Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd Logo
Upload

Welcome to Scribd!

  • 1 views

    SNLP_Syllabus

    Uploaded by

    Ahadit AB

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    SNLP_Syllabus

    Uploaded by

    Ahadit AB
    1 views3 pages

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    1 views3 pages

    SNLP_Syllabus

    Uploaded by

    Ahadit AB

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    You are on page 1of 3

    Item 66/29 - Annexure - 25

    Course code Course Title L T P C


    BCSE419L Speech and Language Processing 3 0 0 3
    Pre-requisite NIL Syllabus version
    1.0
    Course Objectives
    1. Be competent with fundamental concepts for natural language processing and
    automatic speech recognition
    2. To understand technologies involved in developing speech and language
    applications.
    3. To demonstrate the use of deep learning for building applications in speech and
    natural language processing

    Course Outcomes
    At the end of this course, student will be able to:
    1. Describe the importance of different NLP modules in Text processing and
    fundamentals of speech production
    2. Describe ways to represent speech and text
    3. Demonstrate the working of sequence models for text
    4. Use signal processing techniques to analyze/represent the speech signal
    5. Execute trials of speech/language systems

    Module:1 Introduction to Natural Language Processing 7 hours


    Overview of NLP - Introduction to Levels of NLP - Morhpology: Derivational &
    Inflectional Morphology - POS tagging - Parsing: Shallow and Dependency
    Parsing, Semantics:
    Word Level Semantics and Thematic roles.
    Module:2 Text Preprocessing & Feature Representation 8 hours
    Introduction to Corpora, Sentence Segmentation, Stemming: Porter Stemmer, Bag of words
    and Vector Space Model, Topic Modeling, N-gram Language Model, Smoothing, Word
    Embeddings: Word2Vec, Glove and Fasttext.
    Module:3 Applications of NLP-1 6 hours
    Sentiment Classification using ML & DL models, Named Entity Recognition - CRF and
    LSTMs, Text Summarization - Statistical and Deep Learning models.
    Module:4 Applications of NLP-2 4 hours
    Machine Translation - Encoder & Decoder Model, Attention Models, Question Answering -
    Knowledge based Q&A and Deep Learning models for Q&A.
    Module:5 Introduction to Speech Processing 6 hours
    Fundamentals of speech production – Perception of sound – Vocal tract model - Phonetics
    - Short-Time analysis of the signal – Energy – Zero crossing – Autocorrelation – Short
    time Fourier analysis.
    Module:6 Feature Representaion of Speech Signal 4 hours
    Mel Frequency Cepstral Coeffecients, Perceptual linear prediction (PLP), Linear prediction
    cepstral coefficients (LPCC), Gammatone Frequency Cepstral Coefficients (GFCC), i-vector.
    Module:7 Automatic Speech and Speaker Recognition 8 hours
    Automatic Speech recognition formulation: Isolated word recognition – Large vocabulary
    continuous speech recognition - HMM/GMM based speech recognition – DNN/HMM
    model
    -- CNN based speech recognition - RNN language Models – Evaluation metrics, Speaker

    Proceedings of the 66th Academic Council (16.06.2022) 663


    Item 66/29 - Annexure - 25

    recognition model – Alexa/Google assistant based application development.

    Module:8 Contemporary issues 2 hours

    Total Lecture hours: 45 Hours

    Text Book(s)
    1. Dan Jurafsky, James H. Martin “Speech and Language Processing”, Draft of 3rd
    Edition,Prentice Hall 2022.
    2. Jacob Benesty, M. M. Sondhi, Yiteng Huang "Springer Handbook of Speech
    Processing", Springer, 2008.
    Reference Books
    1. Uday Kamath, John Liu, James Whitaker "Deep Learning for NLP and Speech
    Recognition" Springer, ,2019.
    2. Steven Bird, Ewan Klein, Edward Loper "Natural Language Processing with Python",
    O'Reilly Media. 2009.
    3. Ben Gold, Nelson Morgan, Dan Ellis “Speech and Audio Signal Processing: Processing
    and Perception of Speech and Music”, John Wiley & Sons, 2011.
    Mode of Evaluation: CAT / Written Assignment / Quiz / FAT
    Recommended by Board of Studies 09-05-2022
    Approved by Academic Council No. 66 Date 16-06-2022

    Proceedings of the 66th Academic Council (16.06.2022) 664


    Item 66/29 - Annexure - 25

    Course code Course Title L T P C


    BCSE419P Speech and Language Processing Lab 0 0 2 1
    Pre-requisite NIL Syllabus version
    1.0
    Course Objectives
    1. Be competent with fundamental concepts for natural language processing and
    automatic speech recognition
    2. To understand technologies involved in developing speech and
    language applications.
    3. To demonstrate the use of deep learning for building applications in speech and
    natural language processing
    Course Outcome
    At the end of this course, student will be able to:
    1. Describe the importance of different NLP modules in text processioning and
    fundamentals of speech production
    2. Describe ways to represent speech and text
    3. Demonstrate the working of sequence models for text
    4. Use signal processing techniques to analyze/represent the speech signal
    5. Execute trials of speech/language systems
    Indicative Experiments
    1. Installing various packages for text and Speech Processing: NLTK, 3 Hours
    Spacy, Speech Recognition etc.
    2. POS Tagging and Parsing using various python packages 2 Hours
    3. Implementation of BOW, topic models for text representation and 2 Hours
    classification
    4. Implementing N-gram language models for next word prediction 2 Hours
    5. Implementing Word embedding based text classification 2 Hours
    6. Implementing CNN for sentiment analysis 2 Hours
    7. Implementing RNN for Named Entity recognition 2 Hours
    8. Implementing text summarization using deep learning 2 Hours
    9. Implementing chatbot using deep learning 2 Hours
    10. Implementing machine translation using encoder-decoder 2 Hours
    models
    11. Developing speech recognition system to recognize voice 3 Hours
    commands
    12. Developing speech recognition system to recognize 3 Hours
    continuous speech
    13. Implementing CNN based speech recognition using mel 3 Hours
    spectal images

    Total Laboratory Hours 30 hours


    Text Book(s)
    1. Delip Rao, Brian McMahan, “Natural Language Processing with PyTorch: Build
    Intelligent Language Applications Using Deep Learning”, 2019, 1st Edition, O'Reilly
    Media.
    Reference Books
    1. Mark Liu, “Make Python Talk: Build Apps with Voice Control and Speech
    Recognition ”, 2021, 1st Edition, No Starch Press.
    Mode of Evaluation: CAT / Mid-Term Lab/ FAT
    Recommended by Board of Studies 09-05-2022
    Approved by Academic Council No. 66 Date 16-06-2022

    Proceedings of the 66th Academic Council (16.06.2022) 106


    5

    You might also like