Transformer: A general framework from machine translation to others
Abstract Machine translation is an important and challenging task that aims at automatically
translating natural language sentences from one language into another. Recently …
translating natural language sentences from one language into another. Recently …
The multilingual tedx corpus for speech recognition and translation
We present the Multilingual TEDx corpus, built to support speech recognition (ASR) and
speech translation (ST) research across many non-English source languages. The corpus is …
speech translation (ST) research across many non-English source languages. The corpus is …
Improving speech translation by understanding and learning from the auxiliary text translation task
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 model …
performance. In this study, we are interested in training a speech to text translation model …
A general multi-task learning framework to leverage text data for speech to text tasks
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 …
for applications that need to map one sequence to a different sequence. Its success heavily …
Listen, understand and translate: Triple supervision decouples end-to-end speech-to-text translation
An end-to-end speech-to-text translation (ST) takes audio in a source language and outputs
the text in a target language. Existing methods are limited by the amount of parallel corpus …
the text in a target language. Existing methods are limited by the amount of parallel corpus …
CTC-based compression for direct speech translation
Previous studies demonstrated that a dynamic phone-informed compression of the input
audio is beneficial for speech translation (ST). However, they required a dedicated model for …
audio is beneficial for speech translation (ST). However, they required a dedicated model for …
Consecutive decoding for speech-to-text translation
Speech-to-text translation (ST), which directly translates the source language speech to the
target language text, has attracted intensive attention recently. However, the combination of …
target language text, has attracted intensive attention recently. However, the combination of …
RealTranS: End-to-end simultaneous speech translation with convolutional weighted-shrinking transformer
End-to-end simultaneous speech translation (SST), which directly translates speech in one
language into text in another language in real-time, is useful in many scenarios but has not …
language into text in another language in real-time, is useful in many scenarios but has not …
M-adapter: Modality adaptation for end-to-end speech-to-text translation
End-to-end speech-to-text translation models are often initialized with pre-trained speech
encoder and pre-trained text decoder. This leads to a significant training gap between pre …
encoder and pre-trained text decoder. This leads to a significant training gap between pre …
Orthros: Non-autoregressive end-to-end speech translation with dual-decoder
Fast inference speed is an important goal towards real-world deployment of speech
translation (ST) systems. End-to-end (E2E) models based on the encoder-decoder …
translation (ST) systems. End-to-end (E2E) models based on the encoder-decoder …