Transformer ASR With Contextual Block Processing

Abstract

The Transformer self-attention network has recently shown promising performance as an alternative to recurrent neural networks (RNNs) in end-to-end (E2E) automatic speech recognition (ASR) systems. However, the Transformer has a drawback in that the entire input sequence is required to compute self-attention. In this paper, we propose a new block processing method for the Transformer encoder by introducing a context-aware inheritance mechanism. An additional context embedding vector handed over from the previously processed block helps to encode not only local acoustic information but also global linguistic, channel, and speaker attributes. We introduce a novel mask technique to implement the context inheritance to train the model efficiently. Evaluations of the Wall Street Journal (WSJ), Librispeech, VoxForge Italian, and AISHELL-1 Mandarin speech recognition datasets show that our proposed contextual block processing method outperforms naive block processing consistently. Furthermore

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keytsunoo2019transformer

Related papers

• Towards Online End-to-end Transformer Automatic Speech Recognition (2019)0.00
• Improving Transformer-based Conversational ASR By Inter-sentential Attention Mechanism (2022)7.50
• Transformers With Convolutional Context For ASR (2019)0.00
• Blockwise Streaming Transformer For Spoken Language Understanding And Simultaneous Speech Translation (2022)4.52
• Advanced Long-context End-to-end Speech Recognition Using Context-expanded Transformers (2021)10.07
• Transformer-transducer: End-to-end Speech Recognition With Self-attention (2019)0.00
• Attention-based ASR With Lightweight And Dynamic Convolutions (2019)9.03
• Towards Effective And Compact Contextual Representation For Conformer Transducer Speech Recognition Systems (2023)7.16