Recognising audio-visual speech in vehicles using the AVICAR database

Interacting with technology within a vehicle environment using a voice interface can greatly reduce the effects of driver distraction. Most current approaches to this problem only utilise the audio signal, making them susceptible to acoustic noise. An obvious approach to circumvent this is to use the visual modality in addition. However, capturing, storing and distributing audio-visual data in a vehicle environment is very costly and difficult. One current dataset available for such research is the AVICAR [1] database. Unfortunately this database is largely unusable due to timing mismatch between the two streams and in addition, no protocol is available. We have overcome this problem by re-synchronising the streams on the phone-number portion of the dataset and established a protocol for further research. This paper presents the first audio-visual results on this dataset for speaker-independent speech recognition. We hope this will serve as a catalyst for future research in this area.

Speech recognition in adverse environments using lip information

The performance of automatic speech recognition systems deteriorates in the presence of noise. One known solution is to incorporate video information with an existing acoustic speech recognition system. We investigate the performance of the individual acoustic and visual sub-systems and then examine different ways in which the integration of the two systems may be performed. The system is to be implemented in real time on a Texas Instruments' TMS320C80 DSP.

Visual route recognition with a handful of bits

In this paper we use a sequence-based visual localization algorithm to reveal surprising answers to the question, how much visual information is actually needed to conduct effective navigation? The algorithm actively searches for the best local image matches within a sliding window of short route segments or 'sub-routes', and matches sub-routes by searching for coherent sequences of local image matches. In contract to many existing techniques, the technique requires no pre-training or camera parameter calibration. We compare the algorithm's performance to the state-of-the-art FAB-MAP 2.0 algorithm on a 70 km benchmark dataset. Performance matches or exceeds the state of the art feature-based localization technique using images as small as 4 pixels, fields of view reduced by a factor of 250, and pixel bit depths reduced to 2 bits. We present further results demonstrating the system localizing in an office environment with near 100% precision using two 7 bit Lego light sensors, as well as using 16 and 32 pixel images from a motorbike race and a mountain rally car stage. By demonstrating how little image information is required to achieve localization along a route, we hope to stimulate future 'low fidelity' approaches to visual navigation that complement probabilistic feature-based techniques.

Cross database training of audio-visual hidden Markov models for phone recognition

Speech recognition can be improved by using visual information in the form of lip movements of the speaker in addition to audio information. To date, state-of-the-art techniques for audio-visual speech recognition continue to use audio and visual data of the same database for training their models. In this paper, we present a new approach to make use of one modality of an external dataset in addition to a given audio-visual dataset. By so doing, it is possible to create more powerful models from other extensive audio-only databases and adapt them on our comparatively smaller multi-stream databases. Results show that the presented approach outperforms the widely adopted synchronous hidden Markov models (HMM) trained jointly on audio and visual data of a given audio-visual database for phone recognition by 29% relative. It also outperforms the external audio models trained on extensive external audio datasets and also internal audio models by 5.5% and 46% relative respectively. We also show that the proposed approach is beneficial in noisy environments where the audio source is affected by the environmental noise.

Channel selection in the short-time modulation domain for distant speech recognition

Automatic speech recognition from multiple distant micro- phones poses significant challenges because of noise and reverberations. The quality of speech acquisition may vary between microphones because of movements of speakers and channel distortions. This paper proposes a channel selection approach for selecting reliable channels based on selection criterion operating in the short-term modulation spectrum domain. The proposed approach quantifies the relative strength of speech from each microphone and speech obtained from beamforming modulations. The new technique is compared experimentally in the real reverb conditions in terms of perceptual evaluation of speech quality (PESQ) measures and word error rate (WER). Overall improvement in recognition rate is observed using delay-sum and superdirective beamformers compared to the case when the channel is selected randomly using circular microphone arrays.

Likelihood-maximising frameworks for enhanced in-car speech recognition

Speech recognition in car environments has been identified as a valuable means for reducing driver distraction when operating non-critical in-car systems. Likelihood-maximising (LIMA) frameworks optimise speech enhancement algorithms based on recognised state sequences rather than traditional signal-level criteria such as maximising signal-to-noise ratio. Previously presented LIMA frameworks require calibration utterances to generate optimised enhancement parameters which are used for all subsequent utterances. Sub-optimal recognition performance occurs in noise conditions which are significantly different from that present during the calibration session - a serious problem in rapidly changing noise environments. We propose a dialog-based design which allows regular optimisation iterations in order to track the changing noise conditions. Experiments using Mel-filterbank spectral subtraction are performed to determine the optimisation requirements for vehicular environments and show that minimal optimisation assists real-time operation with improved speech recognition accuracy. It is also shown that the proposed design is able to provide improved recognition performance over frameworks incorporating a calibration session.

Cascading appearance-based features for visual speaker verification

The cascading appearance-based (CAB) feature extraction technique has established itself as the state of the art in extracting dynamic visual speech features for speech recognition. In this paper, we will focus on investigating the effectiveness of this technique for the related speaker verification application. By investigating the speaker verification ability of each stage of the cascade we will demonstrate that the same steps taken to reduce static speaker and environmental information for the speech recognition application also provide similar improvements for speaker recognition. These results suggest that visual speaker recognition can improve considerable when conducted solely through a consideration of the dynamic speech information rather than the static appearance of the speaker's mouth region.

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.

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.

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.