paper-with-me

Papers

Listen and Fill in the Missing Letters: Non-Autoregressive Transformer for Speech Recognition

2019-11-10 · Nanxin Chen, Shinji Watanabe, Jesús Villalba, Najim Dehak

Recently very deep transformers have outperformed conventional bi-directional long short-term memory networks by a large margin in speech recognition. However, to put it into production usage, inference computation cost is still a serious concern in real scenarios. In this paper, we study two different non-autoregressive transformer structure for automatic speech recognition (ASR): A-CMLM and A-FMLM. During training, for both frameworks, input tokens fed to the decoder are randomly replaced by special mask tokens. The network is required to predict the tokens corresponding to those mask tokens by taking both unmasked context and input speech into consideration. During inference, we start from all mask tokens and the network iteratively predicts missing tokens based on partial results. We show that this framework can support different decoding strategies, including traditional left-to-right. A new decoding strategy is proposed as an example, which starts from the easiest predictions to the most difficult ones. Results on Mandarin (Aishell) and Japanese (CSJ) ASR benchmarks show the possibility to train such a non-autoregressive network for ASR. Especially in Aishell, the proposed method outperformed the Kaldi ASR system and it matches the performance of the state-of-the-art autoregressive transformer with 7x speedup. Pretrained models and code will be made available after publication.

📄 PDF Abstract BibTeX arXiv:1911.04908

Code (0)

등록된 구현이 없습니다.

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)DecoderMachine Translationspeech-recognitionSpeech Recognition

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
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
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…
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

Diverse Image Inpainting with Bidirectional and Autoregressive Transformers

2021-04-26 · Yingchen Yu, Fangneng Zhan, Rongliang Wu, Jianxiong Pan 외

Image inpainting is an underdetermined inverse problem, which naturally allows diverse contents to fill up the missing or corrupted regions realistically. Prevalent approaches using convolutional neural networks (CNNs) c…

DiversityImage InpaintingLanguage ModelingLanguage Modelling

Can Language Models Learn to Listen?

2023-08-21 · ICCV 2023 1 · Evonne Ng, Sanjay Subramanian, Dan Klein, Angjoo Kanazawa 외

We present a framework for generating appropriate facial responses from a listener in dyadic social interactions based on the speaker's words. Given an input transcription of the speaker's words with their timestamps, ou…

Language ModelingLanguage ModellingLarge Language Model

Listen Attentively, and Spell Once: Whole Sentence Generation via a Non-Autoregressive Architecture for Low-Latency Speech Recognition

2020-05-11 · Ye Bai, Jiangyan Yi, Jian-Hua Tao, Zhengkun Tian 외

Although attention based end-to-end models have achieved promising performance in speech recognition, the multi-pass forward computation in beam-search increases inference time cost, which limits their practical applicat…

Sentencespeech-recognitionSpeech Recognition

Effectiveness of Linguistic and Learner Features to Listenability Measurement Using a Decision Tree Classifier

2016-12-01 · WS 2016 12 · Katsunori Kotani, Takehiko Yoshimi

In learning Asian languages, learners encounter the problem of character types that are different from those in their first language, for instance, between Chinese characters and the Latin alphabet. This problem also aff…

Reading Comprehension

DiffListener: Discrete Diffusion Model for Listener Generation

2025-02-05 · Siyeol Jung, Taehwan Kim

The listener head generation (LHG) task aims to generate natural nonverbal listener responses based on the speaker's multimodal cues. While prior work either rely on limited modalities (e.g. audio and facial information)…

model