Related papers: Fine Grained Knowledge Transfer for Personalized T…

Deep learning-empowered semantic communication is regarded as a promising candidate for future 6G networks. Although existing semantic communication systems have achieved superior performance compared to traditional methods, the end-to-end…

Fact-based dialogue generation is a task of generating a human-like response based on both dialogue context and factual texts. Various methods were proposed to focus on generating informative words that contain facts effectively. However,…

The cornerstone of multilingual neural translation is shared representations across languages. Given the theoretically infinite representation power of neural networks, semantically identical sentences are likely represented differently.…

This work presents self-supervised learning methods for developing monaural speaker-specific (i.e., personalized) speech enhancement models. While generalist models must broadly address many speakers, specialist models can adapt their…

Generative seq2seq dialogue systems are trained to predict the next word in dialogues that have already occurred. They can learn from large unlabeled conversation datasets, build a deep understanding of conversational context, and generate…

Spoken Language Understanding (SLU) is a key component of goal oriented dialogue systems that would parse user utterances into semantic frame representations. Traditionally SLU does not utilize the dialogue history beyond the previous…

The past few years have seen remarkable progress in the decoding of speech from brain activity, primarily driven by large single-subject datasets. However, due to individual variation, such as anatomy, and differences in task design and…

Recent statistical approaches have improved the robustness and scalability of spoken dialogue systems. However, despite recent progress in domain adaptation, their reliance on in-domain data still limits their cross-domain scalability. In…

Nowadays, automatical personality inference is drawing extensive attention from both academia and industry. Conventional methods are mainly based on user generated contents, e.g., profiles, likes, and texts of an individual, on social…

This paper proposes a unified model to conduct emotion transfer, control and prediction for sequence-to-sequence based fine-grained emotional speech synthesis. Conventional emotional speech synthesis often needs manual labels or reference…

When building state-of-the-art speech translation models, the need for large computational resources is a significant obstacle due to the large training data size and complex models. The availability of pre-trained models is a promising…

Fine-tuning pre-trained generative language models to down-stream language generation tasks has shown promising results. However, this comes with the cost of having a single, large model for each task, which is not ideal in low-memory/power…

Natural language generators for task-oriented dialogue must effectively realize system dialogue actions and their associated semantics. In many applications, it is also desirable for generators to control the style of an utterance. To date,…

This paper addresses the privacy and security concerns associated with deep neural language models, which serve as crucial components in various modern AI-based applications. These models are often used after being pre-trained and…

Conversational Text-to-Speech (TTS) aims to synthesis an utterance with the right linguistic and affective prosody in a conversational context. The correlation between the current utterance and the dialogue history at the utterance level…

In domain adaptation for neural machine translation, translation performance can benefit from separating features into domain-specific features and common features. In this paper, we propose a method to explicitly model the two kinds of…

Recent research in the design of end to end communication system using deep learning has produced models which can outperform traditional communication schemes. Most of these architectures leveraged autoencoders to design the encoder at the…

A good neural sequence-to-sequence summarization model should have a strong encoder that can distill and memorize the important information from long input texts so that the decoder can generate salient summaries based on the encoder's…

End-to-end deep learning for communication systems, i.e., systems whose encoder and decoder are learned, has attracted significant interest recently, due to its performance which comes close to well-developed classical encoder-decoder…

We propose a selective encoding model to extend the sequence-to-sequence framework for abstractive sentence summarization. It consists of a sentence encoder, a selective gate network, and an attention equipped decoder. The sentence encoder…