Feature Transfer Learning for Wav2Text Sequence-to-Sequence ASR

• Item type: SIG Technical Reports(1)
• 公開日: 2018-12-03
• タイトル: Feature Transfer Learning for Wav2Text Sequence-to-Sequence ASR
• タイトル / 言語: en
• タイトル: Feature Transfer Learning for Wav2Text Sequence-to-Sequence ASR
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: セッション1 音声認識
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_18gh
• 資源タイプ: technical report
• 著者所属: Nara Institute of Science and Technology／RIKEN, Center for Advanced Intelligence Project AIP
• 著者所属: Nara Institute of Science and Technology／RIKEN, Center for Advanced Intelligence Project AIP
• 著者所属: Nara Institute of Science and Technology／RIKEN, Center for Advanced Intelligence Project AIP
• 著者所属(英): en
• 著者所属(英): Nara Institute of Science and Technology / RIKEN, Center for Advanced Intelligence Project AIP
• 著者所属(英): en
• 著者所属(英): Nara Institute of Science and Technology / RIKEN, Center for Advanced Intelligence Project AIP
• 著者所属(英): en
• 著者所属(英): Nara Institute of Science and Technology / RIKEN, Center for Advanced Intelligence Project AIP
• 著者名: Andros, Tjandra; Sakriani, Sakti; Satoshi, Nakamura
• 著者名(英): Andros, Tjandra; Sakriani, Sakti; Satoshi, Nakamura
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: In this paper, we construct the first end-to-end attention-based encoder-decoder model to process directly from raw speech waveform to the text transcription. We called the model as ”Attention-basedWav2Text”. To assist the training process of the end-to-end model, we propose to utilize a feature transfer learning. Experimental results also reveal that the proposed Attention-based Wav2Text model directly with raw waveform could achieve a better result in comparison with the attentional encoder-decoder model trained on standard front-end filterbank features.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: In this paper, we construct the first end-to-end attention-based encoder-decoder model to process directly from raw speech waveform to the text transcription. We called the model as ”Attention-basedWav2Text”. To assist the training process of the end-to-end model, we propose to utilize a feature transfer learning. Experimental results also reveal that the proposed Attention-based Wav2Text model directly with raw waveform could achieve a better result in comparison with the attentional encoder-decoder model trained on standard front-end filterbank features.
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AN10442647
• 書誌情報: 研究報告音声言語情報処理（SLP）; 巻 2018-SLP-125, 号 3, p. 1-2, 発行日 2018-12-03
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 2188-8663
• Notice: SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc.
• 出版者 / 言語: ja
• 出版者: 情報処理学会