91 citations · 146 across the 14 of their papers we have counts for
14 papers
Hybrid Transducer and Attention based Encoder-Decoder Modeling for Speech-to-Text Tasks
Yun Tang, Anna Y. Sun, Hirofumi Inaguma +5
Transducer and Attention based Encoder-Decoder (AED) are two widely used frameworks for speech-to-text tasks. They are designed for different purposes and each has its own benefits…
Enhancing Speech-to-Speech Translation with Multiple TTS Targets
Jiatong Shi, Yun Tang, Ann Lee +4
It has been known that direct speech-to-speech translation (S2ST) models usually suffer from the data scarcity issue because of the limited existing parallel materials for both sou…
Named Entity Detection and Injection for Direct Speech Translation
Marco Gaido, Yun Tang, Ilia Kulikov +3
In a sentence, certain words are critical for its semantic. Among them, named entities (NEs) are notoriously challenging for neural models. Despite their importance, their accurate…
Unified Speech-Text Pre-training for Speech Translation and Recognition
Yun Tang, Hongyu Gong, Ning Dong +8
We describe a method to jointly pre-train speech and text in an encoder-decoder modeling framework for speech translation and recognition. The proposed method incorporates four sel…
FST: the FAIR Speech Translation System for the IWSLT21 Multilingual Shared Task
Yun Tang, Hongyu Gong, Xian Li +4
In this paper, we describe our end-to-end multilingual speech translation system submitted to the IWSLT 2021 evaluation campaign on the Multilingual Speech Translation shared task.…
Improving Speech Translation by Understanding and Learning from the Auxiliary Text Translation Task
Yun Tang, Juan Pino, Xian Li +2
Pretraining and multitask learning are widely used to improve the speech to text translation performance. In this study, we are interested in training a speech to text translation…
Pay Better Attention to Attention: Head Selection in Multilingual and Multi-Domain Sequence Modeling
Hongyu Gong, Yun Tang, Juan Pino +1
Multi-head attention has each of the attention heads collect salient information from different parts of an input sequence, making it a powerful mechanism for sequence modeling. Mu…
A General Multi-Task Learning Framework to Leverage Text Data for Speech to Text Tasks
Yun Tang, Juan Pino, Changhan Wang +2
Attention-based sequence-to-sequence modeling provides a powerful and elegant solution for applications that need to map one sequence to a different sequence. Its success heavily r…
fairseq S2T: Fast Speech-to-Text Modeling with fairseq
Changhan Wang, Yun Tang, Xutai Ma +4
We introduce fairseq S2T, a fairseq extension for speech-to-text (S2T) modeling tasks such as end-to-end speech recognition and speech-to-text translation. It follows fairseq's car…
Self-Training for End-to-End Speech Translation
Juan Pino, Qiantong Xu, Xutai Ma +2
One of the main challenges for end-to-end speech translation is data scarcity. We leverage pseudo-labels generated from unlabeled audio by a cascade and an end-to-end speech transl…
Orthogonal Relation Transforms with Graph Context Modeling for Knowledge Graph Embedding
Yun Tang, Jing Huang, Guangtao Wang +2
Translational distance-based knowledge graph embedding has shown progressive improvements on the link prediction task, from TransE to the latest state-of-the-art RotatE. However, N…
Relation Module for Non-answerable Prediction on Question Answering
Kevin Huang, Yun Tang, Jing Huang +2
Machine reading comprehension(MRC) has attracted significant amounts of research attention recently, due to an increase of challenging reading comprehension datasets. In this paper…
Multi-hop Reading Comprehension across Multiple Documents by Reasoning over Heterogeneous Graphs
Ming Tu, Guangtao Wang, Jing Huang +3
Multi-hop reading comprehension (RC) across documents poses new challenge over single-document RC because it requires reasoning over multiple documents to reach the final answer. I…
Deep Speaker Embedding Learning with Multi-Level Pooling for Text-Independent Speaker Verification
Yun Tang, Guohong Ding, Jing Huang +2
This paper aims to improve the widely used deep speaker embedding x-vector model. We propose the following improvements: (1) a hybrid neural network structure using both time delay…