Papers by Xiaosong Qiao

4 papers
CB-Whisper: Contextual Biasing Whisper Using Open-Vocabulary Keyword-Spotting (2024.lrec-main)

Copied to clipboard

Challenge: End-to-end automatic speech recognition systems struggle to recognize rare name entities such as personal names, organizations and terminologies that are not frequently encountered in the training data.
Approach: They propose a convolutional neural network-based ASR system that performs open-vocabulary keyword-spotting before the decoder to match the features between the entities and the utterances.
Outcome: The proposed system significantly improves mixed-error-rate (MER) and entity recall compared to the original Whisper model on three internal datasets and two publicly available datasets.
SmartSpanNER: Making SpanNER Robust in Low Resource Scenarios (2023.findings-emnlp)

Copied to clipboard

Challenge: Named Entity Recognition (NER) is one of the most fundamental tasks in natural language processing.
Approach: They propose a method which introduces a Named Entity Head (NEH) prediction task to SpanNER and performs multi-task learning together with task of span classification.
Outcome: The proposed method improves the robustness of SpanNER in low resource scenarios on the CoNLL03, Few-NERD, GENIA and ACE05 benchmark datasets.
Cross-Domain Audio Deepfake Detection: Dataset and Analysis (2024.emnlp-main)

Copied to clipboard

Challenge: Existing audio deepfake detection datasets are outdated and lack generalization capabilities.
Approach: They construct a new cross-domain audio deepfake detection dataset comprising over 300 hours of speech data that is generated by five advanced zero-shot TTS models.
Outcome: The proposed models achieve 4.1% and 6.5% error rates in the cross-domain ADD dataset generated by five advanced zero-shot TTS models.
Multimodal Machine Translation with Text-Image In-depth Questioning (2025.findings-acl)

Copied to clipboard

Challenge: Multimodal machine translation (MMT) models focus on intermodal interactions, but focus on simple interactions between nouns and entities in image, overlooking global semantic alignment.
Approach: They propose a Text-Image In-depth Questioning method to deepen interactions and optimize translations by utilizing visual data to capture global semantic alignment.
Outcome: The proposed method achieves state-of-the-art results on five translation directions of Multi30K and AmbigCaps, with +2.35 BLEU on the challenging MSCOCO benchmark.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations