We present a practical and noise-robust speech recognition system which estimates a target-to-interferers power ratio using a zero-crossing-based binaural model and applies the power ratio to a channel attentive missing feature decoder in the cepstral domain. In a natural multisource environment, our binaural model extracts spatial cues at each zero-crossing of a filterbank output signal to loc...

A recent innovation in artificial intelligence research has been the integration of multiple artificial intelligence techniques into hybrid intelligent systems. Hybrid artificial intelligent systems seek to overcome the deficiencies of traditional artificial techniques by combining techniques with complementary capabilities. Using these hybrid systems, researchers have been able to solve a vari...

On some probability space (Ω,F,P), let (X)t≥0, 1 ≤ i ≤ d be d independent Brownian motions with constant drifts μ(i), 1 ≤ i ≤ d, and (T (j) n , Z n )n≥1, 1 ≤ j ≤ m be m independent compound Poisson processes independent of the Brownian motions (X)t≥0, 1 ≤ i ≤ d. For every 1 ≤ j ≤ m, (T (j) n )n≥1 are the arrival times, and (Z n )n≥1 are the marks on some measurable space (E, E), with arrival ra...

II diffraction problem was overcome by incorporating a new time delay factor into the GCC-PHAT method under the assumption of a spherical robot head. The ambiguity problem was overcome by utilizing the amplification effect of the pinnae. Finally the difficulties with multisource sound localization in real environments were addressed by extending the proposed ML-based SSL method using the new ti...

Because frequency load identification method will confront with the ill-posed problem of finding the inverse of coefficient matrix and it can only identify one load source, a new uncorrelated multi-source load identification algorithm based on linear regression and least-squares of generalized matrix inverse is proposed. According to response signals of multi-spot, this new algorithm can identi...

BBN submitted system combination outputs for Czech-English, German-English, SpanishEnglish, and French-English language pairs. All combinations were based on confusion network decoding. The confusion networks were built using incremental hypothesis alignment algorithm with flexible matching. A novel bi-gram count feature, which can penalize bi-grams not present in the input hypotheses correspon...

In a Cyber-Medicine System (CMS), the Internet is used to deliver healthcare services, such as medical consultations, diagnosis, and prescriptions. Services allow end-users (patients) online access to consultations and treatment with medical professionals. When the services benefit from the end-users activity and collaborative work, then the system becomes Social CMS (SCMS). In this position pa...