Unified Multimodal Punctuation Restoration Framework for Mixed-Modality Corpus
It addresses a practical problem in real-world speech recognition systems where transcripts are a mix of audio and non-audio data, offering a pervasive solution for mixed-modality punctuation.
The paper tackles punctuation restoration for mixed-modality transcripts (with and without audio) by proposing UniPunc, a unified multimodal framework that outperforms strong baselines by at least 0.8 overall F1 scores, achieving new state-of-the-art results.
The punctuation restoration task aims to correctly punctuate the output transcriptions of automatic speech recognition systems. Previous punctuation models, either using text only or demanding the corresponding audio, tend to be constrained by real scenes, where unpunctuated sentences are a mixture of those with and without audio. This paper proposes a unified multimodal punctuation restoration framework, named UniPunc, to punctuate the mixed sentences with a single model. UniPunc jointly represents audio and non-audio samples in a shared latent space, based on which the model learns a hybrid representation and punctuates both kinds of samples. We validate the effectiveness of the UniPunc on real-world datasets, which outperforms various strong baselines (e.g. BERT, MuSe) by at least 0.8 overall F1 scores, making a new state-of-the-art. Extensive experiments show that UniPunc's design is a pervasive solution: by grafting onto previous models, UniPunc enables them to punctuate on the mixed corpus. Our code is available at github.com/Yaoming95/UniPunc