Shiwan Zhao
Shiwan Zhao has 3 papers in our library, in 2026, most of them on Sentiment & emotion, Speech & spoken language, Vision & language; often with Haoqin Sun, Hui Wang, Jiaming Zhou.
OpenAlex · h-index 0 · 3 works · 0 citations OpenAlex, 2026-10-14
📄 3 works in our library · 🔗 Cited 6 times in our library · 1 more in our library without a page yet · ⭐ Paper Stars ranking: #10011
Affiliations
Fields, topics and concepts
📚 Shelves 7The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 3 worksComputer Science · 3 worksArtificial Intelligence · 3 worksLanguage and Linguistics · 3 worksSignal Processing · 3 worksPsychology · 1 workExperimental and Cognitive Psychology · 1 work
🧭 Topics 3Research subjects and languages the work is about.Sentiment & emotion · 1 workVision & language · 1 workSpeech & spoken language · 1 work
💡 Concepts 1Key ideas and methods explained on our concept pages.Child-directed speech · 1 work
Works by year
2020s
Papers
- EmotionTalk: An Interactive Chinese Multimodal Emotion Dataset With Rich Annotations (2026 · 6 citations)
Chinese multimodal emotion recognition (MER) has far fewer resources than English. Existing Chinese corpora are mostly clipped from films and TV, so their quality is often low. They also tend to lack conversational structure or rich labels. Emotion captioning additionally relies on unreleased data, which makes… - SpeechLLM-as-Judges: Towards General and Interpretable Speech Quality Evaluation (2026 · 3 citations)
Judging how good synthetic speech sounds is still difficult. Common tools such as MOS ratings, A/B tests, or MCD produce a single number or a binary choice, which explains nothing about the judgment. Learned predictors such as UTMOS are usually limited to one task and one language. The authors propose… - ChildTalk: A Multi-Dialect Chinese Child Speech Corpus with Full-Length Child–Caregiver Conversations for Speech Recognition (2026)
Recognizing children's speech is hard for ASR systems. Child voices differ acoustically from the adult data most models are trained on, and Mandarin child corpora are scarce. Existing ones are often closed, built from read speech, cut into isolated utterances, or limited to standard Mandarin. The authors address this…
All works
- EmotionTalk: An Interactive Chinese Multimodal Emotion Dataset With Rich AnnotationsFindings of the Association for Computational LinguisticsHaoqin Sun, Jinghua Zhao, Xuechen Wang, et al.2026 · 6 citations
- SpeechLLM-as-Judges: Towards General and Interpretable Speech Quality EvaluationAnnual Meeting of the Association for Computational Linguistics (ACL)Hui Wang, Jinghua Zhao, Yifan Yang, et al.2026 · 3 citations
- ChildTalk: A Multi-Dialect Chinese Child Speech Corpus with Full-Length Child–Caregiver Conversations for Speech RecognitionFindings of the Association for Computational LinguisticsJiaming Zhou, Yujie Guo, Shiwan Zhao, et al.2026
- DIFFA-2: A Practical Diffusion Large Language Model for General Audio Understanding ↗Findings of the Association for Computational Linguistics: ACL 2026 · no summary yetJiaming Zhou et al.2026
Co-authors here
- Haoqin Sun ×3
- Hui Wang ×3
- Jiaming Zhou ×3
- Jinghua Zhao ×2
- Yong Qin ×2
- Jinyu Li
- Shujie Liu
- Xi Yang
- Yan Lu
- Yanzhe Zhang
- Yao Lu
- Yequan Wang
Venues
- Findings of the Association for Computational Linguistics ×2: Findings of the Association for Computational Linguistics 2026 ×2
- Annual Meeting of the Association for Computational Linguistics (ACL): ACL 2026
- Findings of the Association for Computational Linguistics: ACL 2026
Cited by
Updated
This page in Markdown → https://md.research.elamur.ai/free/en/authors/shiwan-zhao/