End-to-end Rich Transcription-style Automatic Speech Recognition With Semi-supervised Learning
2021 · Tomohiro Tanaka, Ryo Masumura, Mana Ihori, et al.
Abstract
We propose a semi-supervised learning method for building end-to-end rich transcription-style automatic speech recognition (RT-ASR) systems from small-scale rich transcription-style and large-scale common transcription-style datasets. In spontaneous speech tasks, various speech phenomena such as fillers, word fragments, laughter and coughs, etc. are often included. While common transcriptions do not give special awareness to these phenomena, rich transcriptions explicitly convert them into special phenomenon tokens as well as textual tokens. In previous studies, the textual and phenomenon tokens were simultaneously estimated in an end-to-end manner. However, it is difficult to build accurate RT-ASR systems because large-scale rich transcription-style datasets are often unavailable. To solve this problem, our training method uses a limited rich transcription-style dataset and common transcription-style dataset simultaneously. The Key process in our semi-supervised learning is to convert
Authors
(none)
Tags
Stats
Related papers
- End-to-end ASR: From Supervised To Semi-supervised Learning With Modern Architectures (2019)0.00
- Semi-supervised Sequence-to-sequence ASR Using Unpaired Speech And Text (2019)0.00
- Exploiting Semi-supervised Training Through A Dropout Regularization In End-to-end Speech Recognition (2019)6.34
- Semi-supervised Learning For Multi-speaker Text-to-speech Synthesis Using Discrete Speech Representation (2020)5.24
- Fast Offline Transformer-based End-to-end Automatic Speech Recognition For Real-world Applications (2021)7.16
- Deep Contextualized Acoustic Representations For Semi-supervised Speech Recognition (2019)14.62
- From Weak Labels To Strong Results: Utilizing 5,000 Hours Of Noisy Classroom Transcripts With Minimal Accurate Data (2025)0.00
- End To End ASR System With Automatic Punctuation Insertion (2020)0.00