Self-Attention Transducers for End-to-End Speech Recognition
Recurrent neural network transducers (RNN-T) have been successfully applied in end-to-end speech recognition. However, the recurrent structure makes it difficult for parallelization . In this paper, we propose a self-attention transducer (SA-T) for speech recognition. RNNs are replaced with self-attention blocks, which are powerful to model long-term dependencies inside sequences and able to be efficiently parallelized. Furthermore, a path-aware regularization is proposed to assist SA-T to learn alignments and improve the performance. Additionally, a chunk-flow mechanism is utilized to achieve online decoding. All experiments are conducted on a Mandarin Chinese dataset AISHELL-1. The results demonstrate that our proposed approach achieves a 21.3% relative reduction in character error rate compared with the baseline RNN-T. In addition, the SA-T with chunk-flow mechanism can perform online decoding with only a little degradation of the performance.
Code (0)
등록된 구현이 없습니다.
Tasks
speech-recognitionSpeech RecognitionSimilar Papers 제목 키워드 기반
HENT-SRT: Hierarchical Efficient Neural Transducer with Self-Distillation for Joint Speech Recognition and Translation
Neural transducers (NT) provide an effective framework for speech streaming, demonstrating strong performance in automatic speech recognition (ASR). However, the application of NT to speech translation (ST) remains chall…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Computational EfficiencyDecoder+3Anchored Speech Recognition with Neural Transducers
Neural transducers have achieved human level performance on standard speech recognition benchmarks. However, their performance significantly degrades in the presence of cross-talk, especially when the primary speaker has…
speech-recognitionSpeech RecognitionComposing Finite State Transducers on GPUs
Weighted finite-state transducers (FSTs) are frequently used in language processing to handle tasks such as part-of-speech tagging and speech recognition. There has been previous work using multiple CPU cores to accelera…
CPUGPUPart-Of-Speech Taggingspeech-recognition+1LAMASSU: Streaming Language-Agnostic Multilingual Speech Recognition and Translation Using Neural Transducers
Automatic speech recognition (ASR) and speech translation (ST) can both use neural transducers as the model structure. It is thus possible to use a single transducer model to perform both tasks. In real-world application…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Language Identificationspeech-recognition+3Accelerating Transducers through Adjacent Token Merging
Recent end-to-end automatic speech recognition (ASR) systems often utilize a Transformer-based acoustic encoder that generates embedding at a high frame rate. However, this design is inefficient, particularly for long sp…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)GPUspeech-recognition+1