Syllabus
Unit 1
Introduction and Acoustic Phonetics, Overview of dialog: Human conversation. Task-oriented dialog. Dialog systems, Machine Learning in Dialog- Recurrent NNs, Attention, Transformers
Unit 2
Automatic Speech Recognition, Foundation models for spoken language-Using the Speech Brain ASR toolkit, Advanced ASR
Unit 3
Text to Speech (TTS): Overview. Text normalization, Spectrogram prediction, Vocoding, TTS, Evaluation.
Objectives and Outcomes
Course Objectives
- The course aims to introduce spoken language technology with an emphasis on dialog and conversational systems
- The course helps in establishing the understanding of Deep learning and other methods for automatic speech recognition, speech synthesis systems for robotics
Course Outcomes
After completing this course, students will be able to
|
CO1
|
Demonstrate understanding of acoustic phonetics in the context of spoken language.
|
|
CO2
|
Analyze different types of dialog systems and their applications.
|
|
CO3
|
Apply AI techniques used in dialog systems.
|
|
CO4
|
Implement automatic speech recognition, text-to-speech synthesis, and evaluation.
|
CO-PO Mapping
|
PO/PSO
|
PO1
|
PO2
|
PO3
|
PO4
|
PO5
|
PO6
|
PO7
|
PO8
|
PO9
|
PO10
|
PO11
|
PO12
|
PSO1
|
PSO2
|
PSO3
|
|
CO
|
|
CO1
|
3
|
3
|
2
|
3
|
2
|
2
|
1
|
1
|
2
|
2
|
1
|
3
|
2
|
0
|
2
|
|
CO2
|
3
|
3
|
3
|
3
|
2
|
2
|
1
|
2
|
2
|
3
|
2
|
3
|
0
|
0
|
0
|
|
CO3
|
3
|
3
|
3
|
3
|
3
|
2
|
1
|
2
|
3
|
2
|
2
|
3
|
2
|
2
|
0
|
|
CO4
|
3
|
3
|
3
|
3
|
3
|
2
|
1
|
2
|
3
|
3
|
2
|
3
|
2
|
2
|
1
|
Text Books / References
“
Text Books / References
Dan Jurafsky and James H. Martin. Speech and Language Processing, (3rd ed. draft), available at https://web.stanford.edu/~jurafsky/slp3/
Yoav Goldberg. A Primer on Neural Network Models for Natural Language Processing. Available at https://u.cs.biu.ac.il/~yogo/nnlp.pdf
Ian Goodfellow, Yoshua Bengio, and Aaron Courville. Deep Learning. MIT Press. Available at https://www.deeplearningbook.org/
“
