Topic Identification for Speech without ASR
This addresses the challenge of topic identification in resource-limited settings where ASR training data is scarce, offering an incremental improvement over existing methods.
The paper tackles the problem of topic identification for speech without relying on ASR by proposing unsupervised tokenizations into word-like or phoneme-like units, and shows that a CNN-based framework achieves competitive performance on single-label and multi-label classification tasks.
Modern topic identification (topic ID) systems for speech use automatic speech recognition (ASR) to produce speech transcripts, and perform supervised classification on such ASR outputs. However, under resource-limited conditions, the manually transcribed speech required to develop standard ASR systems can be severely limited or unavailable. In this paper, we investigate alternative unsupervised solutions to obtaining tokenizations of speech in terms of a vocabulary of automatically discovered word-like or phoneme-like units, without depending on the supervised training of ASR systems. Moreover, using automatic phoneme-like tokenizations, we demonstrate that a convolutional neural network based framework for learning spoken document representations provides competitive performance compared to a standard bag-of-words representation, as evidenced by comprehensive topic ID evaluations on both single-label and multi-label classification tasks.