Abstract | ||
---|---|---|
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 teaming 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. |
Year | DOI | Venue |
---|---|---|
2017 | 10.21437/Interspeech.2017-1093 | 18TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2017), VOLS 1-6: SITUATED INTERACTION |
Keywords | DocType | Volume |
topic identification, unsupervised term discovery, acoustic unit discovery, convolutional neural networks | Conference | abs/1703.07476 |
ISSN | Citations | PageRank |
2308-457X | 1 | 0.39 |
References | Authors | |
0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Chunxi Liu | 1 | 23 | 3.28 |
Jan Trmal | 2 | 235 | 20.91 |
Matthew Wiesner | 3 | 5 | 2.85 |
Craig Harman | 4 | 25 | 3.90 |
Sanjeev Khudanpur | 5 | 2155 | 202.00 |