Related papers: Phoneme-aware Encoding for Prefix-tree-based Conte…

Tokenization and sub-tokenization based models like word2vec, BERT and the GPTs are the state-of-the-art in natural language processing. Typically, these approaches have limitations with respect to their input representation. They fail to…

Automatic speech recognition (ASR) systems often encounter difficulties in accurately recognizing rare words, leading to errors that can have a negative impact on downstream tasks such as keyword spotting, intent detection, and text…

Attention mechanism is one of the most successful techniques in deep learning based Natural Language Processing (NLP). The transformer network architecture is completely based on attention mechanisms, and it outperforms sequence-to-sequence…

Machine learning on trees has been mostly focused on trees as input to algorithms. Much less research has investigated trees as output, which has many applications, such as molecule optimization for drug discovery, or hint generation for…

Graph encoders in AMR-to-text generation models often rely on neighborhood convolutions or global vertex attention. While these approaches apply to general graphs, AMRs may be amenable to encoders that target their tree-like structure. By…

While large multilingual automatic speech recognition (ASR) models achieve remarkable performance, the internal mechanisms of the end-to-end pipeline, particularly concerning fairness and efficacy across languages, remain underexplored.…

Typically, unsupervised segmentation of speech into the phone and word-like units are treated as separate tasks and are often done via different methods which do not fully leverage the inter-dependence of the two tasks. Here, we unify them…

Despite the recent advancements in Automatic Speech Recognition (ASR), the recognition of accented speech still remains a dominant problem. In order to create more inclusive ASR systems, research has shown that the integration of accent…

Code-switching (CS) automatic speech recognition (ASR) faces challenges due to the language confusion resulting from accents, auditory similarity, and seamless language switches. Adaptation on the pre-trained multi-lingual model has shown…

Handwritten Mathematical Expression Recognition (HMER) has extensive applications in automated grading and office automation. However, existing sequence-based decoding methods, which directly predict $\LaTeX$ sequences, struggle to…

Given an input sequence (or prefix), modern language models often assign high probabilities to output sequences that are repetitive, incoherent, or irrelevant to the prefix; as such, model-generated text also contains such artifacts. To…

Contextual ASR or hotword customization holds substantial practical value. Despite the impressive performance of current end-to-end (E2E) automatic speech recognition (ASR) systems, they often face challenges in accurately recognizing rare…

By incorporating additional contextual information, deep biasing methods have emerged as a promising solution for speech recognition of personalized words. However, for real-world voice assistants, always biasing on such personalized words…

Employing pre-trained language models (LM) to extract contextualized word representations has achieved state-of-the-art performance on various NLP tasks. However, applying this technique to noisy transcripts generated by automatic speech…

Cross-lingual speech emotion recognition (SER) remains a challenging task due to differences in phonetic variability and speaker-specific expressive styles across languages. Effectively capturing emotion under such diverse conditions…

Neural networks with tree-based sentence encoders have shown better results on many downstream tasks. Most of existing tree-based encoders adopt syntactic parsing trees as the explicit structure prior. To study the effectiveness of…

Targeted sentiment classification aims at determining the sentimental tendency towards specific targets. Most of the previous approaches model context and target words with RNN and attention. However, RNNs are difficult to parallelize and…

Generative Adversarial Networks (GANs) have shown great capacity on image generation, in which a discriminative model guides the training of a generative model to construct images that resemble real images. Recently, GANs have been extended…

This paper proposes a model for automatic prosodic label annotation, where the predicted labels can be used for training a prosody-controllable text-to-speech model. The proposed model utilizes not only rich acoustic features extracted by a…

The recent emergence of joint CTC-Attention model shows significant improvement in automatic speech recognition (ASR). The improvement largely lies in the modeling of linguistic information by decoder. The decoder joint-optimized with an…