bibliography.bib

 @article{ajibola_alim_khair_alang_rashid_2018, title={Some Commonly Used Speech Feature Extraction Algorithms}, DOI={10.5772/intechopen.80419}, journal={From Natural to Artificial Intelligence - Algorithms and Applications}, author={Ajibola Alim, Sabur and Khair Alang Rashid, Nahrul}, year={2018}, month={Dec}} 
 @article{ali_ahmad_zhou_iqbal_ali_2014, title={DWT features performance analysis for automatic speech recognition of Urdu}, volume={3}, DOI={10.1186/2193-1801-3-204}, number={1}, journal={SpringerPlus}, author={Ali, Hazrat and Ahmad, Nasir and Zhou, Xianwei and Iqbal, Khalid and Ali, Sahibzada Muhammad}, year={2014}, month={Apr}} 
 @article{daqrouq_al-qawasmi_al_azzawi_abu_hilal_2011, title={Discrete Wavelet Transform & Linear Prediction Coding Based Method for Speech Recognition via Neural Network}, DOI={10.5772/20978}, journal={Discrete Wavelet Transforms - Biomedical Applications}, author={Daqrouq, Khaled and Al-Qawasmi, Abdel-Rahman and Al Azzawi, Khalooq Y and Abu Hilal, Turki}, year={2011}, month={Sep}} 
 @article{graves_fernández_gomez_schmidhuber_2006, title={Connectionist Temporal Classification: Labelling Unsegmented Sequence Data with Recurrent Neural Networks}, volume={2006}, DOI={10.1145/1143844.1143891}, journal={ICML 2006 - Proceedings of the 23rd International Conference on Machine Learning}, author={Graves, Alex and Fernández, Santiago and Gomez, Faustino and Schmidhuber, Jürgen}, year={2006}, month={Jan}, pages={369–376}} 
 @article{graves_mohamed_hinton_2013, title={Speech Recognition with Deep Recurrent Neural Networks}, volume={38}, DOI={10.1109/icassp.2013.6638947}, journal={ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings}, author={Graves, Alex and Mohamed, Abdel-rahman and Hinton, Geoffrey}, year={2013}, month={Mar}} 
 @article{hannun_2017, title={Sequence modeling with CTC}, volume={2}, DOI={10.23915/distill.00008}, number={11}, journal={Distill}, author={Hannun, Awni}, year={2017}, month={Nov}} 
 @article{hönig_stemmer_hacker_brugnara_2005, title={Revising Perceptual Linear Prediction (PLP)}, DOI={10.21437/interspeech.2005-138}, journal={Interspeech 2005}, author={Hönig, Florian and Stemmer, Georg and Hacker, Christian and Brugnara, Fabio}, year={2005}, month={Sep}} 
 @article{janse_magre_kurzekar_deshmukh_2014, title={A Comparative Study between MFCC and DWT Feature Extraction Technique}, volume={3}, DOI={10.17577/IJERTV3IS11110}, number={1}, journal={International Journal of Engineering Research & Technology}, author={Janse, Pooja V and Magre, Smita B and Kurzekar, Pratik K and Deshmukh, Rajendra R}, year={2014}, month={Jan}} 
 @article{lee_gommers_waselewski_wohlfahrt_oleary_2019, title={PyWavelets: A Python package for wavelet analysis}, volume={4}, DOI={10.21105/joss.01237}, number={36}, journal={Journal of Open Source Software}, author={Lee, Gregory and Gommers, Ralf and Waselewski, Filip and Wohlfahrt, Kai and OLeary, Aaron}, year={2019}, month={Apr}, pages={1237}} 
 @article{lindgren_lind_2019, title={Language Classification Using Neural Networks}, DOI={urn:nbn:se:uu:diva-385537}, journal={Dissertation}, author={Lindgren, Andreas and Lind, Gustav}, year={2019}} 
 @article{li_2015, title={Performance Analysis of Objective Speech Quality Measures in Mel Domain}, volume={9}, DOI={10.3923/jse.2015.350.361}, number={2}, journal={Journal of Software Engineering}, author={Li, Lu}, year={2015}, month={Jan}, pages={350–361}} 
 @article{nehe_holambe_2012, title={DWT and LPC based feature extraction methods for isolated word recognition}, volume={2012}, DOI={10.1186/1687-4722-2012-7}, number={1}, journal={EURASIP Journal on Audio, Speech, and Music Processing}, author={Nehe, Navnath S and Holambe, Raghunath S}, year={2012}, month={Jan}} 
 @article{rao_k._e._2017, title={Speech Recognition Using Articulatory and Excitation Source Features}, DOI={10.1007/978-3-319-49220-9}, journal={SpringerBriefs in Speech Technology}, author={Rao, K. Sreenivasa and K. E., Manjunath}, year={2017}} 
 @article{wang_acero_chelba_2003, title={Is word error rate a good indicator for spoken language understanding accuracy}, DOI={10.1109/asru.2003.1318504}, journal={2003 IEEE Workshop on Automatic Speech Recognition and Understanding (IEEE Cat. No.03EX721)}, author={Wang, Ye-Yi and Acero, A. and Chelba, C.}, year={2003}, month={Nov}, pages={577–582}} 
 @article{wang_deng_pu_huang_2017, title={Residual Convolutional CTC Networks for Automatic Speech Recognition}, volume={abs/1702.07793}, DOI={10.48550/arXiv.1702.07793}, journal={CoRR}, author={Wang, Yisen and Deng, Xuejiao and Pu, Songbai and Huang, Zhiheng}, year={2017}, month={Feb}} 
 @article{zhang_2022, title={English Speech Recognition System Model Based on Computer-Aided Function and Neural Network Algorithm}, volume={2022}, DOI={10.1155/2022/7846877}, journal={Computational Intelligence and Neuroscience}, author={Zhang, Jin}, year={2022}, month={Jan}, pages={1–11}} 
 @book{koehn_2020, place={New York, New York}, title={Neural Machine Translation}, publisher={Cambridge University Press}, author={Koehn, Philipp}, year={2020}} 
 @book{smith_2007, place={Stanford, California}, url={https://ccrma.stanford.edu/~jos/sasp/}, journal={Spectral Audio Signal Processing}, publisher={W3K Publishing}, author={Smith, Julius O}, year={2007}} 
 @misc{biswal_2022, title={Recurrent neural network (RNN) tutorial: Types and examples [updated]: Simplilearn}, url={https://www.simplilearn.com/tutorials/deep-learning-tutorial/rnn}, journal={Simplilearn.com}, publisher={Simplilearn}, author={Biswal, Avijeet}, year={2022}, month={Nov}} 
 @misc{brownlee_2021, title={A gentle introduction to long short-term memory networks by the experts}, url={https://machinelearningmastery.com/gentle-introduction-long-short-term-memory-networks-experts/}, journal={MachineLearningMastery.com}, author={Brownlee, Jason}, year={2021}, month={Jul}} 
 @misc{green_2018, title={Seeing sound: What is a spectrogram?}, url={https://blogs.bl.uk/sound-and-vision/2018/09/seeing-sound-what-is-a-spectrogram.html}, journal={Sound and vision blog}, publisher={British Library}, author={Green, Greg}, year={2018}, month={Sep}} 
 @misc{ibm_cloud_education_2020, title={What are recurrent neural networks?}, url={https://www.ibm.com/cloud/learn/recurrent-neural-networks}, journal={IBM}, author={IBM Cloud Education}, year={2020}, month={Sep}} 
 @misc{ito_johnson_2017, url={https://keithito.com/LJ-Speech-Dataset/}, journal={The LJ Speech Dataset}, author={Ito, Keith and Johnson, Linda}, year={2017}} 
 @misc{lendave_2021, title={LSTM Vs GRU in Recurrent Neural Network: A Comparative Study}, url={https://analyticsindiamag.com/lstm-vs-gru-in-recurrent-neural-network-a-comparative-study/}, journal={Developers Corner}, publisher={Analytics India Magazine}, author={Lendave, Vijaysinh}, year={2021}, month={Aug}} 
 @misc{mahanta_padmanabhan_2021, title={Audio Feature Extraction}, url={https://devopedia.org/audio-feature-extraction}, journal={Devopedia}, publisher={Devopedia Foundation}, author={Mahanta, Saranga K and Padmanabhan, Arvind}, year={2021}, month={May}} 
 @misc{mehrotra_2021, title={Let’s Understand The Problems with Recurrent Neural Networks}, url={https://www.analyticsvidhya.com/blog/2021/07/lets-understand-the-problems-with-recurrent-neural-networks/.}, journal={Analytics Vidhya}, author={Mehrotra, Siddharth}, year={2021}, month={Jul}} 
 @misc{mlearnere_2021, title={Learning from audio: The Mel Scale, Mel Spectrograms, and Mel Frequency Cepstral coefficients}, url={https://towardsdatascience.com/learning-from-audio-the-mel-scale-mel-spectrograms-and-mel-frequency-cepstral-coefficients-f5752b6324a8}, journal={Medium}, publisher={Towards Data Science}, author={Mlearnere}, year={2021}, month={Apr}} 
 @misc{nechyba_2004, title={Introduction to the Discrete Wavelet Transform (DWT)}, url={https://mil.ufl.edu/nechyba/www/eel6562/course_materials/t5.wavelets/intro_dwt.pdf}, journal={Machine Intelligence Lab}, publisher={University of Florida}, author={Nechyba, Michael C}, year={2004}, month={Feb}} 
 @misc{ramakrishnan_2021_16, title={Lecture 16: Connectionist Temporal Classification, sequence prediction}, url={https://www.youtube.com/watch?v=RowViowx1Bg}, journal={YouTube}, publisher={YouTube}, author={Ramakrishnan, Bhiksha}, year={2021}, month={May}} 
 @misc{ramakrishnan_2021_17, title={Lecture 17: Connectionist Temporal Classification (CTC), sequence to sequence prediction}, url={https://www.youtube.com/watch?v=5Rj0J9AuGw0}, journal={YouTube}, publisher={YouTube}, author={Ramakrishnan, Bhiksha}, year={2021}, month={Apr}} 
 @misc{scheidl_2018, title={An Intuitive Explanation of Connectionist Temporal Classification}, url={https://towardsdatascience.com/intuitively-understanding-connectionist-temporal-classification-3797e43a86c}, journal={Medium}, publisher={Towards Data Science}, author={Scheidl, Harald}, year={2018}, month={Jun}} 
 @misc{singh_2019, title={MFCC's made easy}, url={https://medium.com/@tanveer9812/mfccs-made-easy-7ef383006040}, journal={Medium}, publisher={Medium}, author={Singh, Tanveer}, year={2019}, month={Jun}} 
 @misc{sonix_authors_2022, title={A short history of speech recognition}, url={https://sonix.ai/history-of-speech-recognition}, journal={Sonix}, author={Sonix Authors}, year={2022}} 
 @misc{summa_linguae_authors_2021, title={Speech recognition software: History, present, and future}, url={https://summalinguae.com/language-technology/speech-recognition-software-history-future/}, journal={Summa Linguae}, author={Summa Linguae Authors}, year={2021}, month={Jun}} 
 @misc{talebi_2022, title={The Wavelet Transform}, url={https://towardsdatascience.com/the-wavelet-transform-e9cfa85d7b34}, journal={Medium}, publisher={Towards Data Science}, author={Talebi, Shawhin}, year={2022}, month={Dec}} 
 @misc{taspinar_2021, title={A guide for using the Wavelet Transform in Machine Learning}, url={https://ataspinar.com/2018/12/21/a-guide-for-using-the-wavelet-transform-in-machine-learning/}, journal={ML Fundamentals}, author={Taspinar, Ahmet}, year={2021}, month={Aug}} 
 @misc{thomala_2022, title={Baidu: R&D spending 2021}, url={https://www.statista.com/statistics/1079978/china-baidu-research-and-development-costs/}, journal={Statista}, author={Thomala, Lai Lin}, year={2022}, month={Apr}} 
 @misc{wang_2021, title={Automatic Speech Recognition 101: How ASR systems work}, url={https://www.dialpad.com/blog/automatic-speech-recognition/}, journal={Dialpad}, author={Wang, Riqiang}, year={2021}} 
 @misc{wasilewski_2019, title={Wavelet browser by pywavelets}, url={https://wavelets.pybytes.com/wavelet/bior6.8/}, journal={Biorthogonal 6.8 wavelet (bior6.8) properties, filters and functions - Wavelet Properties Browser}, author={Wasilewski, Filip}, year={2019}} 

 @book{ibm_cloud_education_2020, title={Types of recurrent neural networks}, url={https://www.ibm.com/content/dam/connectedassets-adobe-cms/worldwide-content/cdp/cf/ul/g/ba/82/types-of-recurrent-neural-networks-combined.component.simple-narrative-xl.ts=1671213187506.jpg/content/adobe-cms/us/en/topics/recurrent-neural-networks/jcr:content/root/table_of_contents/body/simple_narrative_1474352927/image}, journal={What is recurrent neural networks?}, publisher={IBM}, author={IBM Cloud Education}, year={2020}, month={Sep}} 
 @book{lopez_2019, title={RNN vs LSTM vs GRU}, url={http://dprogrammer.org/wp-content/uploads/2019/04/RNN-vs-LSTM-vs-GRU-1024x308.png}, journal={RNN, LSTM & GRU}, author={lopez, dProgrammer}, year={2019}, month={Apr}} 
 @book{rathi_2018, title={FeedForward Neural Networks}, url={https://mukulrathi.com/static/648e5207805f95bf09c330a43d89d295/04614/neural-net.webp}, journal={DEMYSTIFYING DEEP LEARNING}, author={Rathi, Mukul}, year={2018}, month={Aug}} 
 @misc{vedala_2022, title={Mel scale}, url={https://en.wikipedia.org/wiki/Mel_scale#/media/File:Mel-Hz_plot.svg}, journal={Wikipedia}, publisher={Wikimedia Foundation}, author={Vedala, Krishna}, year={2022}, month={Oct}} 
 @misc{wasilewski_2008, title={Biorthogonal 6.8 Wavelet (bior6.8)}, url={https://wavelets.pybytes.com/wavelet/bior6.8/}, journal={Wavelet Properties Browser}, author={Wasilewski, Filip}, year={2008}}