Yu Wu

Large-Scale Self-Supervised Speech Representation Learning for Automatic Speaker Verification

2022 · ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

The speech representations learned from large-scale unlabeled data have shown better generalizability than those from supervised learning and thus attract a lot of interest to be applied for various downstream tasks. In this paper, we …

Detecting Speaker Personas from Conversational Texts

2021 · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Personas are useful for dialogue response prediction.

Text Morphing

2018 · arXiv (Cornell University)

In this paper, we introduce a novel natural language generation task, termed as text morphing, which targets at generating the intermediate sentences that are fluency and smooth with the two input sentences. We propose the …

Accelerating Transducers through Adjacent Token Merging

2023 · arXiv (Cornell University)

Recent end-to-end automatic speech recognition (ASR) systems often utilize a Transformer-based acoustic encoder that generates embedding at a high frame rate. However, this design is inefficient, particularly for long speech signals due to the quadratic …

SemGO: Goal-Oriented Semantic Policy Based on MHSA for Object Goal Navigation

2024

Object Goal Navigation is a task that seeks to allow intelligent agents to locate and navigate to a particular object goal in an unfamiliar environment. However, the current goal-oriented semantic policy, which is based on …

Hierarchical Recurrent Attention Network for Response Generation

2018 · Proceedings of the AAAI Conference on Artificial Intelligence

We study multi-turn response generation in chatbots where a response is generated according to a conversation context. Existing work has modeled the hierarchy of the context, but does not pay enough attention to the fact …

Neural Response Generation With Dynamic Vocabularies

2018 · Proceedings of the AAAI Conference on Artificial Intelligence

We study response generation for open domain conversation in chatbots. Existing methods assume that words in responses are generated from an identical vocabulary regardless of their inputs, which not only makes them vulnerable to generic …

Keyphrase Generation with Correlation Constraints

2018

In this paper, we study automatic keyphrase generation.

Sequential Matching Network: A New Architecture for Multi-turn Response Selection in Retrieval-Based Chatbots

2017

We study response selection for multiturn conversation in retrieval-based chatbots. Existing work either concatenates utterances in context or matches a response with a highly abstract context vector finally, which may lose relationships among utterances or …

Response Generation by Context-Aware Prototype Editing

2019 · Proceedings of the AAAI Conference on Artificial Intelligence

Open domain response generation has achieved remarkable progress in recent years, but sometimes yields short and uninformative responses. We propose a new paradigm, prototypethen-edit for response generation, that first retrieves a prototype response from a …

Template-Based Named Entity Recognition Using BART

2021

There is a recent interest in investigating fewshot NER, where the low-resource target domain has different label sets compared with a resource-rich source domain. Existing methods use a similarity-based metric. However, they cannot make full …