Tree-constrained Pointer Generator with Graph Neural Network Encodings
for Contextual Speech Recognition

Tree-constrained Pointer Generator with Graph Neural Network Encodings for Contextual Speech Recognition

Interspeech (Interspeech), 2022

2 July 2022

Guangzhi Sun

ArXiv (abs)PDF HTML

Papers citing "Tree-constrained Pointer Generator with Graph Neural Network Encodings for Contextual Speech Recognition"

9 / 9 papers shown

Title
PARCO: Phoneme-Augmented Robust Contextual ASR via Contrastive Entity Disambiguation Jiajun He Naoki Sawada Koichi Miyazaki Tomoki Toda 214 0 0 04 Sep 2025
Zero-shot Context Biasing with Trie-based Decoding using Synthetic Multi-Pronunciation Changsong Liu Yizhou Peng Eng Siong Chng 107 0 0 25 Aug 2025
PMF-CEC: Phoneme-augmented Multimodal Fusion for Context-aware ASR Error Correction with Error-specific Selective DecodingIEEE Transactions on Audio, Speech, and Language Processing (TASLP), 2025 Jiajun He Tomoki Toda 134 3 0 31 May 2025
MaLa-ASR: Multimedia-Assisted LLM-Based ASR Guanrou Yang Ziyang Ma Fan Yu Zhifu Gao Shiliang Zhang Xie Chen AuLLM 295 5 0 09 Jun 2024
SlideSpeech: A Large-Scale Slide-Enriched Audio-Visual CorpusIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2023 Haoxu Wang Fan Yu Xian Shi Yuezhang Wang Shiliang Zhang Ming Li 237 17 0 11 Sep 2023
Knowledge-Aware Audio-Grounded Generative Slot Filling for Limited Annotated DataComputer Speech and Language (CSL), 2023 Guangzhi Sun Chuxu Zhang Ivan Vulić Paweł Budzianowski P. Woodland 172 6 0 04 Jul 2023
Can Contextual Biasing Remain Effective with Whisper and GPT-2?Interspeech (Interspeech), 2023 Guangzhi Sun Xianrui Zheng Chuxu Zhang P. Woodland 177 28 0 02 Jun 2023
Graph Neural Networks for Contextual ASR with the Tree-Constrained Pointer GeneratorIEEE/ACM Transactions on Audio Speech and Language Processing (TASLP), 2023 Guangzhi Sun Chuxu Zhang P. Woodland 179 9 0 30 May 2023
End-to-end Spoken Language Understanding with Tree-constrained Pointer GeneratorIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2022 Guangzhi Sun Chuxu Zhang P. Woodland 181 8 0 29 Oct 2022