language Computer science Speech recognition 020206 networking & telecommunications 02 engineering and technology Computer Science - Sound 030507 speech-language pathology & audiology 03 medical and health sciences Factorization Audio and Speech Processing (eess.AS) 0202 electrical engineering electronic engineering information engineering FOS: Electrical engineering electronic engineering information engineering 0305 other medical science Computation and Language (cs.CL) Electrical Engineering and Systems Science - Audio and Speech Processing |
| Zdroj: | Interspeech 2021 |
| Popis: | End-to-end multilingual speech recognition involves using a single model training on a compositional speech corpus including many languages, resulting in a single neural network to handle transcribing different languages. Due to the fact that each language in the training data has different characteristics, the shared network may struggle to optimize for all various languages simultaneously. In this paper we propose a novel multilingual architecture that targets the core operation in neural networks: linear transformation functions. The key idea of the method is to assign fast weight matrices for each language by decomposing each weight matrix into a shared component and a language dependent component. The latter is then factorized into vectors using rank-1 assumptions to reduce the number of parameters per language. This efficient factorization scheme is proved to be effective in two multilingual settings with $7$ and $27$ languages, reducing the word error rates by $26\%$ and $27\%$ rel. for two popular architectures LSTM and Transformer, respectively. Submitted to Interspeech 2021 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|