Summary of the paper
| Title | WTIMIT: The TIMIT Speech Corpus Transmitted Over The 3G AMR Wideband Mobile Network |
|---|---|
| Authors | Patrick Bauer, David Scheler and Tim Fingscheidt |
| Abstract | In anticipation of upcoming mobile telephony services with higher speechquality, a wideband (50 Hz to 7 kHz) mobile telephony derivative of TIMIT hasbeen recorded called WTIMIT. It opens up various scientific investigations;e.g., on speech quality and intelligibility, as well as on wideband upgrades ofnetwork-side interactive voice response (IVR) systems with retrained orbandwidth-extended acoustic models for automatic speech recognition (ASR).Wideband telephony could enable network-side speech recognition applicationssuch as remote dictation or spelling without the need of distributed speechrecognition techniques. The WTIMIT corpus was transmitted via two preparedNokia 6220 mobile phones over T-Mobile's 3G wideband mobile network in TheHague, The Netherlands, employing the Adaptive Multirate Wideband (AMR-WB)speech codec. The paper presents observations of transmission effects andphoneme recognition experiments. It turns out that in the case of widebandtelephony, server-side ASR should not be carried out by simply decimatingreceived signals to 8 kHz and applying existent narrowband acoustic models. Nordo we recommend just simulating the AMR-WB codec for training of widebandacoustic models. Instead, real-world wideband telephony channel data (such asWTIMIT) provides the best training material for wideband IVR systems. |
| Language | LR national/international projects, organizational/policy issues |
| Topics | Speech resource/database, Speech Recognition/Understanding, LR national/international projects, organizational/policy issues |
Full paper  |
WTIMIT: The TIMIT Speech Corpus Transmitted Over The 3G AMR Wideband Mobile Network |
| Bibtex | @InProceedings{BAUER10.285, author = {Patrick Bauer, David Scheler and Tim Fingscheidt}, title = {WTIMIT: The TIMIT Speech Corpus Transmitted Over The 3G AMR Wideband Mobile Network}, 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} } |