paper-with-me

홈 › Papers

A Unified Neural Architecture for Joint Dialog Act Segmentation and Recognition in Spoken Dialog System

2018-07-01 · WS 2018 7 · Tianyu Zhao, Tatsuya Kawahara

In spoken dialog systems (SDSs), dialog act (DA) segmentation and recognition provide essential information for response generation. A majority of previous works assumed ground-truth segmentation of DA units, which is not available from automatic speech recognition (ASR) in SDS. We propose a unified architecture based on neural networks, which consists of a sequence tagger for segmentation and a classifier for recognition. The DA recognition model is based on hierarchical neural networks to incorporate the context of preceding sentences. We investigate sharing some layers of the two components so that they can be trained jointly and learn generalized features from both tasks. An evaluation on the Switchboard Dialog Act (SwDA) corpus shows that the jointly-trained models outperform independently-trained models, single-step models, and other reported results in DA segmentation, recognition, and joint tasks.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Language ModelingLanguage ModellingResponse GenerationSegmentationspeech-recognitionSpeech RecognitionSpoken Language Understanding

Similar Papers 제목 키워드 기반

Joint Learning of Dialog Act Segmentation and Recognition in Spoken Dialog Using Neural Networks

2017-11-01 · IJCNLP 2017 11 · Tianyu Zhao, Tatsuya Kawahara

Dialog act segmentation and recognition are basic natural language understanding tasks in spoken dialog systems. This paper investigates a unified architecture for these two tasks, which aims to improve the model{'}s per…

Automatic Speech Recognition (ASR)Natural Language UnderstandingSegmentationSpeech Recognition+1

End-to-End Joint Semantic Segmentation of Actors and Actions in Video

2018-09-01 · ECCV 2018 9 · Jingwei Ji, Shyamal Buch, Alvaro Soto, Juan Carlos Niebles

Traditional video understanding tasks include human action recognition and actor/object semantic segmentation. However, the combined task of providing semantic segmentation for different actor classes simultaneously with…

Action RecognitionSegmentationSemantic SegmentationTemporal Action Localization+2

UniConv: A Unified Conversational Neural Architecture for Multi-domain Task-oriented Dialogues

2020-04-29 · EMNLP 2020 11 · Hung Le, Doyen Sahoo, Chenghao Liu, Nancy F. Chen 외

Building an end-to-end conversational agent for multi-domain task-oriented dialogues has been an open challenge for two main reasons. First, tracking dialogue states of multiple domains is non-trivial as the dialogue age…

Dialogue State Tracking

MuraNet: Multi-task Floor Plan Recognition with Relation Attention

2023-09-01 · Lingxiao Huang, Jung-Hsuan Wu, Chiching Wei, Wilson Li

The recognition of information in floor plan data requires the use of detection and segmentation models. However, relying on several single-task models can result in ineffective utilization of relevant information when t…

RelationSegmentation

End-to-end speech-to-dialog-act recognition

2020-04-23 · Viet-Trung Dang, Tianyu Zhao, Sei Ueno, Hirofumi Inaguma 외

Spoken language understanding, which extracts intents and/or semantic concepts in utterances, is conventionally formulated as a post-processing of automatic speech recognition. It is usually trained with oracle transcrip…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition+1