If you are working with me e.g. for your MSc project, here are some starting points for reading, and for tooling up:

Recommended reading:

1. Computational Analysis of Sound Scenes and Events - a good textbook from 2018. Chapter 2 is a very good intro to many of the fundamentals in audio processing for machine learning.
2. Computational bioacoustics with deep learning: a review and roadmap - a very up-to-date review paper by me, for animal sound in particular.
3. The Good Research Code Handbook - Read this!
4. Suggested reading: getting going with deep learning - a list of useful reading that our lab members rely on (from 2019).
5. Probabilistic Machine Learning: An introduction by Kevin Murphy - a very good comprehensive textbook (new edition 2022).

Useful software tools:

I'm assuming you will be using Python, as well as one of the standard deep learning frameworks and/or scikit-learn, and also git to keep track of your code. These are standard (and you'll see some of that in the "Good Research Code Handbook" above). Slightly more specialist:

• DVC - for keeping track of datasets, and/or machine learning experiments (ideally you know git already, for this)
• Weights and biases - for keeping track of the outputs from machine learning experiments, and visualising them nicely
• librosa - a Python library for working with sound files
• Sonic Visualiser - a great desktop app to explore/annotate sound files interactively

Please do let me know if there are other top tips you would add to this list...

Recently I've been learning more and more how to cook vegan. It seems hard at first to be totally plant-based, for sure. There are some super cheap ingredients which I had no idea were so useful! So here are my absolute top tips, things to put in your store cupboard and you can use every week, for all kinds of uses.

1. Peanut butter. It's surprising how useful this stuff is - not just for spreading on your toast! But also for providing a big nutritious boost as well as a thick sauce in various stews, or thickening up the dough in cakes and cookies. Try these:
   • West African peanut stew - this is a lovely dish, and easy enough for a midweek meal.
   • Pad thai
   • Indonesian peanut sauce. This is a popular sauce in the Netherlands, a bit like "satay sauce" - a dark, sweet and thick peanut/chilli/soy sauce. (NB needs tamarind, and also kecap manis, but the latter can be substituted with soy+sugar.) You can serve this is loads of ways - a big dollop of it on top of your fried rice; "gado gado" (an Indonesian platter of veg+egg to dip into your peanut sauce), or just dip your chips (fries) in it!
   • Kidney bean & peanut butter burgers - very cheap and cheerful
   • Vegan peanut butter and rasberry jam Blondies - a slightly posh recipe since it uses chia seeds and coconut oil, but tasty.
   • TBC: peanut butter cookies. Seems obvious, but I haven't tried making those.
2. Chickpeas. We don't have a lot of chickpea recipes in British cooking, so I didn't expect them to be that useful, and I certainly didn't think of putting them in the oven or in a frying pan...! The famous chickpea food is certainly hummus, and making your own hummus is very easy, quick and satisfying. Chickpea curry is also a go-to option when you want a big batch of curry!
   • Home-made hummus: chickpeas, garlic, tahini, olive oil, lemon juice, and a touch of salt, all in the blender. Easy! ... If you don't have a blender you can even make "rough hummus" by just mashing it all up with a fork or a masher, resulting in a kind of hummusy salad which is nice on toast.
   • Warm spiced cauliflower and chickpea salad with pomegranate seeds (a Nigella recipe)
   • Roasted / slow-fried chickpeas
   • Katte chhole (chickpea curry). I use a recipe from "Vegan Street Food" by Jackie Kearney, which infuses the chickpeas in tea (using a teabag) for some extra flavour depth. Other recipes online e.g. this one.
   • Chana chaat - this one takes a bit of work, but it's an awesome sort-of indian chickpea "nachos"-type salad dish, layers of amazing flavour.
3. Gram flour (chickpea flour). Chickpea flour is common in Indian cooking (it's used for pakora and onion bhaji), and it's quite different from wheat flour - it's very handy to know how to use it. The thing you need to get right is the ratio of water to flour: in some cases you need a very liquid batter, and in some recipes you need it to be thicker so it doesn't "fall off". You'll get the hang of it!
   • Cecina - an italian thing, a kind of oven-baked dish - you can include whatever flavours you like, but I totally recommend the rosemary.
   • Spanish tortilla
   • Sweetcorn fritters
   • Panisse - it's a bit like polenta, you can make up a batch of big panisse "chunky chips" with a smooth texture and a crispy outer crust.
   • Pakora and/or onion bhaji
   • Herby jackfruit fritters
4. Black beans. You can get all sorts of beans, but black beans are special because they have a good dark and ever-so-slightly meaty taste which helps add flavour to various veggie meals.
   • My black bean chorizo ... you can make nice things like carbonara with it.
   • Black bean & nectarine tacos
   • Black bean & pesto wrap
   • Black bean burgers - making the most of their "meaty"ness. For example these black bean and quinoa burgers.

So: pick an ingredient, put it in your store cupboard, and learn how to make MORE dishes with that one ingredient. It's good to get better, and the practice comes in handy when you're low on ideas mid-week some time.

Of course there are some much more well-known ingredients which everyone associates with vegetarians: lentils, tofu. I'm assuming that you don't need as many tips about those, you can find recipes everywhere.

This Indonesian-style peanut sauce is much loved by the Dutch in their "adopted" (!) Indonesian taste. It goes really well as a basis for gado gado, and also with many other indonesian dishes. Having never been to Indonesia, I can only claim this is a good match to the sauce we get in the Netherlands!

NOTE: If you have "kecap manis", then use it! -- you can replace half the soy sauce with kecap manis, and reduce the sugar (leaving out perhaps a third of it). That gives a more authentic full flavour. It's not very common in Britain.

Ingredients:

• 200g peanut butter
• ~5 tbsp (dark) soy sauce --- you may end up adding more later --- and you could replace half of this with kecap manis
• 50ml coconut milk
• ~7 heaped tsp (soft) brown sugar
• Juice of half a lime
• 1/2 tsp chilli sauce
• 1/2 tsp chilli flakes
• 1 tsp ground ginger
• 1/2 tsp ground cumin

• 100ml (approx!) tamarind juice --- OR 25 ml (approx) tamarind paste

• 1 clove garlic

• ~100ml water

If using tamarind "block", remember to prep it first (by soaking the right amount in warm water for a few minutes at least).

In a small blender whizz up everything except for the garlic and the water. You can add a bit of the water, to make it easier to get it out again.

Crush the garlic and fry it in a little veg oil, in a milk pan or similar, just until softened (don't let it burn), Then add the blended mixture and cook it for ten minutes or more, stirring. Add water as it cooks, enough to get the consistency right.

My mum's pear frangipane tart is a classic. Rich almondy frangipane, and soft pears, go together really well. Here, I've made a vegan version, partly by adapting Domestic Gothess's frangipane recipe. (Follow that link for lots of photos and tips on the process.)

The rich taste of frangipane is traditionally made with butter and egg. In this version, the egg is replaced by cornflour, flour and aquafaba. Aquafaba is the liquid from a tin of chickpeas (!) and can be whipped up in various ways. Here you do NOT need to whip the aquafaba, it (and the cornflour) simply help to bind the mixture around all that ground almond, plus a bit of baking powder for rise. Instead of butter, it's good to use a vegan "block" butter instead of margarine, to ensure this vegan version has a good rich impression. I used Violife, DG uses Naturli. Non-vegans can use old-fashioned butter.

You get great results using tinned pears in syrup for this tart. Apparently you can also use fresh pears, but that didn't work so well when I tried it (perhaps I should have poached them slightly first?). Anyway, a tin of pears in syrup is great for this.

Makes a single tart good for 8-10 portions.

FOR THE PASTRY:

• 150 g plain (all-purpose) flour
• 35 g ground almonds
• 35 g icing (powdered) sugar, or caster sugar
• a pinch of salt
• 100 g vegan block butter (NOT the spreadable kind), cold and diced
• 1/2 Tbsp cold vodka (or water)

FOR THE FILLING:

• 50 g melted vegan block butter
• 75 g caster sugar
• 30 g plain (all-purpose) flour
• 3 g cornflour (cornstarch)
• 55 ml aquafaba or non dairy milk
• 120 g ground almonds
• 1/3 tsp baking powder
• 1/2 tsp almond extract
• 1/2 tsp vanilla extract
• One tin of pears in syrup (230g pears from 410g net, 5 pear-halves)

To make the pastry: mix the flour, almonds, sugar and salt together. Add the butter, cold and diced, and rub it into the dry ingredients with your fingertips until it resembles fine breadcrumbs. Then add the vodka/water, bit by bit, mixing with your fingers or a utensil until the pastry comes together in a ball. (You can also do all this in a food processor.)

Shape the pastry into a disc, wrap in clingfilm, and place in the fridge for at least half an hour.

Preheat the oven to 180 degrees C. Grease a springform tart tin, about 9 inches / 20 cm diameter.

Take the pastry from the fridge and roll it out to a disc large enough to fill the tin and go up the sides. (If you have to roll it back into a ball and roll it out again, that's fine.) Carefully lift it into the tin. Trim off excess pastry from the top. We probably only need it to be about 1cm deep, but deeper is fine.

Prick the pastry all over the base with a fork, then blind bake it, as follows. Place a sheet of baking paper or tinfoil in that will cover the whole base. Put baking beans (or rice, lentils...) in to fill the floor of the pastry, making sure they go right to the edge. Bake this in the oven for 25 minutes, then take out the baking beans and the baking paper/foil, and return to the oven for another 5 minutes of cooking.

During that last bit of cooking, make the frangipane. Whisk together the melted vegan butter and the sugar, then the flour and cornflour, followed by the aquafaba. Finally, mix in the ground almonds, baking powder, and vanilla/almond extract. I also added some of the juice (30ml?) from the pear tin, to make the frangipane liquid enough to pour a bit more easily, and of course for a bit of flavour.

Now assemble the tart. Take the pastry base out of the oven, and arrange the pear-halves nicely in it, cut side down. I used all five pear-halves in my tin. Pour the frangipane into the gaps where the pears are not, making a nice even layer in the pastry case. Spread it out evenly.

Return to the oven and cook for 30 minutes

Leave to cool in the tins for 20 minutes before turning out. Serve with cream, plain yogurt, or something like that; the tart is delicious warm or cold. Store any leftovers in an airtight container for up to 3 days.

We've discovered some lovely vegetarian recipes this year! The lockdown last year was actually a pretty good opportunity to get better at cooking, especially when we had to dig into our stockpile - yes, it really got to that point, strange to think now. This year was a bit less extreme in that sense, but we've come across lots of new recipes, and in particular getting better at being vegan-compatible. Here is a selection of the absolute best recipes we've been eating this year.

First, main courses - all vegan, all lovely!

• Meera Sodha's hasselback celeriac with pomegranate, miso, red onion --- a gorgeous combination of flavours, great. We've made this multiple times because the flavour combination is so ace.
• Chana chaat - Delicious! Layers of complex, fruity & sour flavours, in this Indian chickpea salad/streetfood snack
• Sweet potato and kimchi cakes --- a great trick with kimchi!
• Jackfruit & bean rendang, topped with lime zest, toasted coconut, and fried onions - served with rice, spicy sambal and a pineapple ring :)
• Turkish spiral flatbread ("BÖYLE BİR LEZZET YOK") - I don't know what this is, but watch the video, it's fun to make, quite easy, and a lovely lunch!
• Red lentil and squash soup with za’atar croutons -- easy, nice, filling
• Winter mushroom stew: many types of mushroom (200g per person), with dark beer (herfstbock), winter spices (star anise, bay, clove), stock, onion rings, and brown sugar. Served with celeriac chips (which were tossed in cornflour and oven-baked for 40mins).

These two main courses are not vegan but lovely anyway:

• Pasta met kruidenpangrattato -- a nice variant: crunchy pasta! This recipe is in Dutch
• Lancashire cheese & onion pie

Desserts (all vegan):

• Figs poached in orange, cardamom and honey (from the book "Fruit" by HFW)
• Rhubarb, cardamom and pistachio tart
• Vegan sticky toffee pudding

Treats (all vegan):

• Vegan banana chocolate chip muffins
• Chocolate courgette cake (I replaced the soft icing with a crunchy choc shell, yum.)

See also my list from five years ago (FIVE??), The best vegetarian recipes of 2016. If you want to follow along with more foody explorations, I have a dedicated Twitter feed at @nomnomdan.

Shout outs to some awesome convenience foods we found in the Netherlands:

• Lidl Vegetarische Bradworst -- very good indeed. Yv said it was exactly like those other dutch sausages, I said it was quite british-sausage-y.
• Kips Vega Pate (the classic version) -- great pate taste. We had it on sarnies on holiday, and it's fabulous.
• Future Sausage -- very nice! One of the nicest veggie sausages we've had - https://futurefarm.io/
• Mr & Mrs Watson "Aged Camemberti" -- phenomenal texture, and very good nuanced flavour. Glad we bought it!

As I write this, I am flying through the night on a Nightjet night-train from the Netherlands to southern Germany. It's a delightful train ride with lots of nice little touches. Before bedtime, I sit here with a drink in my hand, watching the views go by outside. The view alternates between peaceful countryside and urban/industrial busyness. It really feels like you can see a lot from here.

I'm angry. I'm angry on behalf of my friends, family, and everyone else back home. The UK government has just upended plans for the HS2 and "Northern Powerhouse" railways. I left the UK partly because it has a stupid political setup that frustrates all attempts at (simultaneously) two important things: sensible evolution of policy, and sensible planning and provision for our future. One of the scraps of hope I held on to had been this: The HS2 rail project, imperfect as it is, was one of the few big projects that the UK had actually got its act together on, during my lifetime, or at least one of the few big projects outside London. As a northerner I need HS2 to be implemented sensibly, because I know and feel how left-behind we've been in terms of the over-centralised London government investing in us. Plus, of course, modern train systems mean there's less need to fly or drive: so even when they have some impact in being built, they're likely to be good for our climate aims as well as for providing nice things to ordinary people, making life a little better.

The UK political system means, to a first approximation, that it's pretty likely the wind will blow the opposite way every four years. This is because it's effectively trapped in a two-party system, seesawing between the two. Big projects might eventually get planned - but then they get canned, or at least bodged, a few years later. Thanks to the stupid voting system it's really unlikely this will change in the next couple of decades. In a more sensible system, such as a proportional system, people's votes actually have the effect they're meant to. Parties that were once top-dog can fade to nothing if they don't do good work.

And the UK's problems are even more stuck when you realise how heavily centralised it all is. I hadn't realised this until I left the country and saw other ways of doing it. Running the country from London, pushing all local democracy to the fringe and hoovering up the person-power (see stats from Tom Forth on this), is so blinkered it hurts. The broken voting system, mentioned above, wouldn't matter so much if our local regions (county councils) still had budgets and leverage to get stuff done.

I want the UK to be better. I want to help too. I tried to make a difference while I was there, and I hope I can do again one day. I tried, and in many ways I was stymied.

I'm now living in a European country which - while not perfect - gives me a sense of optimism, a sense that it's possible to make sensible investments and plans that will help everyone. The basic feeling is the feeling that at the top level (politics, civil society, whatever), the rules of the game are not fixed to fuck us over.

I'm flying through the pitch-dark countryside right now, in a delightful night-train that crosses three countries, and I'm still impressed that it can cross countries so effortlessly. - Funnily enough, night-trains were more common in the past before the era of the motorway. Many night train services were dismantled as the car took over. Now, though, we realise they're a good way to do things, and there are many night train services being rekindled across the continent, in an evolving mix of government planning and commercial endeavour. All democracies are messy, and all have good decades and bad decades. I feel hope here, seeing what happens when there's a foundation that allows for civil negotiation and long-term planning.

This week was the DCASE 2021 workshop, a great workshop with lots of interesting research activity on Detection and Classification of Acoustic Scenes and Events.

Some observations from me:

• The development of "SED" (sound event detection) into "SELD" (sound event localisation and detection) is really welcome. There are lots of applications in which we want to infer the spatial location (or the direction) of the sound sources: robotics, bioacoustic surveying, etc. I saw some high-quality performance, and good development of synthetic training datasets etc.
  • There will always be tasks with no spatial information (lots of them!), so it seems likely that both SED and SELD should continue to be refined, in parallel.
  • The addition of spatial localisation brings the subject matter even closer to that of our underwater cousin DCLDE (Detection, Classification, Localization, and Density Estimation of Marine Mammals using Passive Acoustics). There's no need to consider "merging" workshops, but perhaps we should have more exchange between these communities.
• I appreciated the focus on small-footprint neural networks which was created by Task 1a's requirement for submitted systems to have a limited number of parameters (limited to 128kb of nonzero parameters). I remain unsure about whether this specific constraint is the best one - what about the size of the model, for example? It could be nice to try something such as applying a total RAM constraint on the entire process. But, still, the challenge encouraged the production on good small-footprint classifiers.
• I am proud of our work on Task 5, "few-shot bioacoustic event detection", of the large team that put it together, and the submitted works! I'm particularly proud because the way we designed the task is extremely closely linked to problems that practitioners in bioacoustics or animal behaviour face, and I think that with a little more development, we can hand them some good useful tools. I believe we have a very good balance: a task that is needed in practice, while also being conceptually interesting for algorithm development. (Here's a quick video overview of the task by Veronica.)

In the "town hall" plenary we discussed some interesting opinions about how to organise DCASE going forward. There was also a very interesting discussion, emerging from the "industry panel" plenary, of privacy and GDPR issues in using sound sensors in public. I'd like to thank the contributors to that discussion - it's a non-trivial issue and so it's very good to hear some well-considered perspectives on this.

You can watch the videos from DCASE 2021 here.

I'm looking forward to DCASE 2022 - in Nancy, France, in November. See you there!

I'm an academic working on AI and Biodiversity - my research is described here. If you're an MSc student at Tilburg University CSAI department (or elsewhere), you could take your project with me. In most cases you will need some deep learning skills, and in most cases you'll be working with natural sounds such as wildlife sound monitoring. Here are some specific topics of interest right now, that you could study:

• Novelty detection for biodiversity images/audio (with an industry partner)
  • We use images and sound recordings to detect birds, insects and plants all across the Netherlands. But what if we receive an upload with a species we don’t know about, or an unusual file that needs expert attention? In this project you will work with machine learning methods for anomaly detection, and apply them to biodiversity data. You will help to improve automatic monitoring of biodiversity, in the Netherlands and beyond.
• Detecting birdsong on-device
  • Automatic detection of sounds is useful for "wake-up" functionality in a smartphone. It's already used for keyword-spotting in mobile devices. Can we use it to automatically detect a particular birdsong? In this project we would like to develop a phone app that can listen continuously and react when a particular bird species is detected. We know this is possible, and you can solve it using standard deep learning toolkits - but the big challenge will be to run this on-phone (Android, iOS), creating a smart but low-power algorithm that can run on device. In this project you might use existing "keyword spotting" tools, or use toolkits such as TFlite to port an algorithm onto device.
• Classifying rare fish from photos (with an industry partner)
  • Our partner runs an app for anglers, who submit photos of the fish they catch, for automatic species ID. Can we use this unique dataset to help monitor the fish biodiversity of the Netherlands? Organisations such as the Waterschaps are obliged to make biodiversity reports to the EU, so would benefit from automatic monitoring technology. However, there is an interesting research question: photos of fish taken out of water are very different from those on automatic underwater cameras.This is an extreme example of "domain adaptation" in machine learning. You could also investigate how to classify rare fish species, in which we only have 1 or 2 live images – can image synthesis, or collections of drawings, help?
• Build a better bird classifier (with an industry partner)
  • Warblr is a mobile app for automatic birdsong classification. The company uses machine learning. It has its training dataset, but now it also has many thousands of user-contributed sound recordings (unlabelled). Can you use these data to train a better classifier for the app? The classifier must also fit within the constraints of the running service: no more than 10 million parameters, and no more than 4 seconds to produce a decision. To work on this problem, you might use methods such as self-supervised learning, semi-supervised learning, pretraining, model distillation, or model pruning.
• Birdsong automatic transcription
  • For images we have "object detection", and the equivalent for audio is "sound event detection" (SED). But - can we successfully detect all the sound events in a dawn chorus, when many birds are singing early in the morning? We have a dataset of annotated birdsong recordings. SED has been studied using deep learning, but we don't know if it works well enough for dense sound scenes of multiple birds. If we could get this working, we could understand animal behaviour (for example, are the birds taking turns) and also improve biodiversity monitoring
• Perceiver as a model of bat echolocation foraging
  • Some bats can recognise their favourite flowers by the sound of the echolocation reflected back to them. We replicated this process using a neural network, in a recent research paper. In the paper, we commented that there may be better ways to handle the sequential analysis of multiple echoes. A recent new neural network called Perceiver seems to be appropriate for this. Can you use it to analyse spectrograms of reflected bat echolocations?
• Optimal updating of a deep learning classifier service
  • We deploy deep learning (DL) classifiers, often using convolutional neural networks (CNNs), to recognise animal images and sounds. We also continuously receive new data – some of it labelled, some of it unlabelled. What’s the optimal way to “update” our classifier for best results? We could train it again from scratch; we could "fine tune" it using the new data; we could keep part of the model "frozen" and re-train part of it. And how would we verify that the model was not worse than the previous one? In this project you will design and validate an approach for updating a classifier for use in a live deployed web service, considering theoretical and practical aspects of how to maintain and improve the quality of service.
• Detecting animal sounds to improve animal welfare (with an industry partner)
  • We work with a small company that creates a device placed in farms to monitor the health and wellbeing of animals. They already monitor climate conditions and visual changes - but sound could also be a key indicator for animal health issues. Coughs, screams, or "alarm calls" could be detected (in cows, pigs, chickens, and more) to ensure any problems with welfare can be alerted rapidly. In this project you will train an AI algorithm to detect specific animal sounds, using data from a real commercial product, and implemeting the algorithm to run efficiently on a device (Raspberry Pi-based). You will validate the performance of the detector, try out improvements - and there is potential to deploy the system in a live setting, if the results are good.
• Birdsong classification with spectrogram patches
  • A recent deep learning paper found that using “patch embeddings” was a powerful method for image classification. It has some similarities with older methods used on patch embeddings of spectrograms for sound classification. In this project you will adapt the recent image-classification work for birdsong classification, and find out if you can create the next generation of powerful birdsong classifier.
• Sound event detection using transformers/perceivers
  • There has been recent interest in the "Transformer" and "Perceiver" neural network architecture, originally used for text data but now for images and audio. Can they be used for sound event detection/classification? In this project you will run a detection (or classification) audio task and compare their performance against standard CNN models.
• A simulated dataset for wildlife Sound Event Localisation and Detection
  • It is very useful to automatically localise and detect sounds – for example, multiple people speaking in a room. It would also be highly useful for outdoor wildlife monitoring – but there’s a problem: in order to train machine learning, we need a well-annotated training dataset, but it’s very hard to do this for outdoor natural sound recordings, because the sounds are complex and hard to annotate exactly. In this project, you will follow a recent method for creating synthetic SELD datasets but adapt it for outdoor sound. The challenges will be to obtain good sound source material, as well as “impulse responses” for natural reverberation, and to evaluate the naturalness of the synthesised sound recordings. Your work will enable the next generation of intelligent wildlife monitoring.

Also we have INTERNSHIP ideas:

• Internship: “Human perception of bird sounds”
  • We have conducted a research study in which we played bird song “syllables” to birds, and asked the birds which sounds were similar to each other. But what do humans think? Would they make the same decisions as birds? In this study you will reproduce our bird song comparison study with human volunteers. More specifically, volunteers hear 3 sounds, let’s cal them A/X/B, and they are asked: does X sound more similar to A or to B? From this study, we will be able to explore how similar or different human sound perception is to birds’ sound perception.
• Internship: "Adding annotation ability to the world’s largest open birdsong database"
  • Xeno Canto is the world’s biggest database of birdsong, with 60,000 recordings submitted each year. For data analysis and animal behaviour research, it’s useful to have annotations of the recordings (“who sung when”), but the site doesn’t have a facility for that. In this project you will add this feature. You’ll work with the existing PHP/MySQL website, adding a database table to upload+validate+store CSV annotations, and also perhaps visualise these annotations or provide users with direct editing ability.

Here are some PAST projects I've supervised:

• 2021:
  • Voice anonymisation in wildlife sound recordings
  • Insect sound classification using deep learning
  • Detecting animal sounds to improve animal welfare
  • Wildlife sound source separation using deep learning
• 2019:
  • Efficient bird sound detection on the Bela embedded system [Paper]
  • Short-term Prediction of Power Generated from Photovoltaic Systems using Gaussian Process Regression [Paper]
  • Listen like a bat: plant classification using echolocation and deep learning
  • Evaluating the impact of Full Spectrum Temporal Convolutional Neural Networks on Bird Species Sound Classification
• 2018:
  • Detecting and classifying animal calls
• 2017:
  • Estimating & Mitigating the Impact of Acoustic Environments on Digital Audio Signalling [Paper]

Check out the published papers to see some details from the kind of work we do!

Get in touch with me by email, info here. You're welcome to suggest a topic of your own, though to work with me it should concern new deep learning methods and/or animal sounds.