2023-02-08 更新
Unleashing the True Potential of Sequence-to-Sequence Models for Sequence Tagging and Structure Parsing
Authors:Han He, Jinho D. Choi
Sequence-to-Sequence (S2S) models have achieved remarkable success on various text generation tasks. However, learning complex structures with S2S models remains challenging as external neural modules and additional lexicons are often supplemented to predict non-textual outputs. We present a systematic study of S2S modeling using contained decoding on four core tasks: part-of-speech tagging, named entity recognition, constituency and dependency parsing, to develop efficient exploitation methods costing zero extra parameters. In particular, 3 lexically diverse linearization schemas and corresponding constrained decoding methods are designed and evaluated. Experiments show that although more lexicalized schemas yield longer output sequences that require heavier training, their sequences being closer to natural language makes them easier to learn. Moreover, S2S models using our constrained decoding outperform other S2S approaches using external resources. Our best models perform better than or comparably to the state-of-the-art for all 4 tasks, lighting a promise for S2S models to generate non-sequential structures.
PDF Accepted to TACL 2023: Transactions of the Association for Computational Linguistics, post-acceptance final version
点此查看论文截图
PAMP: A unified framework boosting low resource automatic speech recognition
Authors:Zeping Min, Qian Ge, Zhong Li, Weinan E
We propose a novel text-to-speech (TTS) data augmentation framework for low resource automatic speech recognition (ASR) tasks, named phoneme audio mix up (PAMP). The PAMP method is highly interpretable and can incorporate prior knowledge of pronunciation rules. Furthermore, PAMP can be easily deployed in almost any language, extremely for low resource ASR tasks. Extensive experiments have demonstrated the great effectiveness of PAMP on low resource ASR tasks: we achieve a \textbf{10.84\%} character error rate (CER) on the common voice Cantonese ASR task, bringing a great relative improvement of about \textbf{30\%} compared to the previous state-of-the-art which was achieved by fine-tuning the wav2vec2 pretrained model.
PDF
点此查看论文截图
LipFormer: Learning to Lipread Unseen Speakers based on Visual-Landmark Transformers
Authors:Feng Xue, Yu Li, Deyin Liu, Yincen Xie, Lin Wu, Richang Hong
Lipreading refers to understanding and further translating the speech of a speaker in the video into natural language. State-of-the-art lipreading methods excel in interpreting overlap speakers, i.e., speakers appear in both training and inference sets. However, generalizing these methods to unseen speakers incurs catastrophic performance degradation due to the limited number of speakers in training bank and the evident visual variations caused by the shape/color of lips for different speakers. Therefore, merely depending on the visible changes of lips tends to cause model overfitting. To address this problem, we propose to use multi-modal features across visual and landmarks, which can describe the lip motion irrespective to the speaker identities. Then, we develop a sentence-level lipreading framework based on visual-landmark transformers, namely LipFormer. Specifically, LipFormer consists of a lip motion stream, a facial landmark stream, and a cross-modal fusion. The embeddings from the two streams are produced by self-attention, which are fed to the cross-attention module to achieve the alignment between visuals and landmarks. Finally, the resulting fused features can be decoded to output texts by a cascade seq2seq model. Experiments demonstrate that our method can effectively enhance the model generalization to unseen speakers.
PDF Under review
点此查看论文截图