Speaker Clustering With Neural Networks And Audio Processing
This work addresses speaker identification in audio recordings, but it is incremental as it aims to match existing methods rather than surpass them.
The paper tackled speaker clustering by applying neural networks and audio processing to differentiate speakers in recordings, achieving accuracy comparable to state-of-the-art methods.
Speaker clustering is the task of differentiating speakers in a recording. In a way, the aim is to answer "who spoke when" in audio recordings. A common method used in industry is feature extraction directly from the recording thanks to MFCC features, and by using well-known techniques such as Gaussian Mixture Models (GMM) and Hidden Markov Models (HMM). In this paper, we studied neural networks (especially CNN) followed by clustering and audio processing in the quest to reach similar accuracy to state-of-the-art methods.