Robust indoor speaker recognition in a network of audio and video sensors ☆
- a Visionlab, ISSS, Heriot Watt University, Edinburgh EH14 4AS, UK
- b University of Edinburgh, Edinburgh EH9 3JG, UK
- Received 4 October 2015, Revised 26 April 2016, Accepted 28 April 2016, Available online 4 June 2016
Joint audio–video system to recognise a speaker in acoustic/visual clutter noise proposed.
Audio–video signals are combined at low and higher-level of data abstraction.
Audio–video signals are combined to detect, track and recognise speaker.
Cooperative audio–video data lead to a robust tracking system in a realistic scenario.
Required hardware is less complex and scenario less constrained than other approaches.
Situational awareness is achieved naturally by the human senses of sight and hearing in combination. Automatic scene understanding aims at replicating this human ability using microphones and cameras in cooperation. In this paper, audio and video signals are fused and integrated at different levels of semantic abstractions. We detect and track a speaker who is relatively unconstrained, i.e., free to move indoors within an area larger than the comparable reported work, which is usually limited to round table meetings. The system is relatively simple: consisting of just 4 microphone pairs and a single camera. Results show that the overall multimodal tracker is more reliable than single modality systems, tolerating large occlusions and cross-talk. System evaluation is performed on both single and multi-modality tracking. The performance improvement given by the audio–video integration and fusion is quantified in terms of tracking precision and accuracy as well as speaker diarisation error rate and precision–recall (recognition). Improvements vs. the closest works are evaluated: 56% sound source localisation computational cost over an audio only system, 8% speaker diarisation error rate over an audio only speaker recognition unit and 36% on the precision–recall metric over an audio–video dominant speaker recognition method.
- Speaker diarisation;
- Security biometric;
- Audio–video speaker tracking;
- Multimodal fusion
The establishment of the digital era has created applications which combine audio and video to automate human activity analysis and understanding. We highlight the main areas of interest. First, for surveillance applications, i.e., detecting a person's biometric features to ensure that there are no intruders in a restricted area . Second, understanding people social behaviour and interaction to determine their “role” and their intentions . Third, detecting a possible threat in a public place  and, consequently, beam-forming and segmenting a dialogue . Typical surveillance scenarios are characterised by the use of many wide area, distributed sensors covering unconstrained scenarios. Scene monitoring is often required to be real-time, thus computationally inexpensive algorithms are fundamental to the development of an effective system, but this is not always evident in the literature at present, and this is the challenge we address in this work.
1.1. Related work
The first step to full audio–video (AV) human activity analysis and understanding systems is detecting and tracking speakers through significant occlusions. State-of-the-art sound source localisation algorithms  and  are still computationally expensive, hence they are not suitable for “real-time” (or frame-rate) applications. Solving large video occlusions is still an inherently challenging research problem: many existing papers solve the problem by using advanced multi-camera 3-dimensional (3D) systems  which are prone to error when the camera views do not overlap. They are computationally expensive, requiring GPU/FPGA implementations to function at frame-rate when parallelisation is possible. Complementary use of audio and video is able to compensate for noisy, missing and erroneous data, reducing the number of sensors and the computational resources required at the expense of minimal effort in integrating or fusing signals , , , , , , , , , , , , , , ,  and .
Audio and video fusion can be achieved in several ways chiefly using variations of sampling techniques , , ,  and . Existing AV person tracking system architectures work well only in highly sanitised, i.e., constrained and predictable scenarios: principally meeting rooms and diarisation , ,  and  in which the person motion is either stationary, e.g., when people are talking seated around a fixed table. Existing systems use large sensor networks in which microphones and cameras are often very close or even attached to people , ,  and . A hierarchical system is more likely to achieve robust situational awareness. These are more robust, as accurate and require lower algorithmic and hardware complexity  and . The weakness is that such systems often treat the two signals as if they were derived from truly independent processes: assuming one source of noise can affect only one kind of signal. None of the previous work explores whether an underlying relation between audio and video exists and seeks to exploit it fully.
AV event or anomaly detection literature is generally based on inferring AV signal correlations to recognise whether a relevant event has happened in some scenario of interest , ,  and . The same correlation approach may be used to pick out the dominant speaker from a group of speaking people, without audio beamforming, filtering, blind source separation and data association  and . The definition of dominant speaker is clearly useful: a high degree of gesticulation and speaking activity are the fundamental cues to define dominance , ,  and . In fact, gesturing is 80–90% of the time associated to speaking activity . Focussing on gesticulation detection is particularly suitable for low resolution video, where fine lip motion detection is not applicable and where close microphones may not be available.
To aid the reader, a schematic is shown in Fig. 1 and links to the different sections of the papers are explicitly made in the caption. Section 2 presents the integration of audio and video data at the signal level and their fusion at decision level for speaker detection and tracking (see ). A speaker voice recognition unit is implemented to make the multimodal tracking robust to occlusions (see also ). In Section 3, the experiments and the results related to the first part of the system are described. Here, the benefits of fusing multimodal data are highlighted remarking that standalone trackers have worse performances than the AV solution. Then, a possible solution to the problem of tracking the current speaker identity through occlusions by recognising speakers voices is demonstrated. Section 4 presents how to visualise in large indoor surveillance-like scenarios the dominant speaker identity when multiple people speak contemporaneously without resorting to sophisticated algorithms (see also ). Finally, in Section 5 the conclusions of this research study are highlighted and future avenues of research enumerated.