In this paper we conduct a feasibility study of delay-critical safety applications over vehicular ad hoc networks based on the emerging dedicated short range communications (DSRC) standard. In particular, we quantify the bit error rate, throughput and latency associated with vehicle collision avoidance applications running on top of mobile ad hoc networks employing the physical and MAC layers of DSRC. Towards this objective, the study goes through two phases. First, we conduct a detailed simulation study of the DSRC physical layer in order to judge the link bit error rate performance under a wide variety of vehicles speeds and multi-path delay spreads. We observe that the physical layer is highly immune to large delay spreads that might arise in the highway environment whereas performance degrades considerably at high speeds in a multi-path environment. Second, we develop a simulation testbed for a DSRC vehicular ad hoc network executing vehicle collision avoidance applications in an attempt to gauge the level of support the DSRC standard provides for this type of applications. Initial results reveal that DSRC achieves promising latency performance, yet, the throughput performance needs further improvement.

Automatic speech recognition (ASR) systems for children have lagged behind in performance when compared to adult ASR. The exact problems and evaluation methods for child ASR have not yet been fully investigated. Recent work from the robotics community suggests that ASR for kindergarten speech is especially difficult, even though this age group may benefit most from voice-based educational and diagnostic tools. Our study focused on ASR performance for specific grade levels (K-10) using a word identification task. Grade-specific ASR systems were evaluated, with particular attention placed on the evaluation of kindergarten-aged children (5-6 years old). Experiments included investigation of grade-specific interactions with triphone models using feature space maximum likelihood linear regression (fMLLR), vocal tract length normalization (VTLN), and subglottal resonance (SGR) normalization. Our results indicate that kindergarten ASR performs dramatically worse than even 1st grade ASR, likely due to large speech variability at that age. As such, ASR systems may require targeted evaluations on kindergarten speech rather than being evaluated under the guise of "child ASR." Additionally, results show that systems trained in matched conditions on kindergarten speech may be less suitable than mismatched-grade training with 1st grade speech. Finally, we analyzed the phonetic errors made by the kindergarten ASR.

The ability to automatically characterize all RF sources that have signijicant energy at a particular point in space has important applications in scientific, military, and industrial settings. Examples include automatic characterization of interference in radio astronomy, automatic signal detection and classijication for military surveillance, and inteverence characterization for communication-system test and evaluation. Such analyses are particularly diffcult when the unknown RF signals overlap in both time andfrequency or when the number of possible signal types is large.In this paper; we present a methd of automatically detecting, characterizing, and classijiing each of a number of RF sources that can spectrally and temporally overlap and that can be weak relative to the receiver noise. The method exploits the structure of higherorder statistics of manmade RF signals.

Due to within-speaker variability in phonetic content and/or speaking style, the performance of automatic speaker verification (ASV) systems degrades especially when the enrollment and test utterances are short. This study examines how different types of variability influence performance of ASV systems. Speech samples (< 2 sec) from the UCLA Speaker Variability Database containing 5 different read sentences by 200 speakers were used to study content variability. Other samples (about 5 sec) that contained speech directed towards pets, characterized by exaggerated prosody, were used to analyze style variability. Using the i-vector/PLDA framework, the ASV system error rate with MFCCs had a relative increase of at least 265% and 730% in content-mismatched and style-mismatched trials, respectively. A set of features that represents voice quality (F0, F1, F2, F3, H1-H2, H2-H4, H4-H2k, A1, A2, A3, and CPP) was also used. Using score fusion with MFCCs, all conditions saw decreases in error rates. In addition, using the NIST SRE10 database, score fusion provided relative improvements of 11.78% for 5-second utterances, 12.41% for 10-second utterances, and a small improvement for long utterances (about 5 min). These results suggest that voice quality features can improve short-utterance text-independent ASV system performance.

No abstract