Title | ||
---|---|---|
HIERARCHICAL TRANSFORMER-BASED LARGE-CONTEXT END-TO-END ASR WITH LARGE-CONTEXT KNOWLEDGE DISTILLATION |
Abstract | ||
---|---|---|
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, large-context E2E-ASR models, which take into account long-range sequential contexts beyond utterance boundaries, well handle a sequence of utterances such as discourses and conversations. However, the transformer architecture, which has recently achieved state-of-the-art ASR performance among utterance-level ASR systems, has not yet been introduced into the large-context ASR systems. We can expect that the transformer architecture can be leveraged for effectively capturing not only input speech contexts but also long-range sequential contexts beyond utterance boundaries. Therefore, this paper proposes a hierarchical transformer-based large-context E2E-ASR model that combines the transformer architecture with hierarchical encoder-decoder based large-context modeling. In addition, in order to enable the proposed model to use long-range sequential contexts, we also propose a large-context knowledge distillation that distills the knowledge from a pre-trained large-context language model in the training phase. We evaluate the effectiveness of the proposed model and proposed training method on Japanese discourse ASR tasks. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/ICASSP39728.2021.9414928 | 2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021) |
Keywords | DocType | Citations |
large-context endo-to-end automatic speech recognition, transformer, hierarchical encoder-decoder, knowledge distillation | Conference | 0 |
PageRank | References | Authors |
0.34 | 0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ryo Masumura | 1 | 25 | 28.24 |
Naoki Makishima | 2 | 1 | 4.06 |
Mana Ihori | 3 | 1 | 5.41 |
Akihiko Takashima | 4 | 1 | 4.40 |
Tomohiro Tanaka | 5 | 17 | 8.61 |
Orihashi, S. | 6 | 3 | 5.50 |