Description and contextualization of the subject

The goal of the course is for students to become familiar with the fundamental applications of speech signal processing, such as spech synthesis and automatic speech recognition. With a practical approach, the main paradigms that have been applied in both technologies will be analyzed, the procedures for the development of these systems will be described and the necessary resources and voice databases will also be presented. Students will practice with real systems. Additionally, other applications related to voice processing such as speaker or emotion recognition, voice conversion or diarization, among others, will be briefly reviewed.



To take this subject, the student must master the basic models of speech production, the concepts of temporal and frequency analysis of signals and the fundamentals of signal digitization.

Learning outcomes of the subject

• RA1 Demonstrate understanding of the problems related to the acoustic modeling of the voice signal.

• RA2 Manage tools for the analysis and processing of the voice signal.

• RA3 Demonstrate understanding of automatic speech and speaker recognition systems and voice synthesis, as well as the techniques used to evaluate them.

• RA4 Develop a basic speech recognition system.

• RA5 Extract information from a scientific article and present it orally to an interdisciplinary and international audience.

Ordinary call: orientations and renunciation

For the evaluation of students in the ordinary call, different tools will be used:



- Written exam

At the end of the course there will be a written exam. In it, students must demonstrate their mastery of the concepts explained in the lectures and that are described in the notes provided. The exam may contain a multiple choice answer part and a development part.



- Lab practices

The practices will be carried out partially during the face-to-face classes. The student must compulsorily submit a report of the practices carried out, according to the indications provided. The compulsory practice reports must be delivered on the dates indicated during the course.



- Oral presentation

At the beginning of the course, topics will be proposed to be worked on by the students. At the end of the course there will be oral presentations of said works. Both the presentations made and the descriptive document of the work will be evaluated.



To waive the ordinary call, the student must notify the teaching staff of the subject two weeks before the end of the course.

Extraordinary call: orientations and renunciation

In the extraordinary call, the students will be evaluated for the same competences as in the ordinary call, for which the following assessment tools are established:



- Written exam that will cover the concepts taught in the lectures. The exam may have a multiple choice part and a development part.



- Laboratory practices: the reports of the practices proposed during the course must be submitted compulsorily.



- Oral presentation: An oral presentation will be made on a topic chosen by the student and a document will be delivered with the description of the work carried out.

Temary

1. Speech modelling

2. Speech synthesis

3. Speech recognition

4. Other speech technologies

Bibliography

Compulsory materials

Students will have the following materials necessary for the development of the subject available at eGela (http://egela.ehu.eus/):



- Slides with the theoretical content of the subject, topics T1-T4.



- Scripts for the lab practices, one file per practice with a theoretical introduction and the description of the work that must be done in the lab.



- Necessary signals, matlab programs, linux scripts and other necessary tools for the development of the practices.

Basic bibliography

- J. G. Proakis, D. G. Manolakis. Digital signal processing. Principles, algorithms and applications (4th edition). Pearson Prentice Hall, 2007. (ISBN: 978-0131873742)



- L. R. Rabiner, R. W. Schafer. Digital processing of speech signal. Prentice-Hall, 1978. (ISBN: 978-0132136037)



- X. Huang, A. Acero, H. Hon. Spoken Language Processing: A Guide to Theory, Algorithm and System Development. Prentice Hall, 2001. (ISBN: 978-0130226167)



- A. V. Oppenheim, R. W. Schafer. Discrete-Time signal processing (3rd edition). Pearson Prentice Hall, 2009. (ISBN: 978-0131988422)

In-depth bibliography

- P. Taylor. Text-to-Speech Synthesis. Cambridge University Press, 2009. (ISBN: 978-0521899277)







- L. Rabiner, B. H. Juang. Fundamentals of Speech Recognition. CRC Press, 1993. (ISBN: 78-0130151575)







- D. Yu, L. Deng. Automatic Speech Recognition: A Deep Learning Approach. Springer, 2015. (ISBN: 978-1447157786)







- W. C. Chu. Speech Coding Algorithms: Foundation and Evolution of Standardized Coders. Wiley-Interscience, 2003. (ISBN: 978-0471373124)

Journals

Computer Speech and Language







Speech Communication







IEEE Transactions on Audio, Speech & Language Processing







IEEE Transactions on Systems, Man and Cybernetics-Part B







IEEE Transactions on Multimedia







Journal of the Acoustical Society of America

Links

- Speech Technologies



http://www.speech.cs.cmu.edu/ news:comp.speech http://festvox.org/



- Review of Speech Synthesis Technology



http://www.acoustics.hut.fi/publications/files/theses/lemmetty_mst/contents.html



- Speech Technology Hyperlinks Page



http://www.speech.cs.cmu.edu/comp.speech/Section5/speechlinks.html



- Demos de sistemas TTS



http://www.acapela-group.com/text-to-speech-interactive-demo.html



http://www.loquendo.com/en/demo-center/tts-demo/



http://enterprisecontent.nuance.com/vocalizer5-network-demo/index.html



http://aholab.ehu.es/tts/tts_en.html