CUSIDE-T: Chunking, Simulating Future And Decoding For Transducer Based Streaming ASR
2024 · Wenbo Zhao, Ziwei Li, Chuan Yu, et al.
Abstract
Streaming automatic speech recognition (ASR) is very important for many real-world ASR applications. However, a notable challenge for streaming ASR systems lies in balancing operational performance against latency constraint. Recently, a method of chunking, simulating future context and decoding, called CUSIDE, has been proposed for connectionist temporal classification (CTC) based streaming ASR, which obtains a good balance between reduced latency and high recognition accuracy. In this paper, we present CUSIDE-T, which successfully adapts the CUSIDE method over the recurrent neural network transducer (RNN-T) ASR architecture, instead of being based on the CTC architecture. We also incorporate language model rescoring in CUSIDE-T to further enhance accuracy, while only bringing a small additional latency. Extensive experiments are conducted over the AISHELL-1, WenetSpeech and SpeechIO datasets, comparing CUSIDE-T and U2++ (both based on RNN-T). U2++ is an existing counterpart of chunk
Authors
(none)
Tags
Stats
Related papers
- CUSIDE: Chunking, Simulating Future Context And Decoding For Streaming ASR (2022)7.50
- Cuside-array: A Streaming Multi-channel End-to-end Speech Recognition System With Realistic Evaluations (2024)0.00
- An Investigation Of Enhancing CTC Model For Triggered Attention-based Streaming ASR (2021)0.00
- Dynamic Chunk Convolution For Unified Streaming And Non-streaming Conformer ASR (2023)6.77
- Sscformer: Push The Limit Of Chunk-wise Conformer For Streaming ASR Using Sequentially Sampled Chunks And Chunked Causal Convolution (2022)3.58
- Lookahead When It Matters: Adaptive Non-causal Transformers For Streaming Neural Transducers (2023)0.00
- Mask-ctc-based Encoder Pre-training For Streaming End-to-end Speech Recognition (2023)0.00
- Bridging The Gap Between Streaming And Non-streaming ASR Systems Bydistilling Ensembles Of CTC And RNN-T Models (2021)3.58