Exploiting Chinese character models to improve speech recognition performance

The Chinese language is based on characters which are syllabic in nature. Since languages have syllabotactic rules which govern the construction of syllables and their allowed sequences, Chinese character sequence models can be used as a first level approximation of allowed syllable sequences. N-gram character sequence models were trained on 4.3 billion characters. Characters are used as a first level recognition unit with multiple pronunciations per character. For comparison the CU-HTK Mandarin word based system was used to recognize words which were then converted to character sequences. The character only system error rates for one best recognition were slightly worse than word based character recognition. However combining the two systems using log-linear combination gives better results than either system separately. An equally weighted combination gave consistent CER gains of 0.1-0.2% absolute over the word based standard system. Copyright © 2009 ISCA.

Language model combination and adaptation using weighted finite state transducers

In speech recognition systems language model (LMs) are often constructed by training and combining multiple n-gram models. They can be either used to represent different genres or tasks found in diverse text sources, or capture stochastic properties of different linguistic symbol sequences, for example, syllables and words. Unsupervised LM adaptation may also be used to further improve robustness to varying styles or tasks. When using these techniques, extensive software changes are often required. In this paper an alternative and more general approach based on weighted finite state transducers (WFSTs) is investigated for LM combination and adaptation. As it is entirely based on well-defined WFST operations, minimum change to decoding tools is needed. A wide range of LM combination configurations can be flexibly supported. An efficient on-the-fly WFST decoding algorithm is also proposed. Significant error rate gains of 7.3% relative were obtained on a state-of-the-art broadcast audio recognition task using a history dependently adapted multi-level LM modelling both syllable and word sequences. ©2010 IEEE.

Assessment of CFD models for shock boundary-layer interaction

A workshop on the computational fluid dynamics (CFD) prediction of shock boundary-layer interactions (SBLIs) was held at the 48th AIAA Aerospace Sciences Meeting. As part of the workshop numerous CFD analysts submitted solutions to four experimentally measured SBLIs. This paper describes the assessment of the CFD predictions. The assessment includes an uncertainty analysis of the experimental data, the definition of an error metric and the application of that metric to the CFD solutions. The CFD solutions provided very similar levels of error and in general it was difficult to discern clear trends in the data. For the Reynolds Averaged Navier-Stokes methods the choice of turbulence model appeared to be the largest factor in solution accuracy. Large-eddy simulation methods produced error levels similar to RANS methods but provided superior predictions of normal stresses.

Investigation of acoustic units for LVCSR systems

One important issue in designing state-of-the-art LVCSR systems is the choice of acoustic units. Context dependent (CD) phones remain the dominant form of acoustic units. They can capture the co-articulatory effect in speech via explicit modelling. However, for other more complicated phonological processes, they rely on the implicit modelling ability of the underlying statistical models. Alternatively, it is possible to construct acoustic models based on higher level linguistic units, for example, syllables, to explicitly capture these complex patterns. When sufficient training data is available, this approach may show an advantage over implicit acoustic modelling. In this paper a wide range of acoustic units are investigated to improve LVCSR system performance. Significant error rate gains up to 7.1% relative (0.8% abs.) were obtained on a state-of-the-art Mandarin Chinese broadcast audio recognition task using word and syllable position dependent triphone and quinphone models. © 2011 IEEE.

Synchronous operation control of the Brushless Doubly-Fed Machine

The paper presents a novel vector control structure for the Brushless Doubly-Fed Machine (BDFM) which is derived based on the machine synchronous operation. In fact, the synchronous operation of the BDFM provides an efficient approach for determining the required reference angle in the machine vector control structure. The utilization of such reference angle makes the vector control structure presented in this paper different from and, in fact, more effective than the existing rotor flux and stator flux orientation schemes proposed for the machine. The results of implementing the vector control scheme in simulations confirm the effectiveness of the proposed approach for the BDFM control. © 2010 IEEE.

Femtosecond superradiant emission in AlGaInAs quantum-well semiconductor laser structures.

Ultrashort superradiant pulse generation from a 1580 nm AlGaInAs multiple quantum-well (MQW) semiconductor structure has been experimentally demonstrated for the first time. Superradiance is confirmed by analyzing the evolution of the optical temporal waveforms and spectra. Superradiant trends and regimes are studied as a function of driving condition. An optical pulse train is obtained at 1580 nm wavelength, with pulse durations as short as 390 fs and pulse peak powers of 7.2 W.

Assessment of computational fluid dynamics and experimental data for shock boundary-layer interactions

A workshop on the computational fluid dynamics (CFD) prediction of shock boundary-layer interactions (SBLIs) was held at the 48th AIAA Aerospace Sciences Meeting. As part of the workshop, numerous CFD analysts submitted solutions to four experimentally measured SBLIs. This paper describes the assessment of the CFD predictions. The assessment includes an uncertainty analysis of the experimental data, the definition of an error metric, and the application of that metric to the CFD solutions. The CFD solutions provided very similar levels of error and, in general, it was difficult to discern clear trends in the data. For the Reynolds-averaged Navier-Stokes (RANS) methods, the choice of turbulence model appeared to be the largest factor in solution accuracy. Scale-resolving methods, such as large-eddy simulation (LES), hybrid RANS/LES, and direct numerical simulation, produced error levels similar to RANS methods but provided superior predictions of normal stresses. Copyright © 2012 by Daniella E. Raveh and Michael Iovnovich.