Automatic transcription of spontaneous lecture speech
Automatic transcription of spontaneous lecture speech
复制标题
自动转录自发演讲稿
DOI：
10.1109/asru.2001.1034618
复制
发表时间：
2001
期刊：
影响因子：
--
通讯作者：
S. Furui
中科院分区：
文献类型：
--
作者：
Tatsuya Kawahara;H. Nanjo;S. Furui
我们介绍了我们广泛的自发语音处理和当前的试验演讲语音识别项目。该项目正在收集大量的演讲和谈话资料。我们已经训练了初始基线模型，并证实了真实的讲座和书面笔记的显著差异。在自发演讲语音中，说话速率通常更快并且变化很大，这使得更难应用固定的分割和解码设置。因此，我们提出了顺序解码和说话速率相关的解码策略。顺序解码器同时执行输入话语的自动分割和解码。然后，根据当前说话速率应用最充分的声学分析、音素模型和解码参数。这些策略实现了对真实的演讲语音自动转写的改进。
We introduce our extensive projects on spontaneous speech processing and current trials of lecture speech recognition. A large corpus of lecture presentations and talks is being collected in the project. We have trained initial baseline models and confirmed significant difference of real lectures and written notes. In spontaneous lecture speech, the speaking rate is generally faster and changes a lot, which makes it harder to apply fixed segmentation and decoding settings. Therefore, we propose sequential decoding and speaking-rate dependent decoding strategies. The sequential decoder simultaneously performs automatic segmentation and decoding of input utterances. Then, the most adequate acoustic analysis, phone models and decoding parameters are applied according to the current speaking rate. These strategies achieve improvement on automatic transcription of real lecture speech.
DOI：
10.21437/eurospeech.2001-396
发表时间：
2001-09
期刊：
--
影响因子：
--
作者：
Akinobu Lee;Tatsuya Kawahara;K. Shikano
通讯作者：
Akinobu Lee;Tatsuya Kawahara;K. Shikano