Representation transfer learning from deep end-to-end speech recognition networks for the classification of health states from speech

2021 ◽  
Vol 68 ◽  
pp. 101204
Author(s):  
Benjamin Sertolli ◽  
Zhao Ren ◽  
Björn W. Schuller ◽  
Nicholas Cummins
Keyword(s):  
Speech Recognition ◽  
Transfer Learning ◽  
Health States ◽  
End To End

scholarly journals Cross-Language End-to-End Speech Recognition Research Based on Transfer Learning for the Low-Resource Tujia Language

Symmetry ◽  
2019 ◽  
Vol 11 (2) ◽  
pp. 179 ◽  
Author(s):  
Chongchong Yu ◽  
Yunbing Chen ◽  
Yueqiao Li ◽  
Meng Kang ◽  
Shixuan Xu ◽  
...  
Keyword(s):  
Speech Recognition ◽  
Transfer Learning ◽  
Short Term Memory ◽  
Recognition System ◽  
Language Recognition ◽  
Low Resource ◽  
End To End ◽  
The Cross ◽  
Hidden Layer ◽  
Cross Language

To rescue and preserve an endangered language, this paper studied an end-to-end speech recognition model based on sample transfer learning for the low-resource Tujia language. From the perspective of the Tujia language international phonetic alphabet (IPA) label layer, using Chinese corpus as an extension of the Tujia language can effectively solve the problem of an insufficient corpus in the Tujia language, constructing a cross-language corpus and an IPA dictionary that is unified between the Chinese and Tujia languages. The convolutional neural network (CNN) and bi-directional long short-term memory (BiLSTM) network were used to extract the cross-language acoustic features and train shared hidden layer weights for the Tujia language and Chinese phonetic corpus. In addition, the automatic speech recognition function of the Tujia language was realized using the end-to-end method that consists of symmetric encoding and decoding. Furthermore, transfer learning was used to establish the model of the cross-language end-to-end Tujia language recognition system. The experimental results showed that the recognition error rate of the proposed model is 46.19%, which is 2.11% lower than the that of the model that only used the Tujia language data for training. Therefore, this approach is feasible and effective.

scholarly journals End-to-End Multiclass Dog Breed Classification

2020 ◽  
Vol 6 (12) ◽  
pp. 87-92
Author(s):  
Vipul Jain andDr. Bhoomi Gupta
Keyword(s):  
Transfer Learning ◽  
Batch Size ◽  
Test Image ◽  
Test Dataset ◽  
Interesting Topic ◽  
Dog Breed ◽  
End To End ◽  
Model Training

Dog breed classification and identification is one of the fine and interesting topic that makes to look upon and find fascinating. This project is based on the classification of the different class of breed in which the evaluation of each test image takes place and the probabilities of each test image finds the accurate breed of the dog. The use of transfer learning that is what you know in one domain and apply into another domain. Training of the model on the train dataset and then find the outcome and accuracy of the model on test dataset images. There are 120 breeds of dog on which the model made the prediction and 10000+ images for the test, train and validate .The model used in this is MOBILENET –V2 to obtain the accuracy of breed of dog with 94+ % accuracy .Tenserflow and Tenserflow hub is used to implement the model training and 100 epochs and batch size of 32 is used to achieve the accuracy.

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.

Sign in / Sign up

Export Citation Format

Share Document