Improve the features available to your model, Remove some of the NOISE present in the data.
In audio data, a common way to do this is to smooth the data and then rectify it so that the total amount of sound energy over time is more distinguishable.
# Rectify the audio signal
audio_rectified = audio.apply(np.abs)
You can also calculate ...
The reason most music-generation models use discrete representations is because the long-term structures of music are very challenging to model. Note that the MIDI data in MAESTRO (used in the two papers you linked) encodes performances, not scores, so they include timing and accents of real performers--but are still sequences of discrete events, not audio.
After some research on the internet, I realized that using VOSK toolkit in python, it can be found (detect) any particular word in audio file or real time audio streaming.
You are heading in the right direction to make an audio-based classifier. This is not quite the same as providing a similarity metric between two pieces of audio, but it may do as a first attempt. You could use the "probability that this audio is a Queen song" as a proxy for similarity.
First of all, is 300 songs even enough?
Nowhere near enough ...
Yes, Transformers can be used to work with audio data, such as audio processing (audio classification, speaker identification, etc) (Audio ALBERT), speech-to-text (Streaming Automatic Speech Recognition with the Transformer Model), and text-to-speech (Neural Speech Synthesis with Transformer Network).
Google has an API you can use. https://cloud.google.com/translate/. Their API can translate audio to text. They also have an API for converting speech to text. The language detection feature should let you detect the language in the resulting text. They have client libraries for the most popular programming languages.
The task of isolating 2 or more speakers is called speaker diarization,
here a list of softwares and useful resources.
Once you have the 2 or more audio files containing the individual voices, you could run some speech-to-text network that also outputs time information.
OK, here is one approach.
Acquire a data set of 'clean' audio samples without barking dogs and an data set of barking dogs sounds.
Generate a training set by mixing random selections of clean audio with a random selections of barking dog noises at various volume levels. This is your input data. Your output data is the clean audio before you added the ...
Handling Multiple Input Types
Multiple input types are common as learning technology moves from academic labs and open source examples into the real world. The design process includes the below four steps, which related directly to this question. There are other steps that don't centrally related not mentioned here.
First Step — List Inputs in Most ...
Yes, intuition says that RNNs like LSTM or GRU will work better in your case, because predicted values might depend on input patterns corresponding to much earlier time intervals.
There is no reason to create samples shifted by a single measurement because many of the samples will contain pretty much the same information for your model. A viable approach is ...