End-to-End Speech Recognition Sequence Training With Reinforcement Learning
نویسندگان
چکیده
منابع مشابه
Improving End-to-End Speech Recognition with Policy Learning
Connectionist temporal classification (CTC) is widely used for maximum likelihood learning in end-to-end speech recognition models. However, there is usually a disparity between the negative maximum likelihood and the performance metric used in speech recognition, e.g., word error rate (WER). This results in a mismatch between the objective function and metric during training. We show that the ...
متن کاملImproved training for online end-to-end speech recognition systems
Achieving high accuracy with end-to-end speech recognizers requires careful parameter initialization prior to training. Otherwise, the networks may fail to find a good local optimum. This is particularly true for low-latency online networks, such as unidirectional LSTMs. Currently, the best strategy to train such systems is to bootstrap the training from a tied-triphone system. However, this is...
متن کاملEnd-to-end Audiovisual Speech Recognition
Several end-to-end deep learning approaches have been recently presented which extract either audio or visual features from the input images or audio signals and perform speech recognition. However, research on end-to-end audiovisual models is very limited. In this work, we present an end-toend audiovisual model based on residual networks and Bidirectional Gated Recurrent Units (BGRUs). To the ...
متن کاملEnd-to-End Speech Recognition Models
For the past few decades, the bane of Automatic Speech Recognition (ASR) systems have been phonemes and Hidden Markov Models (HMMs). HMMs assume conditional independence between observations, and the reliance on explicit phonetic representations requires expensive handcrafted pronunciation dictionaries. Learning is often via detached proxy problems, and there especially exists a disconnect betw...
متن کاملMultichannel End-to-end Speech Recognition
The field of speech recognition is in the midst of a paradigm shift: end-to-end neural networks are challenging the dominance of hidden Markov models as a core technology. Using an attention mechanism in a recurrent encoder-decoder architecture solves the dynamic time alignment problem, allowing joint end-to-end training of the acoustic and language modeling components. In this paper we extend ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Access
سال: 2019
ISSN: 2169-3536
DOI: 10.1109/access.2019.2922617