Summary of the paper
| Title | A Snack Implementation and Tcl/Tk Interface to the Fundamental Frequency Variation Spectrum Algorithm |
|---|---|
| Authors | Kornel Laskowski and Jens Edlund |
| Abstract | Intonation is an important aspect of vocal production, used for a variety ofcommunicative needs. Its modeling is therefore crucial in many speechunderstanding systems, particularly those requiring inference of speaker intentin real-time. However, the estimation of pitch, traditionally the first step inintonation modeling, is computationally inconvenient in such scenarios. This isbecause it is often, and most optimally, achieved only after speechsegmentation and recognition. A consequence is that earlier speech processingcomponents, in today’s state-of-the-art systems, lack intonation awareness byfiat; it is not known to what extent this circumscribes their performance. Inthe current work, we present a freely available implementation of analternative to pitch estimation, namely the computation of the fundamentalfrequency variation (FFV) spectrum, which can be easily employed at any levelwithin a speech processing system. It is our hope that the implementation wedescribe aid in the understanding of this novel acoustic feature space, andthat it facilitate its inclusion, as desired, in the front-end routines ofspeech recognition, dialog act recognition, and speaker recognition systems. |
| Language | Speech Recognition/Understanding |
| Topics | Tools, systems, applications, Prosody, Speech Recognition/Understanding |
Full paper  |
A Snack Implementation and Tcl/Tk Interface to the Fundamental Frequency Variation Spectrum Algorithm |
| Bibtex | @InProceedings{LASKOWSKI10.576, author = {Kornel Laskowski and Jens Edlund}, title = {A Snack Implementation and Tcl/Tk Interface to the Fundamental Frequency Variation Spectrum Algorithm}, booktitle = {Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC'10)}, year = {2010}, month = {may}, date = {19-21}, address = {Valletta, Malta}, editor = {Nicoletta Calzolari (Conference Chair), Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odjik, Stelios Piperidis, Mike Rosner, Daniel Tapias}, publisher = {European Language Resources Association (ELRA)}, isbn = {2-9517408-6-7}, language = {english} } |