Besacier Laurent, Barnard Etienne, Karpov Alexey, and Schultz Tanja.Speech analysis and synthesis by linear prediction of the speech wave.
Deep speech 2: End-to-end speech recognition in English and Mandarin.
Amodei Dario, Anubhai Rishita, Battenberg Eric, Case Carl, Casper Jared, Catanzaro Bryan, Chen Jingdong, Chrzanowski Mike, Coates Adam, Diamos Greg, Elsen Erich, Engel Jesse H., Fan Linxi, Fougner Christopher, Han Tony, Hannun Awni Y., Jun Billy, LeGresley Patrick, Lin Libby, Narang Sharan, Ng Andrew Y., Ozair Sherjil, Prenger Ryan, Raiman Jonathan, Satheesh Sanjeev, Seetapun David, Sengupta Shubho, Wang Yi, Wang Zhiqian, and Wang Chong. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP’12). Applying convolutional neural networks concepts to hybrid NN-HMM model for speech recognition. Abdel-Hamid O., Mohamed A., Jiang H., and Penn G. We have trained the model on the Microsoft Speech Corpus, and we observe a 5.87% decrease in Word Error Rate (WER) with respect to base-model WER. These insights help us in understanding and improving the ASR system as well as provide intuition into the language used for the ASR system. To gain key insights from our Automatic Speech Recognition (ASR) system, we used the inferences from the system and proposed different analysis methods. To improve the performance of the system with the limited size of the dataset, we present a combined language model (Word-level language Model and Character-level language model)-based prefix decoding technique and Bidirectional Encoder Representations from Transformers-based post-processing technique. 
We follow a deep learning-based approach that includes Convolutional Neural Network, Bi-directional Long Short Term Memory layers, Dense layers, and Connectionist Temporal Classification as a loss function. We present a novel approach for improving the performance of an End-to-End speech recognition system for the Gujarati language.
0 kommentar(er)
