The video and slides from Simon’s keynote are now online under Courses > One-off events.
October 11, 2014
Pipeline architecture for TTS
Most text-to-speech systems split the problem into two main stages. The first stage is called the front end and contains many separate processes which gradually build up a linguistic specification from the input text. The second stage typically uses language-independent techniques (although they still require a language-specific speech corpus) to generate a waveform. Here we see those two […]
Continue reading... October 11, 2014
Spectrum and spectrogram
The spectrum and the spectrogram are much more useful ways of analysing speech signals than the waveform. We look at how to create them using Wavesurfer and what effect the analysis window size has on what we see.
Continue reading... October 30, 2015
Wave propagation on the surface of water
At the Alhambra (Granada, Spain) I saw this nice example of waves from a point source propagating in all directions at a fixed speed.
Continue reading... October 25, 2014
A super-simple speech recogniser
We make what is possibly the world’s simplest speech recognition system. It can only recognise two different words, but will help you understand the basic idea of pattern recognition using template matching. The templates are just pre-recorded words, with known labels. The features extracted are just two formant frequencies in the middle of the word, […]
Continue reading... October 18, 2014
TD-PSOLA …the hard way
Time-Domain Pitch Synchronous Overlap and Add (TD-PSOLA) can modify the fundamental frequency and duration of speech signals, without affecting the segment identity – that is, without changing the formants. Normally, it’s an automatic algorithm, but here we do it the hard way – by hand! If you want to follow-along, you will need Audacity and these materials (a […]
Continue reading... February 6, 2012
My inaugural lecture
I talk about how speech synthesis works, in what I hope is a non-technical and accessible way, and finish off with an application of speech synthesis that gives personalised voices to people who are losing the ability to speak. I also try to mention bicycles as many times as possible. For a more up-to-date, slightly more technical, […]
Continue reading... November 15, 2014
Token passing
Token passing is a really nice way to understand (and even to implement) Viterbi search for Hidden Markov Models. Here we see token passing in action, and you can look at the spreadsheet to see the calculations. To keep things simple, we are ignoring transition probabilities in this example. It would be simple to add them […]
Continue reading... October 11, 2014
Sampling and quantisation
Is digital better than analogue? Here we discover that there are limitations when storing waveforms digitally. We learn that the consequence of sampling at a fixed rate is an upper limit on the frequencies that can be represented, called the Nyquist frequency. In addition to the limitations of sampling, storing each sample of the waveform as a […]
Continue reading... November 1, 2022
Bitrate
The bitrate (or bit rate) of a signal is the number of bits required to store, or transmit, 1 s of that signal. A bit is a binary number: either 0 or 1. Let’s calculate the bitrate of a digital waveform. First you should revise the concepts of sampling and quantisation from this module of the […]
Continue reading... October 11, 2014
A simple synthetic vowel
Using Praat, we synthesise a simple vowel-like sound, starting with a pulse train, which we pass through a filter with resonant peaks.
Continue reading... October 11, 2014
Aliasing
In sampling and quantisation we saw that sampling a signal at a fixed rate means that there is an upper limit on the frequencies that can be represented. This limit is called the Nyquist frequency. Before sampling a signal, we must remove all energy above the Nyquist frequency, and here we will see what would […]
Continue reading...
This is the new version. Still under construction.