paper-with-me

Papers

Variable Attention Masking for Configurable Transformer Transducer Speech Recognition

2022-11-02 · Pawel Swietojanski, Stefan Braun, Dogan Can, Thiago Fraga da Silva, Arnab Ghoshal, Takaaki Hori, Roger Hsiao, Henry Mason, Erik McDermott, Honza Silovsky, Ruchir Travadi, Xiaodan Zhuang

This work studies the use of attention masking in transformer transducer based speech recognition for building a single configurable model for different deployment scenarios. We present a comprehensive set of experiments comparing fixed masking, where the same attention mask is applied at every frame, with chunked masking, where the attention mask for each frame is determined by chunk boundaries, in terms of recognition accuracy and latency. We then explore the use of variable masking, where the attention masks are sampled from a target distribution at training time, to build models that can work in different configurations. Finally, we investigate how a single configurable model can be used to perform both first pass streaming recognition and second pass acoustic rescoring. Experiments show that chunked masking achieves a better accuracy vs latency trade-off compared to fixed masking, both with and without FastEmit. We also show that variable masking improves the accuracy by up to 8% relative in the acoustic re-scoring scenario.

📄 PDF Abstract BibTeX arXiv:2211.01438

Code (0)

등록된 구현이 없습니다.

Tasks

speech-recognitionSpeech Recognition

Similar Papers 제목 키워드 기반

XLSR-Transducer: Streaming ASR for Self-Supervised Pretrained Models

2024-07-05 · Shashi Kumar, Srikanth Madikeri, Juan Zuluaga-Gomez, Esaú Villatoro-Tello 외

Self-supervised pretrained models exhibit competitive performance in automatic speech recognition on finetuning, even with limited in-domain supervised data. However, popular pretrained models are not suitable for stream…

Automatic Speech Recognitionspeech-recognitionSpeech Recognition

Transformer-Transducer: End-to-End Speech Recognition with Self-Attention

2019-10-28 · Ching-Feng Yeh, Jay Mahadeokar, Kaustubh Kalgaonkar, Yongqiang Wang 외

We explore options to use Transformer networks in neural transducer for end-to-end speech recognition. Transformer networks use self-attention for sequence modeling and comes with advantages in parallel computation and c…

speech-recognitionSpeech Recognition

Developing Real-time Streaming Transformer Transducer for Speech Recognition on Large-scale Dataset

2020-10-22 · Xie Chen, Yu Wu, Zhenghao Wang, Shujie Liu 외

Recently, Transformer based end-to-end models have achieved great success in many areas including speech recognition. However, compared to LSTM models, the heavy computational cost of the Transformer during inference is …

Decoderspeech-recognitionSpeech Recognition

Exploring RWKV for Memory Efficient and Low Latency Streaming ASR

2023-09-26 · Keyu An, Shiliang Zhang

Recently, self-attention-based transformers and conformers have been introduced as alternatives to RNNs for ASR acoustic modeling. Nevertheless, the full-sequence attention mechanism is non-streamable and computationally…

Chunking

Research on Modeling Units of Transformer Transducer for Mandarin Speech Recognition

2020-04-26 · Li Fu, Xiaoxiao Li, Libo Zi

Modeling unit and model architecture are two key factors of Recurrent Neural Network Transducer (RNN-T) in end-to-end speech recognition. To improve the performance of RNN-T for Mandarin speech recognition task, a novel …

speech-recognitionSpeech Recognition