ELEC-E5500 - Speech Processing, Lecture, 8.9.2022-17.10.2022
Kurssiasetusten perusteella kurssi on päättynyt 17.10.2022 Etsi kursseja: ELEC-E5500
Osion kuvaus
-
The course starts on Thursday 8.9.2022 at 14:15-16:00 in Health Technology House, Auditorio - F239a. Onsite sessions are organized every week on Thursday at the same time in the same place.
Onsite face-to-face
- Weekly lectures are interactive discussions.
- Objective: Learn to appreciate the role and challenges of speech technology in the big picture.
- We alternate between small groups and joint discussions.
- Every session ends with a 15-minute period for writing a learning diary.
- Each submitted learning diary awards one point for the overall score.
- Deadline for submission is Sunday evening
- Reflect on what you have learned this week. Extent is 15 minutes of writing, which is likely something like half a page (2-3 paragraphs).
- One question in the exam will be based on these discussions.
- Participation in onsite sessions is strongly recommended but not mandatory.
- By reflecting on the topic of the week, learning diaries can be written without attending the sessions, but will take more time and effort.
- Exam questions can be answered without attending the sessions, but preparation for the exam will then take more time and effort.
- By reflecting on the topic of the week, learning diaries can be written without attending the sessions, but will take more time and effort.
Online videos and reading material
- Objective: This is the learning material for the download mode. Read texts and watch videos when it best fits your schedule. Skip content which you are already familiar with. Pause when you need time to digest.
- A selection of chapters from https://speechprocessingbook.aalto.fi/
- See section "Learning material"
- See section "Learning material"
- Videos presenting those chapters.
- Weekly collections of material are provided to
- prepare for interactive sessions and
- support the completion of exercises.
- The exam covers all this material.
Exercises
- Objective: Learn the practical tasks in implementing and evaluating speech processing methods.
- A new exercise is released every Tuesday and its submission deadline is on the following Monday.
- Exercise sessions every Friday 14:15-16:00 at Maari E - 229. TAs are there to help and answer questions about exercises. The plan is to have these sessions in hybrid mode (online & onsite).
- Each of the 4 exercises awards up to 6 points to the overall score.
- Exercises are solved using sounds of your own voice or other sound samples of your own. This has multiple benefits:
- You learn to handle real-world sounds and effects. Each voice is unique and will have its own difficulties and properties.
- Describing the effects visible and audible in your voice gives a deeper meaning to the exercises. It is not some obscure anonymous sound sample but it is you.
- Individualized exercises make cheating very difficult. You have to analyze your results and results vary across sound samples and across individual persons.
- You learn to handle real-world sounds and effects. Each voice is unique and will have its own difficulties and properties.
- Detailed instructions and weekly topics released in section "Exercises".
Communication
- The main communication channel is Zulip (an open source alternative to Slack, hosted by Aalto) at https://elec-e5500-2022.zulip.aalto.fi/
- All participants will be invited at the start of the course.
- Access by invitation only. If you have problems with access, email mailto:tom.backstrom@aalto.fi
- Suitable for all non-sensitive questions
- Discuss here and ask questions about exercises & exam etc.
- All participants will be invited at the start of the course.
- "Visiting" hour on Monday's at 10:00-11:00 on zoom with responsible teacher Tom Bäckström
- Link at the bottom of this page
- Ask anything, drink coffee with me or hang out.
- I'll keep the session open for an hour, but work on other things if nobody is there. Shout if I don't notice you :)
Exam
- Objective: Verify that students have participated in activities and solved the exercises themselves, as well as evaluate the level of their knowledge.
- A more-or-less complete list of exam questions will be provided, such that you know the style and extent of questions.
- The exam has 4 questions worth up to 6 points each.
- Depending on the public-health situation, the exam will be either
- a classic pen-and-paper exam with handwritten notes as supporting material (primary alternative)
an online, open-book exam (alternate, if forced to remote teaching).
Grading
Exercises give 4x6 = 24 points, exam gives 4x6 = 24 points and learning diary 6x1 = 6 points, for a total maximum of 54 points. The final grade is calculated with the formula grade = min(5, floor( (total-24)/5 )), or, specifically- for 29 <= total < 34
- for 34 <= total < 39
- for 39 <= total < 44
- for 44 <= total < 49
- for 49 <= total <= 54.
Overall, grading is thus meant to encourage completing exercises and learning diaries. Conversely, the idea is that the exam is easy if you have done your homework.Teaching team
- Responsible teacher (lectures): Tom Bäckström, visiting hour on Mondays at 10:00-11:00 from 5.9.2022 to 31.10.2022, primarily on zoom (see link at bottom of page), but also at Otakaari 3, entry from the Rakentajanaukio side, stairs up to 4th (highest) floor, room F414f. Use the doorbell in the staircase if necessary.
- Teaching assistant (exercises): Sudarsana Kadiri (sudarsana.kadiri@aalto.fi)
Rules
- Copying of material is not allowed.
- We will use both automated tools and manual checking to verify that nothing is copied.
- Single mistakes will be graded to zero.
- Repeated offences and cases with malicious intent will be reported to the administration.
- Looking up things on the internet is allowed and actively encouraged.
- In actual R&D work, we look up stuff on the internet all the time. That is how work is today. We embrace this approach.
- In particular, solutions from previous years can be found online or through friends. Looking at such material is allowed, but discouraged. It is in your best interest to try to learn and understand. Exercises change from year to year and experience has shown that it is easy to spot copy-cats.
- All provided exercise material is copyrighted by Aalto University and redistribution is explicitly not permitted.
Learning goals
- Understanding the basic phenomena of speech; speech production, phonetics.
- Understanding
operating principles and evaluation of benefits and constraints of
speech technologies in the different sub-fields;
- speech modelling,
- speech coding,
- voice activity detection,
- medical analysis of speech and
- speech enhancement (noise reduction, echo cancellation etc.).
- Usage and evaluation of basic tools in speech processing.
- Societal role of speech technology especially with respect to privacy.
- Related topics which are not included:
- Basics of (speech) perception are covered in the course Communication acoustics.
- Language and language modelling is covered by courses on Speech recognition and Statistical natural language processing.
-
Presemo feedback Verkko-osoite
Anonymous feedback channel used primarily during lectures.
- Weekly lectures are interactive discussions.