Automatic speech recognition for the Nepali language using CNN, bidirectional LSTM and ResNet
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910501992136704 |
|---|---|
| author | Dhakal, Manish Chhetri, Arman Gupta, Aman Kumar Lamichhane, Prabin Pandey, Suraj Shakya, Subarna |
| author_facet | Dhakal, Manish Chhetri, Arman Gupta, Aman Kumar Lamichhane, Prabin Pandey, Suraj Shakya, Subarna |
| contents | This paper presents an end-to-end deep learning model for Automatic Speech Recognition (ASR) that transcribes Nepali speech to text. The model was trained and tested on the OpenSLR (audio, text) dataset. The majority of the audio dataset have silent gaps at both ends which are clipped during dataset preprocessing for a more uniform mapping of audio frames and their corresponding texts. Mel Frequency Cepstral Coefficients (MFCCs) are used as audio features to feed into the model. The model having Bidirectional LSTM paired with ResNet and one-dimensional CNN produces the best results for this dataset out of all the models (neural networks with variations of LSTM, GRU, CNN, and ResNet) that have been trained so far. This novel model uses Connectionist Temporal Classification (CTC) function for loss calculation during training and CTC beam search decoding for predicting characters as the most likely sequence of Nepali text. On the test dataset, the character error rate (CER) of 17.06 percent has been achieved. The source code is available at: https://github.com/manishdhakal/ASR-Nepali-using-CNN-BiLSTM-ResNet. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_17825 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Automatic speech recognition for the Nepali language using CNN, bidirectional LSTM and ResNet Dhakal, Manish Chhetri, Arman Gupta, Aman Kumar Lamichhane, Prabin Pandey, Suraj Shakya, Subarna Computation and Language Sound Audio and Speech Processing This paper presents an end-to-end deep learning model for Automatic Speech Recognition (ASR) that transcribes Nepali speech to text. The model was trained and tested on the OpenSLR (audio, text) dataset. The majority of the audio dataset have silent gaps at both ends which are clipped during dataset preprocessing for a more uniform mapping of audio frames and their corresponding texts. Mel Frequency Cepstral Coefficients (MFCCs) are used as audio features to feed into the model. The model having Bidirectional LSTM paired with ResNet and one-dimensional CNN produces the best results for this dataset out of all the models (neural networks with variations of LSTM, GRU, CNN, and ResNet) that have been trained so far. This novel model uses Connectionist Temporal Classification (CTC) function for loss calculation during training and CTC beam search decoding for predicting characters as the most likely sequence of Nepali text. On the test dataset, the character error rate (CER) of 17.06 percent has been achieved. The source code is available at: https://github.com/manishdhakal/ASR-Nepali-using-CNN-BiLSTM-ResNet. |
| title | Automatic speech recognition for the Nepali language using CNN, bidirectional LSTM and ResNet |
| topic | Computation and Language Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2406.17825 |