Is there a method to detect a specific word and tell me the timestamp throughout an audio sample easily? I've been trying to implement something like this but wasn't sure how to approach it.
If you already have the transcript without timestamps (e.g. for an audiobook where you know the source text), you could use https://github.com/readbeyond/aeneas , which infers the timestamps by aligning text-to-speech output with the audio using dynamic time warping.
If you don't have the transcript, you'd use a transcription service that also gives you timestamps. E.g. there was a frontpage submission yesterday where someone used AWS Transcription to count the number of words in each minute of a talk: https://news.ycombinator.com/item?id=21635939
If you can utilize a cloud API, speech transcription route is likely the simplest.
Recognizing spoken words is challenging and data-demanding when it can be spoken by many different speakers.
But if you want to do this on the audio you chop up your audio stream into fixed-length (in time) analysis windows. These length of the window should be a bit longer than the sound of interest (the word). Overlap is normally used for the windows. Say with 90% overlap the next window is created by moving forward by 10%. This gives the model multiple "shots" at detecting the word as it passes by. This is suitable for spotting a word and giving the time within something like 50ms resolution.
For each analysis window you apply feature pre-processing and a model such as the one shown in the article.
This task sounds like what is called Keyword Spotting in academic literature. Which can be seen as as specific version of Audio Event Detection, applied to spoken words.
Given you have a transcription methode (but without the t timestamp output) the simplest methode might be to do a moving window throughout the sample and try to see where the detection results in a positiv.
