图 书 馆
用于端到端语音识别的连接主义时间分类Connectionist Temporal Classification for End-to-End Speech Recognition |
|
| 课程网址: | http://videolectures.net/interACT2016_metze_temporal_classificati... |
| 主讲教师: | Florian Metze |
| 开课单位: | 卡内基梅隆大学 |
| 开课时间: | 2016-07-31 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | The performance of automatic speech recognition (ASR) has improved tremendously due to the application of deep neural networks (DNNs). Despite this progress, building a new ASR system remains a challenging task, requiring various resources, multiple training stages and significant expertise. In this talk, I will present an approach that drastically simplifies building acoustic models for the existing weighted finite state transducer (WFST) based decoding approach, and lends itself to end-to-end speech recognition, allowing optimization for arbitrary criteria. Acoustic modeling now involves learning a single recurrent neural network (RNN), which predicts context-independent targets (e.g., syllables, phonemes or characters). The connectionist temporal classification (CTC) objective function marginalizes over all possible alignments between speech frames and label sequences, removing the need for a separate alignment of the training data. We present a generalized decoding approach based on weighted finite-state transducers (WFSTs), which enables the efficient incorporation of lexicons and language models into CTC decoding. Experiments show that this approach achieves state-of-the-art word error rates, while drastically reducing complexity and speeding up decoding when compared to standard hybrid DNN systems. |
| 关 键 词: | 自动语音识别; 端到端语音识别; 声学建模 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2021-11-26：zkj |
| 最后编审: | 2021-11-26：zkj |
| 阅读次数: | 100 |