VideoDubber: Machine Translation with Speech-Aware Length Control for Video Dubbing
Video dubbing aims to translate the original speech in a film or television program into the speech in a target language, which can be achieved with a cascaded system consisting of speech recognition, machine translation and speech synthesis. To ensure the translated speech to be well aligned with the corresponding video, the length/duration of the translated speech should be as close as possible to that of the original speech, which requires strict length control. Previous works usually control the number of words or characters generated by the machine translation model to be similar to the source sentence, without considering the isochronicity of speech as the speech duration of words/characters in different languages varies. In this paper, we propose a machine translation system tailored for the task of video dubbing, which directly considers the speech duration of each token in translation, to match the length of source and target speech. Specifically, we control the speech length of generated sentence by guiding the prediction of each word with the duration information, including the speech duration of itself as well as how much duration is left for the remaining words. We design experiments on four language directions (German -> English, Spanish -> English, Chinese <-> English), and the results show that the proposed method achieves better length control ability on the generated speech than baseline methods. To make up the lack of real-world datasets, we also construct a real-world test set collected from films to provide comprehensive evaluations on the video dubbing task.
Code (1)
Tasks
Machine TranslationSentencespeech-recognitionSpeech RecognitionSpeech SynthesisTranslationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Length Aware Speech Translation for Video Dubbing
In video dubbing, aligning translated audio with the source audio is a significant challenge. Our focus is on achieving this efficiently, tailored for real-time, on-device video dubbing scenarios. We developed a phoneme-…
TranslationIsochrony-Controlled Speech-to-Text Translation: A study on translating from Sino-Tibetan to Indo-European Languages
End-to-end speech translation (ST), which translates source language speech directly into target language text, has garnered significant attention in recent years. Many ST applications require strict length control to en…
DecoderMachine TranslationSpeech-to-TextSpeech-to-Text Translation+1Hierarchical Multi-task learning framework for Isometric-Speech Language Translation
This paper presents our submission for the shared task on isometric neural machine translation in International Conference on Spoken Language Translation (IWSLT). There are numerous state-of-art models for translation pr…
Machine TranslationMulti-Task LearningTranslationFrom Speech-to-Speech Translation to Automatic Dubbing
We present enhancements to a speech-to-speech translation pipeline in order to perform automatic dubbing. Our architecture features neural machine translation generating output of preferred length, prosodic alignment of …
Machine TranslationSpeech-to-Speech Translationtext-to-speechText to Speech+1Incorporating Noisy Length Constraints into Transformer with Length-aware Positional Encodings
Neural Machine Translation often suffers from an under-translation problem due to its limited modeling of output sequence lengths. In this work, we propose a novel approach to training a Transformer model using length co…
Machine TranslationPredictionSentenceTranslation