Towards a new speech event detection approach for landmark-based speech recognition

• Published in: 2012 IEEE Spoken Language Technology Workshop (SLT) pp. 342 - 347
• Main Authors: Ziegler, S., Ludusan, B., Gravier, G.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01-12-2012
• Subjects: Accuracy; Boosting; Hidden Markov models; landmark-driven ASR; Speech; speech event detection; Speech recognition; Training; Vectors
• ISBN: 9781467351256; 1467351253
• DOI: 10.1109/SLT.2012.6424247

In this work, we present a new approach for the classification and detection of speech units for the use in landmark or event-based speech recognition systems. We use segmentation to model any time-variable speech unit by a fixed-dimensional observation vector, in order to train a committee of boosted decision stumps on labeled training data. Given an unknown speech signal, the presence of a desired speech unit is estimated by searching for each time frame the corresponding segment, that provides the maximum classification score. This approach improves the accuracy of a phoneme classification task by 1.7%, compared to classification using HMMs. Applying this approach to the detection of broad phonetic landmarks inside a landmark-driven HMM-based speech recognizer significantly improves speech recognition.