LAST: Scalable Lattice-Based Speech Modelling in JAX
We introduce LAST, a LAttice-based Speech Transducer library in JAX. With an emphasis on flexibility, ease-of-use, and scalability, LAST implements differentiable weighted finite state automaton (WFSA) algorithms needed for training \& inference that scale to a large WFSA such as a recognition lattice over the entire utterance. Despite these WFSA algorithms being well-known in the literature, new challenges arise from performance characteristics of modern architectures, and from nuances in automatic differentiation. We describe a suite of generally applicable techniques employed in LAST to address these challenges, and demonstrate their effectiveness with benchmarks on TPUv3 and V100 GPU.
Code (1)
Tasks
GPUMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
A Treatise On FST Lattice Based MMI Training
Maximum mutual information (MMI) has become one of the two de facto methods for sequence-level training of speech recognition acoustic models. This paper aims to isolate, identify and bring forward the implicit modelling…
speech-recognitionSpeech RecognitionEnergy-conserving equivariant GNN for elasticity of lattice architected metamaterials
Lattices are architected metamaterials whose properties strongly depend on their geometrical design. The analogy between lattices and graphs enables the use of graph neural networks (GNNs) as a faster surrogate model com…
LSTM Language Models for LVCSR in First-Pass Decoding and Lattice-Rescoring
LSTM based language models are an important part of modern LVCSR systems as they significantly improve performance over traditional backoff language models. Incorporating them efficiently into decoding has been notorious…
CUED@WMT19:EWC\&LMs
Two techniques provide the fabric of the Cambridge University Engineering Department{'}s (CUED) entry to the WMT19 evaluation campaign: elastic weight consolidation (EWC) and different forms of language modelling (LMs). …
Language ModellingSentenceLattice Transformer for Speech Translation
Recent advances in sequence modeling have highlighted the strengths of the transformer architecture, especially in achieving state-of-the-art machine translation results. However, depending on the up-stream systems, e.g.…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Machine Translationspeech-recognition+2