paper-with-me

Papers

Multi-Task Learning with Auxiliary Speaker Identification for Conversational Emotion Recognition

2020-03-03 · Jingye Li, Meishan Zhang, Donghong Ji, Yijiang Liu

Conversational emotion recognition (CER) has attracted increasing interests in the natural language processing (NLP) community. Different from the vanilla emotion recognition, effective speaker-sensitive utterance representation is one major challenge for CER. In this paper, we exploit speaker identification (SI) as an auxiliary task to enhance the utterance representation in conversations. By this method, we can learn better speaker-aware contextual representations from the additional SI corpus. Experiments on two benchmark datasets demonstrate that the proposed architecture is highly effective for CER, obtaining new state-of-the-art results on two datasets.

📄 PDF Abstract BibTeX arXiv:2003.01478

Code (0)

등록된 구현이 없습니다.

Tasks

Emotion Recognition in ConversationMulti-Task LearningSpeaker Identification

Similar Papers 제목 키워드 기반

Speaker-Distinguishable CTC: Learning Speaker Distinction Using CTC for Multi-Talker Speech Recognition

2025-06-09 · Asahi Sakuma, Hiroaki Sato, Ryuga Sugano, Tadashi Kumano 외

This paper presents a novel framework for multi-talker automatic speech recognition without the need for auxiliary information. Serialized Output Training (SOT), a widely used approach, suffers from recognition errors du…

Automatic Speech RecognitionMulti-Task Learningspeech-recognitionSpeech Recognition

Speech Enhancement using Self-Adaptation and Multi-Head Self-Attention

2020-02-14 · Yuma Koizumi, Kohei Yatabe, Marc Delcroix, Yoshiki Masuyama 외

This paper investigates a self-adaptation method for speech enhancement using auxiliary speaker-aware features; we extract a speaker representation used for adaptation directly from the test utterance. Conventional studi…

Multi-Task LearningSpeaker IdentificationSpeech Enhancementspeech-recognition+1

Towards Making the Most of Dialogue Characteristics for Neural Chat Translation

2021-09-02 · EMNLP 2021 11 · Yunlong Liang, Chulun Zhou, Fandong Meng, Jinan Xu 외

Neural Chat Translation (NCT) aims to translate conversational text between speakers of different languages. Despite the promising performance of sentence-level and context-aware neural machine translation models, there …

Machine TranslationResponse GenerationSentenceSpeaker Identification+1

Reusing Preprocessing Data as Auxiliary Supervision in Conversational Analysis

2021-01-01 · Joshua Yee Kim, Kalina Yacef

Conversational analysis systems are trained using noisy human labels and often require heavy preprocessing during multi-modal feature extraction. Using noisy labels in single-task learning increases the risk of over-fitt…

Feature EngineeringMulti-Task Learning

Transfer Learning in Conversational Analysis through Reusing Preprocessing Data as Supervisors

2021-12-02 · Joshua Yee Kim, Tongliang Liu, Kalina Yacef

Conversational analysis systems are trained using noisy human labels and often require heavy preprocessing during multi-modal feature extraction. Using noisy labels in single-task learning increases the risk of over-fitt…

Feature EngineeringMulti-Task LearningTransfer Learning