Speaker and noise factorisation on the AURORA4 task

For many realistic scenarios, there are multiple factors that affect the clean speech signal. In this work approaches to handling two such factors, speaker and background noise differences, simultaneously are described. A new adaptation scheme is proposed. Here the acoustic models are first adapted to the target speaker via an MLLR transform. This is followed by adaptation to the target noise environment via model-based vector Taylor series (VTS) compensation. These speaker and noise transforms are jointly estimated, using maximum likelihood. Experiments on the AURORA4 task demonstrate that this adaptation scheme provides improved performance over VTS-based noise adaptation. In addition, this framework enables the speech and noise to be factorised, allowing the speaker transform estimated in one noise condition to be successfully used in a different noise condition. © 2011 IEEE.

Multi-channel signal separation

The separation of independent sources from mixed observed data is a fundamental and challenging problem. In many practical situations, observations may be modelled as linear mixtures of a number of source signals, i.e. a linear multi-input multi-output system. A typical example is speech recordings made in an acoustic environment in the presence of background noise and/or competing speakers. Other examples include EEG signals, passive sonar applications and cross-talk in data communications. In this paper, we propose iterative algorithms to solve the n × n linear time invariant system under two different constraints. Some existing solutions for 2 × 2 systems are reviewed and compared.

SUB-BAND CODING TECHNIQUES FOR ROBUST 4. 8 TO 8 kb/s SPEECH CODERS.

This paper describes a speech coding technique that has been developed in order to provide a method of digitising speech at bit rates in the range 4. 8 to 8 kb/s, that is insensitive to the effects of acoustic background noise and bit errors on the digital link. The main aim has been to develop a coding scheme which provides speech quality and robustness against noise and errors that is similar to a 16000 b/s continuously variable slope delta (CVSD) coder, but which operates at half its data rate or less. A desirable aim was to keep the complexity of the coding scheme within the scope of what could reasonably be handled by current signal processing chips or by a single custom integrated circuit. Applications areas include mobile radio and small Satcomms terminals.

Challenges in the Silent Aircraft engine design

The Silent Aircraft Initiative goal is to design an aircraft that is imperceptible above background noise outside the airport boundary. The aircraft that fulfils this objective must also be economically competitive with conventional aircraft of the future and therefore fuel consumption and mechanical reliability are key considerations for the design. To meet these ambitious targets, a multi-fan embedded turbofan engine with boundary layer ingestion has been proposed. This configuration includes several new technologies including a variable area nozzle, a complex high-power transmission system, a Low Pressure turbine designed for low-noise, an axial-radial HP compressor, advanced acoustic liners and a low-speed fan optimized for both cruise and off-design operation. These technologies, in combination, enable a low-noise and fuel efficient propulsion system but they also introduce significant challenges into the design. These challenges include difficulties in predicting the noise and performance of the new components but there are also challenges in reducing the design risks and proving that the new concepts are realizable. This paper presents the details of the engine configuration that has been developed for the Silent Aircraft application. It describes the design approach used for the critical components and discusses the benefits of the new technologies. The new technologies are expected to offer significant benefits in noise reduction without compromising fuel burn. However, more detailed design and further research are required to fully control the additional risks generated by the system complexity.

Bypass transition to sustained thermoacoustic oscillations in a linearly stable rijke tube

In this paper we examine triggering in a simple linearly-stable thermoacoustic system using techniques from flow instability and optimal control. Firstly, for a noiseless system, we find the initial states that have highest energy growth over given times and from given energies. Secondly, by varying the initial energy, we find the lowest energy that just triggers to a stable periodic solution. We show that the corresponding initial state grows first towards an unstable periodic solution and, from there, to the stable periodic solution. This exploits linear transient growth, which arises due to nonnormality in the governing equations and is directly analogous to bypass transition to turbulence. Thirdly, we introduce noise that has similar spectral characteristics to this initial state. We show that, when triggering from low noise levels, the system grows to high amplitude self-sustained oscillations by first growing towards the unstable periodic solution of the noiseless system. This helps to explain the experimental observation that linearly-stable systems can trigger to self-sustained oscillations even with low background noise. © 2010 by University of Cambridge. Published by the American Institute of Aeronautics and Astronautics, Inc.

Improving reverberant VTS for hands-free robust speech recognition

Model-based approaches to handling additive background noise and channel distortion, such as Vector Taylor Series (VTS), have been intensively studied and extended in a number of ways. In previous work, VTS has been extended to handle both reverberant and background noise, yielding the Reverberant VTS (RVTS) scheme. In this work, rather than assuming the observation vector is generated by the reverberation of a sequence of background noise corrupted speech vectors, as in RVTS, the observation vector is modelled as a superposition of the background noise and the reverberation of clean speech. This yields a new compensation scheme RVTS Joint (RVTSJ), which allows an easy formulation for joint estimation of both additive and reverberation noise parameters. These two compensation schemes were evaluated and compared on a simulated reverberant noise corrupted AURORA4 task. Both yielded large gains over VTS baseline system, with RVTSJ outperforming the previous RVTS scheme. © 2011 IEEE.

An automatic speaker recognition system for intelligence applications

This paper presents an automatic speaker recognition system for intelligence applications. The system has to provide functionalities for a speaker skimming application in which databases of recorded conversations belonging to an ongoing investigation can be annotated and quickly browsed by an operator. The paper discusses the criticalities introduced by the characteristics of the audio signals under consideration - in particular background noise and channel/coding distortions - as well as the requirements and functionalities of the system under development. It is shown that the performance of state-of-the-art approaches degrades significantly in presence of moderately high background noise. Finally, a novel speaker recognizer based on phonetic features and an ensemble classifier is presented. Results show that the proposed approach improves performance on clean audio, and suggest that it can be employed towards improved real-world robustness. © EURASIP, 2009.