IMPROVED POSTFILTERING TECHNIQUE FOR BLOCK QUANTISATION OF SPEECH.

A modified comb filtering technique is proposed which can be used to reduce framing noise generated when speech signals are transform-coded or vector-quantized. Application of this filter to 9. 6 kbit/s speech in a vector transform coder has been found to improve the perceptual quality of the coded speech.

Application of artificial neural network techniques to low bit-rate speech coding

Research has been undertaken to investigate the use of artificial neural network (ANN) techniques to improve the performance of a low bit-rate vector transform coder. Considerable improvements in the perceptual quality of the coded speech have been obtained. New ANN-based methods for vector quantiser (VQ) design and for the adaptive updating of VQ codebook are introduced for use in speech coding applications.

Optimization of Weighted Finite State Transducer for Speech Recognition

There is considerable interest in creating embedded, speech recognition hardware using the weighted finite state transducer (WFST) technique but there are performance and memory usage challenges. Two system optimization techniques are presented to address this; one approach improves token propagation by removing the WFST epsilon input arcs; another one-pass, adaptive pruning algorithm gives a dramatic reduction in active nodes to be computed. Results for memory and bandwidth are given for a 5,000 word vocabulary giving a better practical performance than conventional WFST; this is then exploited in an adaptive pruning algorithm that reduces the active nodes from 30,000 down to 4,000 with only a 2 percent sacrifice in speech recognition accuracy; these optimizations lead to a more simplified design with deterministic performance.

Robust Audio-Visual Speech Recognition under Noisy Audio-Video Conditions

This paper presents the maximum weighted stream posterior (MWSP) model as a robust and efficient stream integration method for audio-visual speech recognition in environments, where the audio or video streams may be subjected to unknown and time-varying corruption. A significant advantage of MWSP is that it does not require any specific measurements of the signal in either stream to calculate appropriate stream weights during recognition, and as such it is modality-independent. This also means that MWSP complements and can be used alongside many of the other approaches that have been proposed in the literature for this problem. For evaluation we used the large XM2VTS database for speaker-independent audio-visual speech recognition. The extensive tests include both clean and corrupted utterances with corruption added in either/both the video and audio streams using a variety of types (e.g., MPEG-4 video compression) and levels of noise. The experiments show that this approach gives excellent performance in comparison to another well-known dynamic stream weighting approach and also compared to any fixed-weighted integration approach in both clean conditions or when noise is added to either stream. Furthermore, our experiments show that the MWSP approach dynamically selects suitable integration weights on a frame-by-frame basis according to the level of noise in the streams and also according to the naturally fluctuating relative reliability of the modalities even in clean conditions. The MWSP approach is shown to maintain robust recognition performance in all tested conditions, while requiring no prior knowledge about the type or level of noise.

The lipopolysaccharide core of Brucella abortus acts as a shield against innate immunity recognition

Innate immunity recognizes bacterial molecules bearing pathogen-associated molecular patterns to launch inflammatory responses leading to the activation of adaptive immunity. However, the lipopolysaccharide (LPS) of the gram-negative bacterium Brucella lacks a marked pathogen-associated molecular pattern, and it has been postulated that this delays the development of immunity, creating a gap that is critical for the bacterium to reach the intracellular replicative niche. We found that a B. abortus mutant in the wadC gene displayed a disrupted LPS core while keeping both the LPS O-polysaccharide and lipid A. In mice, the wadC mutant induced proinflammatory responses and was attenuated. In addition, it was sensitive to killing by non-immune serum and bactericidal peptides and did not multiply in dendritic cells being targeted to lysosomal compartments. In contrast to wild type B. abortus, the wadC mutant induced dendritic cell maturation and secretion of pro-inflammatory cytokines. All these properties were reproduced by the wadC mutant purified LPS in a TLR4-dependent manner. Moreover, the core-mutated LPS displayed an increased binding to MD-2, the TLR4 co-receptor leading to subsequent increase in intracellular signaling. Here we show that Brucella escapes recognition in early stages of infection by expressing a shield against recognition by innate immunity in its LPS core and identify a novel virulence mechanism in intracellular pathogenic gram-negative bacteria. These results also encourage for an improvement in the generation of novel bacterial vaccines.

Linking Parliamentary Records through Metatdata

The LIPARM schema links the parliamentary record together for the first time by creating a unified metadata scheme for all of its key elements. People, bills, acts, items of business, debates, divisions and sessions will all be described by the scheme and will be linked together across resources which are currently spread out and isolated. For the first time, it will be possible to trace a given MP’s entire voting record or to find every speech they made. It will be possible to follow the passage of every bill or act, and every contribution to the debates that accompany it. Both the historical and the contemporary record of parliamentary proceedings will become accessible in this way for the first time.

A Corpus-Based Approach to Speech Enhancement from Nonstationary Noise

Temporal dynamics and speaker characteristics are two important features of speech that distinguish speech from noise. In this paper, we propose a method to maximally extract these two features of speech for speech enhancement. We demonstrate that this can reduce the requirement for prior information about the noise, which can be difficult to estimate for fast-varying noise. Given noisy speech, the new approach estimates clean speech by recognizing long segments of the clean speech as whole units. In the recognition, clean speech sentences, taken from a speech corpus, are used as examples. Matching segments are identified between the noisy sentence and the corpus sentences. The estimate is formed by using the longest matching segments found in the corpus sentences. Longer speech segments as whole units contain more distinct dynamics and richer speaker characteristics, and can be identified more accurately from noise than shorter speech segments. Therefore, estimation based on the longest recognized segments increases the noise immunity and hence the estimation accuracy. The new approach consists of a statistical model to represent up to sentence-long temporal dynamics in the corpus speech, and an algorithm to identify the longest matching segments between the noisy sentence and the corpus sentences. The algorithm is made more robust to noise uncertainty by introducing missing-feature based noise compensation into the corpus sentences. Experiments have been conducted on the TIMIT database for speech enhancement from various types of nonstationary noise including song, music, and crosstalk speech. The new approach has shown improved performance over conventional enhancement algorithms in both objective and subjective evaluations.