Dynamic Chunk Convolution For Unified Streaming And Non-streaming Conformer ASR
2023 · Xilai Li, Goeric Huybrechts, Srikanth Ronanki, et al.
Abstract
Recently, there has been an increasing interest in unifying streaming and non-streaming speech recognition models to reduce development, training and deployment cost. The best-known approaches rely on either window-based or dynamic chunk-based attention strategy and causal convolutions to minimize the degradation due to streaming. However, the performance gap still remains relatively large between non-streaming and a full-contextual model trained independently. To address this, we propose a dynamic chunk-based convolution replacing the causal convolution in a hybrid Connectionist Temporal Classification (CTC)-Attention Conformer architecture. Additionally, we demonstrate further improvements through initialization of weights from a full-contextual model and parallelization of the convolution and self-attention modules. We evaluate our models on the open-source Voxpopuli, LibriSpeech and in-house conversational datasets. Overall, our proposed model reduces the degradation of the streami
Authors
(none)
Tags
Stats
Related papers
- Sscformer: Push The Limit Of Chunk-wise Conformer For Streaming ASR Using Sequentially Sampled Chunks And Chunked Causal Convolution (2022)3.58
- Dctx-conformer: Dynamic Context Carry-over For Low Latency Unified Streaming And Non-streaming Conformer ASR (2023)2.26
- Unified Streaming And Non-streaming Two-pass End-to-end Model For Speech Recognition (2020)0.00
- Stateful Conformer With Cache-based Inference For Streaming Automatic Speech Recognition (2023)8.60
- Streaming Transformer Transducer Based Speech Recognition Using Non-causal Convolution (2021)8.82
- Dualvc 2: Dynamic Masked Convolution For Unified Streaming And Non-streaming Voice Conversion (2023)5.84
- Chunked Attention-based Encoder-decoder Model For Streaming Speech Recognition (2023)7.81
- CUSIDE: Chunking, Simulating Future Context And Decoding For Streaming ASR (2022)7.50