Audio word similarity for clustering with zero resources based on iterative HMM classification

Amélie Royer (1) , Guillaume Gravier (1) , Vincent Claveau (1)

1 LinkMedia - Creating and exploiting explicit links between multimedia fragments

Recent work on zero resource word discovery makes intensive use of audio fragment clustering to find repeating speech patterns. In the absence of acoustic models, the clustering step traditionally relies on dynamic time warping (DTW) to compare two samples and thus suffers from the known limitations of this technique. We propose a new sample comparison method, called 'similarity by iterative classification', that exploits the modeling capacities of hidden Markov models (HMM) with no supervision. The core idea relies on the use of HMMs trained on randomly labeled data and exploits the fact that similar samples are more likely to be classified together by a large number of random classifiers than dissimilar ones. The resulting similarity measure is compared to DTW on two tasks, namely nearest neighbor retrieval and clustering , showing that the generalization capabilities of probabilis-tic machine learning significantly benefit to audio word comparison and overcome many of the limitations of DTW-based comparison.

Mots clés: acoustic similarity; dynamic time warping; Index Terms— zero-resource speech processing; word; discovery; audio words clustering; unsupervised learning

Domaines: Intelligence artificielle [cs.AI]; Informatique et langage [cs.CL]; Recherche d'information [cs.IR]

Amélie Royer, Guillaume Gravier, Vincent Claveau. Audio word similarity for clustering with zero resources based on iterative HMM classification. International Conference on Acoustics, Speech and Signal Processing, ICASSP, Mar 2016, Shanghai, China. pp.5340 - 5344, ⟨10.1109/ICASSP.2016.7472697⟩. ⟨hal-01394757⟩