End-to-End Model Based on RNN-T for Kazakh Speech Recognition
Authors:
- 25 June 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 163-167
Abstract
Automatic speech recognition is a rapidly developing area in machine learning. The most popular speech recognition systems today are end-to-end systems, especially those models that directly output a sequence of words taking into account the input sound in real time, which are online end-to-end models. Stream speech recognition allows to transfer the audio stream to speech-to-text conversion and get the results of stream speech recognition in real time as the audio is processed. This article discusses and implements a popular RNN-T-based model for recognizing Kazakh speech. The analysis of works related to recognition of Kazakh speech based on the CTC model is also given. The findings demonstrated that an RNN-T-based model can work well without additional components, like a language model and showed the best outcome on our dataset. As a result of the research, the system reached 10.6% CER, which is the best indicator among other end-to-end systems for recognizing Kazakh speech.Keywords
This publication has 14 references indexed in Scilit:
- Improving RNN Transducer Modeling for End-to-End Speech Recognition2019
- An Overview of End-to-End Automatic Speech RecognitionSymmetry, 2019
- Streaming End-to-end Speech Recognition for Mobile Devices2019
- Exploring architectures, data and units for streaming end-to-end speech recognition with RNN-transducer2017
- A Comparison of Sequence-to-Sequence Models for Speech Recognition2017
- Recent progresses in deep learning based acoustic modelsIEEE/CAA Journal of Automatica Sinica, 2017
- Recurrent Neural Network based language modeling with controllable external Memory2017
- Conditional Random Fields in Speech, Audio, and Language ProcessingProceedings of the IEEE, 2013
- Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research GroupsIEEE Signal Processing Magazine, 2012
- Connectionist temporal classification2006