AT&T Research at ICASSP (International Conference on Acoustics, Speech, and Signal Processing)

May 22 - 27, 2011

Prague, Czech Republic

Contact: Diamantino A. Caseiro

AT&T Research will be presenting six papers at this year’s International Conference on Acoustics, Speech and Signal Processing conference, with topics ranging from ASR and acoustic modeling, speech synthesis, and speech translation.


SP-P6: Modeling for ASR :
Enrico Bocchieri (presenting), Diamantino Caseiro, Dimitrios Dimitriadis

Speech Recognition Modeling Advances For Mobile Voice Search

May 24, 2011 at 04:15 PM


SP-L5: Acoustic Modeling I:
Dimitrios Dimitriadis (presenting), Enrico Bocchieri, Diamantino Caseiro

An Alternative Front-End for the AT&T WATSON LV-CSR System

May 25, 2011 at 01:45 PM

An Alternative Frontend for the AT&T WATSON LV-CSR System
Dimitrios Dimitriadis, Enrico Bocchieri, Diamantino Caseiro
International Conference on Acoustics, Speech and Signal Processing,  2011.  [BIB]


MLSP-P3: Machine Learning Methods and Applications II :
Sumit Chopra (presenting), Srinivas Bangalore

Non-Linear Tagging Models with Localist and Distributed Word Representations

May 25, 2011 at 04:15 PM


LP-P2: Speech Translation and Semantic Classification :
Giuseppe Di Fabbrizio, Diamantino Caseiro (presenting), and Amanda Stent

Semantic Data Selection For Vertical Business Voice Search

May 26, 2011 at 09:30 AM


SLP-P4: Paralinguistic and Non-Linguistic Features: Junlan Feng

Location-Aware Query Parsing for Mobile Voice Search

May 27, 2011 at 09:30 AM


EXP-11 Trends in Speech and Spoken Language Processing (expert session): Junlan Feng

May 27, 2011 at 11:45 AM


SP-P18: Speech Synthesis IV :
Alistair Conkie (presenting), Ann Syrdal

Using F0 to Constrain the Unit Selection Viterbi Search

May 27, 2011 at 01:45 PM