FPGA implementation of dual-microphone delay-and-sum beamforming for in-car speech enhancement and recognition

In an automotive environment, the performance of a speech recognition system is affected by environmental noise if the speech signal is acquired directly from a microphone. Speech enhancement techniques are therefore necessary to improve the speech recognition performance. In this paper, a field-programmable gate array (FPGA) implementation of dual-microphone delay-and-sum beamforming (DASB) for speech enhancement is presented. As the first step towards a cost-effective solution, the implementation described in this paper uses a relatively high-end FPGA device to facilitate the verification of various design strategies and parameters. Experimental results show that the proposed design can produce output waveforms close to those generated by a theoretical (floating-point) model with modest usage of FPGA resources. Speech recognition experiments are also conducted on enhanced in-car speech waveforms produced by the FPGA in order to compare recognition performance with the floating-point representation running on a PC.

Contrasting scenarios : embracing speech recognition

The purpose of this chapter is to describe the use of caricatured contrasting scenarios (Bødker, 2000) and how they can be used to consider potential designs for disruptive technologies. The disruptive technology in this case is Automatic Speech Recognition (ASR) software in workplace settings. The particular workplace is the Magistrates Court of the Australian Capital Territory.----- Caricatured contrasting scenarios are ideally suited to exploring how ASR might be implemented in a particular setting because they allow potential implementations to be “sketched” quickly and with little effort. This sketching of potential interactions and the emphasis of both positive and negative outcomes allows the benefits and pitfalls of design decisions to become apparent.----- A brief description of the Court is given, describing the reasons for choosing the Court for this case study. The work of the Court is framed as taking place in two modes: Front of house, where the courtroom itself is, and backstage, where documents are processed and the business of the court is recorded and encoded into various systems.----- Caricatured contrasting scenarios describing the introduction of ASR to the front of house are presented and then analysed. These scenarios show that the introduction of ASR to the court would be highly problematic.----- The final section describes how ASR could be re-imagined in order to make it useful for the court. A final scenario is presented that describes how this re-imagined ASR could be integrated into both the front of house and backstage of the court in a way that could strengthen both processes.

Automatic tracking, super-resolution and recognition of human faces from surveillance video

Identifying an individual from surveillance video is a difficult, time consuming and labour intensive process. The proposed system aims to streamline this process by filtering out unwanted scenes and enhancing an individual's face through super-resolution. An automatic face recognition system is then used to identify the subject or present the human operator with likely matches from a database. A person tracker is used to speed up the subject detection and super-resolution process by tracking moving subjects and cropping a region of interest around the subject's face to reduce the number and size of the image frames to be super-resolved respectively. In this paper, experiments have been conducted to demonstrate how the optical flow super-resolution method used improves surveillance imagery for visual inspection as well as automatic face recognition on an Eigenface and Elastic Bunch Graph Matching system. The optical flow based method has also been benchmarked against the ``hallucination'' algorithm, interpolation methods and the original low-resolution images. Results show that both super-resolution algorithms improved recognition rates significantly. Although the hallucination method resulted in slightly higher recognition rates, the optical flow method produced less artifacts and more visually correct images suitable for human consumption.

Robust speech recognition using speech enhancement

Automatic Speech Recognition (ASR) has matured into a technology which is becoming more common in our everyday lives, and is emerging as a necessity to minimise driver distraction when operating in-car systems such as navigation and infotainment. In “noise-free” environments, word recognition performance of these systems has been shown to approach 100%, however this performance degrades rapidly as the level of background noise is increased. Speech enhancement is a popular method for making ASR systems more ro- bust. Single-channel spectral subtraction was originally designed to improve hu- man speech intelligibility and many attempts have been made to optimise this algorithm in terms of signal-based metrics such as maximised Signal-to-Noise Ratio (SNR) or minimised speech distortion. Such metrics are used to assess en- hancement performance for intelligibility not speech recognition, therefore mak- ing them sub-optimal ASR applications. This research investigates two methods for closely coupling subtractive-type enhancement algorithms with ASR: (a) a computationally-efficient Mel-filterbank noise subtraction technique based on likelihood-maximisation (LIMA), and (b) in- troducing phase spectrum information to enable spectral subtraction in the com- plex frequency domain. Likelihood-maximisation uses gradient-descent to optimise parameters of the enhancement algorithm to best fit the acoustic speech model given a word se- quence known a priori. Whilst this technique is shown to improve the ASR word accuracy performance, it is also identified to be particularly sensitive to non-noise mismatches between the training and testing data. Phase information has long been ignored in spectral subtraction as it is deemed to have little effect on human intelligibility. In this work it is shown that phase information is important in obtaining highly accurate estimates of clean speech magnitudes which are typically used in ASR feature extraction. Phase Estimation via Delay Projection is proposed based on the stationarity of sinusoidal signals, and demonstrates the potential to produce improvements in ASR word accuracy in a wide range of SNR. Throughout the dissertation, consideration is given to practical implemen- tation in vehicular environments which resulted in two novel contributions – a LIMA framework which takes advantage of the grounding procedure common to speech dialogue systems, and a resource-saving formulation of frequency-domain spectral subtraction for realisation in field-programmable gate array hardware. The techniques proposed in this dissertation were evaluated using the Aus- tralian English In-Car Speech Corpus which was collected as part of this work. This database is the first of its kind within Australia and captures real in-car speech of 50 native Australian speakers in seven driving conditions common to Australian environments.

How environmental and organizational complexity affects opportunity recognition and exploitation in development projects

Principal Topic: Project structures are often created by entrepreneurs and large corporate organizations to develop new products. Since new product development projects (NPDP) are more often situated within a larger organization, intrapreneurship or corporate entrepreneurship plays an important role in bringing these projects to fruition. Since NPDP often involves the development of a new product using immature technology, we describe development of an immature technology. The Joint Strike Fighter (JSF) F-35 aircraft is being developed by the U.S. Department of Defense and eight allied nations. In 2001 Lockheed Martin won a $19 billion contract to develop an affordable, stealthy and supersonic all-weather strike fighter designed to replace a wide range of aging fighter aircraft. In this research we define a complex project as one that demonstrates a number of sources of uncertainty to a degree, or level of severity, that makes it extremely difficult to predict project outcomes, to control or manage project (Remington & Zolin, Forthcoming). Project complexity has been conceptualized by Remington and Pollock (2007) in terms of four major sources of complexity; temporal, directional, structural and technological complexity (See Figure 1). Temporal complexity exists when projects experience significant environmental change outside the direct influence or control of the project. The Global Economic Crisis of 2008 - 2009 is a good example of the type of environmental change that can make a project complex as, for example in the JSF project, where project managers attempt to respond to changes in interest rates, international currency exchange rates and commodity prices etc. Directional complexity exists in a project where stakeholders' goals are unclear or undefined, where progress is hindered by unknown political agendas, or where stakeholders disagree or misunderstand project goals. In the JSF project all the services and all non countries have to agree to the specifications of the three variants of the aircraft; Conventional Take Off and Landing (CTOL), Short Take Off/Vertical Landing (STOVL) and the Carrier Variant (CV). Because the Navy requires a plane that can take off and land on an aircraft carrier, that required a special variant of the aircraft design, adding complexity to the project. Technical complexity occurs in a project using technology that is immature or where design characteristics are unknown or untried. Developing a plane that can take off on a very short runway and land vertically created may highly interdependent technological challenges to correctly locate, direct and balance the lift fans, modulate the airflow and provide equivalent amount of thrust from the downward vectored rear exhaust to lift the aircraft and at the same time control engine temperatures. These technological challenges make costing and scheduling equally challenging. Structural complexity in a project comes from the sheer numbers of elements such as the number of people, teams or organizations involved, ambiguity regarding the elements, and the massive degree of interconnectedness between them. While Lockheed Martin is the prime contractor, they are assisted in major aspects of the JSF development by Northrop Grumman, BAE Systems, Pratt & Whitney and GE/Rolls-Royce Fighter Engineer Team and innumerable subcontractors. In addition to identifying opportunities to achieve project goals, complex projects also need to identify and exploit opportunities to increase agility in response to changing stakeholder demands or to reduce project risks. Complexity Leadership Theory contends that in complex environments adaptive and enabling leadership are needed (Uhl-Bien, Marion and McKelvey, 2007). Adaptive leadership facilitates creativity, learning and adaptability, while enabling leadership handles the conflicts that inevitably arise between adaptive leadership and traditional administrative leadership (Uhl-Bien and Marion, 2007). Hence, adaptive leadership involves the recognition and opportunities to adapt, while and enabling leadership involves the exploitation of these opportunities. Our research questions revolve around the type or source of complexity and its relationship to opportunity recognition and exploitation. For example, is it only external environmental complexity that creates the need for the entrepreneurial behaviours, such as opportunity recognition and opportunity exploitation? Do the internal dimensions of project complexity, such as technological and structural complexity, also create the need for opportunity recognition and opportunity exploitation? The Kropp, Zolin and Lindsay model (2009) describes a relationship between entrepreneurial orientation (EO), opportunity recognition (OR), and opportunity exploitation (OX) in complex projects, with environmental and organizational contextual variables as moderators. We extend their model by defining the affects of external complexity and internal complexity on OR and OX. ---------- Methodology/Key Propositions: When the environment complex EO is more likely to result in OR because project members will be actively looking for solutions to problems created by environmental change. But in projects that are technologically or structurally complex project leaders and members may try to make the minimum changes possible to reduce the risk of creating new problems due to delays or schedule changes. In projects with environmental or technological complexity project leaders who encourage the innovativeness dimension of EO will increase OR in complex projects. But projects with technical or structural complexity innovativeness will not necessarily result in the recognition and exploitation of opportunities due to the over-riding importance of maintaining stability in the highly intricate and interconnected project structure. We propose that in projects with environmental complexity creating the need for change and innovation project leaders, who are willing to accept and manage risk, are more likely to identify opportunities to increase project effectiveness and efficiency. In contrast in projects with internal complexity a much higher willingness to accept risk will be necessary to trigger opportunity recognition. In structurally complex projects we predict it will be less likely to find a relationship between risk taking and OP. When the environment is complex, and a project has autonomy, they will be motivated to execute opportunities to improve the project's performance. In contrast, when the project has high internal complexity, they will be more cautious in execution. When a project experiences high competitive aggressiveness and their environment is complex, project leaders will be motivated to execute opportunities to improve the project's performance. In contrast, when the project has high internal complexity, they will be more cautious in execution. This paper reports the first stage of a three year study into the behaviours of managers, leaders and team members of complex projects. We conduct a qualitative study involving a Group Discussion with experienced project leaders. The objective is to determine how leaders of large and potentially complex projects perceive that external and internal complexity will influence the affects of EO on OR. ---------- Results and Implications: These results will help identify and distinguish the impact of external and internal complexity on entrepreneurial behaviours in NPDP. Project managers will be better able to quickly decide how and when to respond to changes in the environment and internal project events.

Representation and learning of visual information for pose recognition

Recovering position from sensor information is an important problem in mobile robotics, known as localisation. Localisation requires a map or some other description of the environment to provide the robot with a context to interpret sensor data. The mobile robot system under discussion is using an artificial neural representation of position. Building a geometrical map of the environment with a single camera and artificial neural networks is difficult. Instead it would be simpler to learn position as a function of the visual input. Usually when learning images, an intermediate representation is employed. An appropriate starting point for biologically plausible image representation is the complex cells of the visual cortex, which have invariance properties that appear useful for localisation. The effectiveness for localisation of two different complex cell models are evaluated. Finally the ability of a simple neural network with single shot learning to recognise these representations and localise a robot is examined.

Fast and robust stereo object recognition for spheres

The paper presents a fast and robust stereo object recognition method. The method is currently unable to identify the rotation of objects. This makes it very good at locating spheres which are rotationally independent. Approximate methods for located non-spherical objects have been developed. Fundamental to the method is that the correspondence problem is solved using information about the dimensions of the object being located. This is in contrast to previous stereo object recognition systems where the scene is first reconstructed by point matching techniques. The method is suitable for real-time application on low-power devices.

Lip detection for audio-visual speech recognition in-car environment

Acoustically, car cabins are extremely noisy and as a consequence audio-only, in-car voice recognition systems perform poorly. As the visual modality is immune to acoustic noise, using the visual lip information from the driver is seen as a viable strategy in circumventing this problem by using audio visual automatic speech recognition (AVASR). However, implementing AVASR requires a system being able to accurately locate and track the drivers face and lip area in real-time. In this paper we present such an approach using the Viola-Jones algorithm. Using the AVICAR [1] in-car database, we show that the Viola- Jones approach is a suitable method of locating and tracking the driver’s lips despite the visual variability of illumination and head pose for audio-visual speech recognition system.

Bengali handwritten character recognition using modified syntactic method

Several approaches have been proposed to recognize handwritten Bengali characters using different curve fitting algorithms and curvature analysis. In this paper, a new algorithm (Curve-fitting Algorithm) to identify various strokes of a handwritten character is developed. The curve-fitting algorithm helps recognizing various strokes of different patterns (line, quadratic curve) precisely. This reduces the error elimination burden heavily. Implementation of this Modified Syntactic Method demonstrates significant improvement in the recognition of Bengali handwritten characters.

Audio visual automatic speech recognition in vehicles

Acoustically, car cabins are extremely noisy and as a consequence, existing audio-only speech recognition systems, for voice-based control of vehicle functions such as the GPS based navigator, perform poorly. Audio-only speech recognition systems fail to make use of the visual modality of speech (eg: lip movements). As the visual modality is immune to acoustic noise, utilising this visual information in conjunction with an audio only speech recognition system has the potential to improve the accuracy of the system. The field of recognising speech using both auditory and visual inputs is known as Audio Visual Speech Recognition (AVSR). Continuous research in AVASR field has been ongoing for the past twenty-five years with notable progress being made. However, the practical deployment of AVASR systems for use in a variety of real-world applications has not yet emerged. The main reason is due to most research to date neglecting to address variabilities in the visual domain such as illumination and viewpoint in the design of the visual front-end of the AVSR system. In this paper we present an AVASR system in a real-world car environment using the AVICAR database [1], which is publicly available in-car database and we show that the use of visual speech conjunction with the audio modality is a better approach to improve the robustness and effectiveness of voice-only recognition systems in car cabin environments.

Temporal-based support vector machines for facial expression recognition

When classifying a signal, ideally we want our classifier to trigger a large response when it encounters a positive example and have little to no response for all other examples. Unfortunately in practice this does not occur with responses fluctuating, often causing false alarms. There exists a myriad of reasons why this is the case, most notably not incorporating the dynamics of the signal into the classification. In facial expression recognition, this has been highlighted as one major research question. In this paper we present a novel technique which incorporates the dynamics of the signal which can produce a strong response when the peak expression is found and essentially suppresses all other responses as much as possible. We conducted preliminary experiments on the extended Cohn-Kanade (CK+) database which shows its benefits. The ability to automatically and accurately recognize facial expressions of drivers is highly relevant to the automobile. For example, the early recognition of “surprise” could indicate that an accident is about to occur; and various safeguards could immediately be deployed to avoid or minimize injury and damage. In this paper, we conducted initial experiments on the extended Cohn-Kanade (CK+) database which shows its benefits.

Speech recognition using ad-hoc microphone arrays

While close talking microphones give the best signal quality and produce the highest accuracy from current Automatic Speech Recognition (ASR) systems, the speech signal enhanced by microphone array has been shown to be an effective alternative in a noisy environment. The use of microphone arrays in contrast to close talking microphones alleviates the feeling of discomfort and distraction to the user. For this reason, microphone arrays are popular and have been used in a wide range of applications such as teleconferencing, hearing aids, speaker tracking, and as the front-end to speech recognition systems. With advances in sensor and sensor network technology, there is considerable potential for applications that employ ad-hoc networks of microphone-equipped devices collaboratively as a virtual microphone array. By allowing such devices to be distributed throughout the users’ environment, the microphone positions are no longer constrained to traditional fixed geometrical arrangements. This flexibility in the means of data acquisition allows different audio scenes to be captured to give a complete picture of the working environment. In such ad-hoc deployment of microphone sensors, however, the lack of information about the location of devices and active speakers poses technical challenges for array signal processing algorithms which must be addressed to allow deployment in real-world applications. While not an ad-hoc sensor network, conditions approaching this have in effect been imposed in recent National Institute of Standards and Technology (NIST) ASR evaluations on distant microphone recordings of meetings. The NIST evaluation data comes from multiple sites, each with different and often loosely specified distant microphone configurations. This research investigates how microphone array methods can be applied for ad-hoc microphone arrays. A particular focus is on devising methods that are robust to unknown microphone placements in order to improve the overall speech quality and recognition performance provided by the beamforming algorithms. In ad-hoc situations, microphone positions and likely source locations are not known and beamforming must be achieved blindly. There are two general approaches that can be employed to blindly estimate the steering vector for beamforming. The first is direct estimation without regard to the microphone and source locations. An alternative approach is instead to first determine the unknown microphone positions through array calibration methods and then to use the traditional geometrical formulation for the steering vector. Following these two major approaches investigated in this thesis, a novel clustered approach which includes clustering the microphones and selecting the clusters based on their proximity to the speaker is proposed. Novel experiments are conducted to demonstrate that the proposed method to automatically select clusters of microphones (ie, a subarray), closely located both to each other and to the desired speech source, may in fact provide a more robust speech enhancement and recognition than the full array could.

The effect of dialect mismatch on likelihood-maximising speech enhancement for noise-robust speech recognition

Traditional speech enhancement methods optimise signal-level criteria such as signal-to-noise ratio, but these approaches are sub-optimal for noise-robust speech recognition. Likelihood-maximising (LIMA) frameworks are an alternative that optimise parameters of enhancement algorithms based on state sequences generated for utterances with known transcriptions. Previous reports of LIMA frameworks have shown significant promise for improving speech recognition accuracies under additive background noise for a range of speech enhancement techniques. In this paper we discuss the drawbacks of the LIMA approach when multiple layers of acoustic mismatch are present – namely background noise and speaker accent. Experimentation using LIMA-based Mel-filterbank noise subtraction on American and Australian English in-car speech databases supports this discussion, demonstrating that inferior speech recognition performance occurs when a second layer of mismatch is seen during evaluation.

Towards improved speech recognition for resource poor languages

In recent times, the improved levels of accuracy obtained by Automatic Speech Recognition (ASR) technology has made it viable for use in a number of commercial products. Unfortunately, these types of applications are limited to only a few of the world’s languages, primarily because ASR development is reliant on the availability of large amounts of language specific resources. This motivates the need for techniques which reduce this language-specific, resource dependency. Ideally, these approaches should generalise across languages, thereby providing scope for rapid creation of ASR capabilities for resource poor languages. Cross Lingual ASR emerges as a means for addressing this need. Underpinning this approach is the observation that sound production is largely influenced by the physiological construction of the vocal tract, and accordingly, is human, and not language specific. As a result, a common inventory of sounds exists across languages; a property which is exploitable, as sounds from a resource poor, target language can be recognised using models trained on resource rich, source languages. One of the initial impediments to the commercial uptake of ASR technology was its fragility in more challenging environments, such as conversational telephone speech. Subsequent improvements in these environments has gained consumer confidence. Pragmatically, if cross lingual techniques are to considered a viable alternative when resources are limited, they need to perform under the same types of conditions. Accordingly, this thesis evaluates cross lingual techniques using two speech environments; clean read speech and conversational telephone speech. Languages used in evaluations are German, Mandarin, Japanese and Spanish. Results highlight that previously proposed approaches provide respectable results for simpler environments such as read speech, but degrade significantly when in the more taxing conversational environment. Two separate approaches for addressing this degradation are proposed. The first is based on deriving better target language lexical representation, in terms of the source language model set. The second, and ultimately more successful approach, focuses on improving the classification accuracy of context-dependent (CD) models, by catering for the adverse influence of languages specific phonotactic properties. Whilst the primary research goal in this thesis is directed towards improving cross lingual techniques, the catalyst for investigating its use was based on expressed interest from several organisations for an Indonesian ASR capability. In Indonesia alone, there are over 200 million speakers of some Malay variant, provides further impetus and commercial justification for speech related research on this language. Unfortunately, at the beginning of the candidature, limited research had been conducted on the Indonesian language in the field of speech science, and virtually no resources existed. This thesis details the investigative and development work dedicated towards obtaining an ASR system with a 10000 word recognition vocabulary for the Indonesian language.