5 accepted papers
We present an audio-visual speech separation learning method that considers the correspondence between the separated signals and the visual signals to reflect the speech characteristics during training. Audio-visual speech separation is a technique to estimate the individual speech signals from a mi…
We present a novel large-context end-to-end automatic speech recognition (E2E-ASR) model and its effective training method based on knowledge distillation. Common E2E-ASR models have mainly focused on utterance-level processing in which each utterance is independently transcribed. On the other hand,…
This paper presents a self-supervised learning method for pointer-generator networks to improve spoken-text normalization. Spoken-text normalization that converts spoken-style text into style normalized text is becoming an important technology for improving subsequent processing such as machine tran…
This paper introduces a spoken-to-written style conversion method that is suitable for handling a series of text such as discourses and conversations. Spoken-to-written style conversion can increase the readability of automatic speech recognition (ASR) outputs because ASR systems transcribe input sp…
This paper presents a novel semi-supervised end-to-end automatic speech recognition (ASR) method that employs consistency training with the use of unlabeled data. In consistency training, unlabeled data can be utilized for constraining a model such that it becomes invariant to small deformation. In…