scholarly journals End-to-end recognition of streaming Japanese speech using CTC and local attention

2020 ◽  
Vol 9 ◽  
Author(s):  
Jiahao Chen ◽  
Ryota Nishimura ◽  
Norihide Kitaoka
Keyword(s):  
Speech Recognition ◽  
Recognition Performance ◽  
Time Lag ◽  
Recognition Algorithm ◽  
Streaming Data ◽  
Continuous Speech Recognition ◽  
Voice Input ◽  
Sequence Modeling ◽  
End To End ◽  
Bidirectional Networks

Many end-to-end, large vocabulary, continuous speech recognition systems are now able to achieve better speech recognition performance than conventional systems. Most of these approaches are based on bidirectional networks and sequence-to-sequence modeling however, so automatic speech recognition (ASR) systems using such techniques need to wait for an entire segment of voice input to be entered before they can begin processing the data, resulting in a lengthy time-lag, which can be a serious drawback in some applications. An obvious solution to this problem is to develop a speech recognition algorithm capable of processing streaming data. Therefore, in this paper we explore the possibility of a streaming, online, ASR system for Japanese using a model based on unidirectional LSTMs trained using connectionist temporal classification (CTC) criteria, with local attention. Such an approach has not been well investigated for use with Japanese, as most Japanese-language ASR systems employ bidirectional networks. The best result for our proposed system during experimental evaluation was a character error rate of 9.87%.

Demonstrated real‐time continuous speech recognition performance

1980 ◽  
Vol 67 (S1) ◽  
pp. S15-S15
Author(s):  
Larry Bahler ◽  
Steve Moshier ◽  
Peter Brown ◽  
James Baker
Keyword(s):  
Speech Recognition ◽  
Real Time ◽  
Recognition Performance ◽  
Continuous Speech ◽  
Continuous Speech Recognition

scholarly journals An Overview of End-to-End Automatic Speech Recognition

Symmetry ◽  
2019 ◽  
Vol 11 (8) ◽  
pp. 1018 ◽  
Author(s):  
Dong Wang ◽  
Xiaodong Wang ◽  
Shaohe Lv
Keyword(s):  
Deep Learning ◽  
Speech Recognition ◽  
Automatic Speech Recognition ◽  
Deep Neural Network ◽  
Mixed Model ◽  
Hidden Markov ◽  
Continuous Speech Recognition ◽  
Learning Techniques ◽  
Long Time ◽  
End To End

Automatic speech recognition, especially large vocabulary continuous speech recognition, is an important issue in the field of machine learning. For a long time, the hidden Markov model (HMM)-Gaussian mixed model (GMM) has been the mainstream speech recognition framework. But recently, HMM-deep neural network (DNN) model and the end-to-end model using deep learning has achieved performance beyond HMM-GMM. Both using deep learning techniques,

Large-vocabulary continuous speech recognition algorithm applied to a multi-modal telephone directory assistance system

1994 ◽  
Vol 15 (3-4) ◽  
pp. 301-310 ◽  
Author(s):  
Yasuhiro Minami ◽  
Kiyohiro Shikano ◽  
Satoshi Takahashi ◽  
Tomokazu Yamada ◽  
Osamu Yoshioka ◽  
...  
Keyword(s):  
Speech Recognition ◽  
Recognition Algorithm ◽  
Assistance System ◽  
Continuous Speech ◽  
Continuous Speech Recognition ◽  
Large Vocabulary ◽  
Telephone Directory ◽  
Directory Assistance

scholarly journals Improving low-resource Tibetan end-to-end ASR by multilingual and multilevel unit modeling

2022 ◽  
Vol 2022 (1) ◽  
Author(s):  
Siqing Qin ◽  
Longbiao Wang ◽  
Sheng Li ◽  
Jianwu Dang ◽  
Lixin Pan
Keyword(s):  
Speech Recognition ◽  
Transfer Learning ◽  
Recognition Performance ◽  
Low Resource ◽  
Learning Framework ◽  
Positive Effects ◽  
End To End ◽  
Historical Heritage ◽  
First Time ◽  
Asr System

AbstractConventional automatic speech recognition (ASR) and emerging end-to-end (E2E) speech recognition have achieved promising results after being provided with sufficient resources. However, for low-resource language, the current ASR is still challenging. The Lhasa dialect is the most widespread Tibetan dialect and has a wealth of speakers and transcriptions. Hence, it is meaningful to apply the ASR technique to the Lhasa dialect for historical heritage protection and cultural exchange. Previous work on Tibetan speech recognition focused on selecting phone-level acoustic modeling units and incorporating tonal information but underestimated the influence of limited data. The purpose of this paper is to improve the speech recognition performance of the low-resource Lhasa dialect by adopting multilingual speech recognition technology on the E2E structure based on the transfer learning framework. Using transfer learning, we first establish a monolingual E2E ASR system for the Lhasa dialect with different source languages to initialize the ASR model to compare the positive effects of source languages on the Tibetan ASR model. We further propose a multilingual E2E ASR system by utilizing initialization strategies with different source languages and multilevel units, which is proposed for the first time. Our experiments show that the performance of the proposed method-based ASR system exceeds that of the E2E baseline ASR system. Our proposed method effectively models the low-resource Lhasa dialect and achieves a relative 14.2% performance improvement in character error rate (CER) compared to DNN-HMM systems. Moreover, from the best monolingual E2E model to the best multilingual E2E model of the Lhasa dialect, the system’s performance increased by 8.4% in CER.

scholarly journals Development of Visual and Audio Speech Recognition Systems Using Deep Neural Networks

2021 ◽  
Author(s):  
Denis Ivanko ◽  
Dmitry Ryumin
Keyword(s):  
Speech Recognition ◽  
State Of The Art ◽  
Recognition Performance ◽  
Recognition Task ◽  
Reading Task ◽  
Lip Reading ◽  
Recognition Systems ◽  
End To End ◽  
Future Work ◽  
Single Modality

In this paper we design end-to-end neural network for the low-resource lip-reading task and audio speech recognition task using 3D CNNs, pre-trained CNN weights of several state-of- the-art models (e.g. VGG19, InceptionV3, MobileNetV2, etc.) and LSTMs. We present two phrase-level speech recognition pipelines: for lip-reading and acoustic speech recognition. We evaluate different combinations of front-end and back-end modules on the RUSAVIC dataset. We compare our results with traditional 2D CNN approach and demonstrate the increase in recognition accuracy up to 14%. Moreover, we carefully studied existing state-of-the-art models to be use for augmentation. Based on the conducted analysis we have chosen 5 most promising model’s architectures and evaluated them on own data. We have tested our systems on a real-word data of two different scenarios: recorded in idling vehicle and during actual driving. Our independently trained systems demonstrated acoustic speech accuracy up to 90% and lip-reading accuracy up to 61%. Future work will focus on the fusion of visual and audio speech modalities and on speaker adaptation. We expect that fused multi-modal information will help to further improve recognition performance compared to a single modality. Another possible direction could be the research of different NN-based architectures to better tackle end-to-end lip-reading task.

Sign in / Sign up

Export Citation Format

Share Document