paper-with-me

Papers

Streaming Transformer-based Acoustic Models Using Self-attention with Augmented Memory

2020-05-16 · Chunyang Wu, Yongqiang Wang, Yangyang Shi, Ching-Feng Yeh, Frank Zhang

Transformer-based acoustic modeling has achieved great suc-cess for both hybrid and sequence-to-sequence speech recogni-tion. However, it requires access to the full sequence, and thecomputational cost grows quadratically with respect to the in-put sequence length. These factors limit its adoption for stream-ing applications. In this work, we proposed a novel augmentedmemory self-attention, which attends on a short segment of theinput sequence and a bank of memories. The memory bankstores the embedding information for all the processed seg-ments. On the librispeech benchmark, our proposed methodoutperforms all the existing streamable transformer methods bya large margin and achieved over 15% relative error reduction,compared with the widely used LC-BLSTM baseline. Our find-ings are also confirmed on some large internal datasets.

📄 PDF Abstract BibTeX arXiv:2005.08042

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Residual Connection 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Multi-Head Attention 설명 없음
Adam 설명 없음
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…

Similar Papers 제목 키워드 기반

Emformer: Efficient Memory Transformer Based Acoustic Model For Low Latency Streaming Speech Recognition

2020-10-21 · Yangyang Shi, Yongqiang Wang, Chunyang Wu, Ching-Feng Yeh 외

This paper proposes an efficient memory transformer Emformer for low latency streaming speech recognition. In Emformer, the long-range history context is distilled into an augmented memory bank to reduce self-attention's…

speech-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

Streaming Transformer ASR with Blockwise Synchronous Inference

2020-06-25 · Emiru Tsunoo, Yosuke Kashiwagi, Shinji Watanabe

The Transformer self-attention network has recently shown promising performance as an alternative to recurrent neural networks in end-to-end (E2E) automatic speech recognition (ASR) systems. However, Transformer has a dr…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)DecoderKnowledge Distillation+2

Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss

2020-02-07 · Qian Zhang, Han Lu, Hasim Sak, Anshuman Tripathi 외

In this paper we present an end-to-end speech recognition model with Transformer encoders that can be used in a streaming speech recognition system. Transformer computation blocks based on self-attention are used to enco…

speech-recognitionSpeech Recognition

ConvRNN-T: Convolutional Augmented Recurrent Neural Network Transducers for Streaming Speech Recognition

2022-09-29 · Martin Radfar, Rohit Barnwal, Rupak Vignesh Swaminathan, Feng-Ju Chang 외

The recurrent neural network transducer (RNN-T) is a prominent streaming end-to-end (E2E) ASR technology. In RNN-T, the acoustic encoder commonly consists of stacks of LSTMs. Very recently, as an alternative to LSTM laye…

speech-recognitionSpeech Recognition