| Conference/Proceedings | 17th in a series of conferences organised by the European Association for Signal, Speech, and Image Processing (EUSIPCO 2009) |
| Start date | 24.08.2009 |
| End date | 28.08.2009 |
| Address | Glasgow, Scotland |
| Organisation | The European Association for Signal Processing (EURASIP) |
| Author(s) | Shan Jin, Thomas Sikora |
| Title | Combining Confusion Networks with probabilistic phone matching for open-vocabulary keyword spotting in spontaneous speech signal |
| Abstract | In this paper, we study several methods for keyword spotting in spontaneous speech signal. Novel method combining probabilistic phone matching (PSM) approach with word confusion networks (WCN) is proposed for open-vocabulary keyword spotting task. This method runs keyword spotting on multi-level transcriptions (WCN and phone-onebest). We propose to use classical string matching for word spotting on WCN. At the same time probabilistic string matching is used for acoustic word spotting on phone-onebest transcription. It is verified that the novel hybrid method outperforms WCN-based and PSM-based approaches in-vocabulary and out-of-vocabulary (OOV) keywords. |
| Key words | phone matching, keyword spotting, confusion networks |