Projects per year
We present an approach for the manual labeling of speech at the articulatory feature level, and a new set of labeled conversational speech collected using this approach. A detailed transcription, including overlapping or reduced gestures, is useful for studying the great pronunciation variability in conversational speech. It also facilitates the testing of feature classiers, such as those used in articulatory approaches to automatic speech recognition. We describe an effort to transcribe a small set of utterances drawn from the Switchboard database using eight articulatory tiers. Two transcribers have labeled these utterances in a multi-pass strategy, allowing for correction of errors. We describe the data collection methods and analyze the data to determine how quickly and reliably this type of transcription can be done. Finally, we demonstrate one use of the new data set by testing a set of multilayer perceptron feature classiers against both the manual labels and forced alignments.
|Title of host publication||Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, 2007 (ICASSP 2007)|
|Number of pages||4|
|Publication status||Published - 1 Apr 2007|
FingerprintDive into the research topics of 'Manual transcription of conversational speech at the articulatory feature level'. Together they form a unique fingerprint.
- 1 Finished
Streamed models for automatic speech recognition (EPSRC Advanced Research Fellowship)
1/01/05 → 31/12/09