Accurate speech recognition can provide a natural interface for human–computer interaction. Recognition rates of the modern speech recognition systems are highly dependent on background noise levels and a choice of acoustic feature extraction method can have a significant impact on system performance. This paper presents a robust speech recognition system based on a front-end motivated by human cochlear processing of audio signals. In the proposed front-end, cochlear behavior is first emulated by the filtering operations of the gammatone filterbank and subsequently by the Inner Hair cell (IHC) processing stage. Experimental results using a continuous density Hidden Markov Model (HMM) recognizer with the proposed Gammatone Hair Cell (GHC) coefficients are lower for clean speech conditions, but demonstrate significant improvement in performance in noisy conditions compared to standard Mel-Frequency Cepstral Coefficients (MFCC) baseline.

No abstract

A common reason for changing the chosen service provider is the users' perception of service. Quality of Experience (QoE) describes the end user's perception of service while using it. A frequent cause of QoE degradation is inadequate traffic routing, where, other than throughput, selected routes do not satisfy minimum network requirements for the given service or services. In order to enable QoE-driven routing, per traffic type defined routing criteria are required. Our goal was to obtain those criteria for relevant services of a telecom operator. For the purpose of identifying services of interest, we first provide short results of user traffic analysis within the telecom operator network. Next, our work presents testbed measurements which explore the impact of packet loss and delay on user QoE for video, voice, and management traffic. For video services, we investigated separately multicast delivery, unicast HTTP Live Streaming (HLS), and unicast Real Time Streaming Protocol (RTSP) traffic. Applying a threshold to QoE values, from the measured dependencies we extracted minimum network performance criteria for the investigated different types of traffic. Finally, we provide a comparison with results available in the literature on the topic.

No abstract

Although craft and home brewing have fueled the beer renaissance in the last decade, affordable, reliable, and simple sensing equipment for such breweries is limited. Thus, this manuscript is motivated by the improvement of the bottle-filling process in such settings with the objective of developing a liquid level sensor based on a novel application of the known optical phenomena of light refraction. Based on the different refraction indices of liquid and air (and critical angle based on Snell’s law), along with a novel LED light source positioning, a reliable liquid level sensor system was built with the aid of an embedded microcontroller. The used operating principle is general and can be used in applications other than the proposed one. The proposed method was extensively tested in a laboratory and limited production settings with a speed of 7 Hz using different liquids and container shapes. It was compared for accuracy to other sensing principles such as ultrasound, infrared, and time-of-flight. It demonstrated comparable or better performance with a height error ranging between −0.1534 mm in static conditions and 1.608 mm for realistic dynamic conditions and good repeatability on the production line with a 4.3 mm standard deviation of the mean.