paper-with-me

홈 › Papers

Improving Transformer-based Conversational ASR by Inter-Sentential Attention Mechanism

2022-07-02 · Kun Wei, Pengcheng Guo, Ning Jiang

Transformer-based models have demonstrated their effectiveness in automatic speech recognition (ASR) tasks and even shown superior performance over the conventional hybrid framework. The main idea of Transformers is to capture the long-range global context within an utterance by self-attention layers. However, for scenarios like conversational speech, such utterance-level modeling will neglect contextual dependencies that span across utterances. In this paper, we propose to explicitly model the inter-sentential information in a Transformer based end-to-end architecture for conversational speech recognition. Specifically, for the encoder network, we capture the contexts of previous speech and incorporate such historic information into current input by a context-aware residual attention mechanism. For the decoder, the prediction of current utterance is also conditioned on the historic linguistic information through a conditional decoder framework. We show the effectiveness of our proposed method on several open-source dialogue corpora and the proposed method consistently improved the performance from the utterance-level Transformer-based ASR models.

📄 PDF Abstract BibTeX arXiv:2207.00883

Code (0)

등록된 구현이 없습니다.

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Decoderspeech-recognitionSpeech Recognition

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Multi-Head Attention 설명 없음
Residual Connection 설명 없음
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…
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…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

Similar Papers 제목 키워드 기반

Modeling Context With Linear Attention for Scalable Document-Level Translation

2021-10-16 · ACL ARR October 2021 10 · Anonymous

Document-level neural machine translation allows models to leverage dependencies beyond sentence-internal context to produce more coherent and consistent translations. However, these models, predominantly based on transf…

Document TranslationMachine TranslationSentenceTranslation

Modeling Context With Linear Attention for Scalable Document-Level Translation

2022-10-16 · Zhaofeng Wu, Hao Peng, Nikolaos Pappas, Noah A. Smith

Document-level machine translation leverages inter-sentence dependencies to produce more coherent and consistent translations. However, these models, predominantly based on transformers, are difficult to scale to long do…

Document Level Machine TranslationDocument TranslationInductive BiasMachine Translation+2

Exploiting Sentential Context for Neural Machine Translation

2019-06-04 · ACL 2019 7 · Xing Wang, Zhaopeng Tu, Long-Yue Wang, Shuming Shi

In this work, we present novel approaches to exploit sentential context for neural machine translation (NMT). Specifically, we first show that a shallow sentential context extracted from the top encoder layer only, can i…

Machine TranslationNMTTranslation

Guided Transformer: Leveraging Multiple External Sources for Representation Learning in Conversational Search

2020-06-13 · Helia Hashemi, Hamed Zamani, W. Bruce Croft

Asking clarifying questions in response to ambiguous or faceted queries has been recognized as a useful technique for various information retrieval systems, especially conversational search systems with limited bandwidth…

Conversational SearchInformation RetrievalQuestion SelectionRepresentation Learning+1

Generating Sentential Arguments from Diverse Perspectives on Controversial Topic

2019-11-01 · WS 2019 11 · ChaeHun Park, Wonsuk Yang, Jong Park

Considering diverse aspects of an argumentative issue is an essential step for mitigating a biased opinion and making reasonable decisions. A related generation model can produce flexible results that cover a wide range …

DiversityRetrieval