Incorporating formant cues into distributed speech recognition systems

The evolution of robust speech recognition systems that maintain a high level of recognition accuracy in difficult and dynamically-varying acoustical environments is becoming increasingly important as speech recognition technology becomes a more integral part of mobile applications. In distributed speech recognition (DSR) architecture the recogniser's front-end is located in the terminal and is connected over a data network to a remote back-end recognition server. The terminal performs the feature parameter extraction, or the front-end of the speech recognition system. These features are transmitted over a data channel to the remote back-end recogniser. DSR provides particular benefits for the applications of mobile devices such as improved recognition performance compared to using the voice channel and ubiquitous access from different networks with a guaranteed level of recognition performance. A feature extraction algorithm integrated into the DSR system is required to operate in real-time as well as with the lowest possible computational costs.

Distributed Speech Recognition (DSR) systems rely on efficient transmission of speech information from distributed clients to a centralized server. Wireless or network communication channels within DSR systems are typically noisy and bursty. Thus, DSR systems must utilize efficient Error Recovery (ER) schemes during transmission of speech information. Some ER strategies, referred to as forward error control (FEC), aim to create redundancy in the source coded bitstream to overcome the effect of channel errors, while others are designed to create spread or delay in the feature stream in order to overcome the effect of bursty channel errors. Furthermore, ER strategies may be designed as a combination of the previously described techniques. This chapter presents an array of error recovery techniques for remote speech recognition applications. This chapter is organized as follows. First, channel characterization and modeling are discussed. Next, media-specific FEC is presented for packet erasure applications, followed by a discussion on media-independent FEC techniques for bit error applications, including general linear block codes, cyclic codes, and convolutional codes. The application of unequal error protection (UEP) strategies utilizing combinations of the aforementioned FEC methods is also presented. Finally, framebased interleaving is discussed as an alternative to overcoming the effect of bursty channel erasures. The chapter concludes with examples of modern standards for channel coding strategies for distributed speech recognition (DSR). 8.1. Distributed Speech Recognition Systems Throughout this chapter various error recovery and detection techniques are discussed. It is therefore necessary to present an overview of a complete experimental DSR system, including feature extraction, a noisy channel model, and an automatic speech recognition engine at the server end (Fig. 8.1). 2 Bengt J. Borgstrom, Alexis Bernard, and Abeer Alwan Feature Extraction Source Coding Channel Coding Channel Decoding Source Decoding Speech Recognition Client Server Noisy Channel input speech

Combined speech enhancement and auditory modelling for robust distributed speech recognition

European standardisation, a key institution for the functioning of the EU single market, functions at the crossroads of private rule-making and public policy. Recently, it has been subjected to fierce scrutiny by the European Commission and the European Court of Justice. Expressed concerns relate to the legal value of standards and the legitimacy of institutions creating them but have broader implications for European competitiveness, highlighting the strategic role of standards. By far much of this critique has been directed towards the European Telecommunications Standards Institute (ETSI), the EU’s crown jewel of technology standardisation. ETSI’s normative power manifests itself in policymaking, legislation and market processes, rendering it an interesting organisation to study as a proxy to understand the legitimacy and resilience of European standardisation. Against this backdrop, this introduction sets the theoretical and legal context for this Special Issue. Upon discussing the background and dynamic of European standardisation, it provides a theoretical framework for ‘crises' and ‘legitimacy’, tailoring it to the particular case of ETSI and the challenges it faces at the policy and judicial level. Lastly, it provides a critical reflection on the Research Articles in this Special Issue, linking them to the current discourses on legitimacy and resilience.

Modern speech recognition applications are heading towards embedded systems and hand-held devices. Distributed Speech Recognition (DSR) system architecture emerged to address this kind of applications. Most of the existing implementations of this system are presented in software fashion, with little consideration to the end product platform in which the system will be deployed. In this paper, an optimized hardware implementation of the front end part of the DSR specified in the basic ETSI Aurora standard ETSI ES 201 108 is presented in FPGA platform prototype, with consideration of migration to structured ASIC in case of mass-production. Main design issues and tips are highlighted. Results are presented in terms of hardware resources utilization, comparison of some basic system components to third party reference designs and compliance to the Aurora standard.

SummaryThe distributed nature of wireless mesh networks (WMNs) allows them to benefit from multiple autonomic functionalities. However, the existing landscape of self‐x solutions (eg, self‐configuration) is fragmented and the lack of a standardized framework through which interoperable autonomics can be developed has been hampering adoption and deployment of autonomics in real‐world service networks. There is a need for a standardized architectural framework that enables to comprehensively support and integrate interoperable components for autonomicity in WMNs. Such an architecture (autonomicity‐enabled wireless mesh architecture) is currently being standardized by the working group called Evolution of Management towards Autonomic Future Internet (AFI) in the European Telecommunications Standards Institute within the Network Technologies Technical Committee. The proposed autonomic wireless mesh architecture is an instantiation of the AFI GANA (Generic Autonomic Network Architecture) reference model, a standards‐based approach to autonomics. This paper complements and extends the early version of the architecture by further detailing the architectural principles and providing experimental and validation results. First, we provide a brief overview of the AFI GANA reference model and then show how each of its building blocks can be instantiated for WMNs. We evaluate the proposed architecture by implementing and testing the 4 basic self‐x functionalities defined by the GANA model. The provided guidelines can now help researchers and engineers build autonomicity‐enabled WMNs using a standardized framework that enables adoption and deployment of autonomics by industry, thereby enabling researchers and engineers to contribute to the further evolution of the standard in the European Telecommunications Standards Institute.

The second-generation digital video broadcasting via satellite (DVB-S2) and the second-generation DVB interactive satellite system (DVB-RCS2) standards published by European Telecommunications Standards Institute (ETSI) have been dominating the global high-throughput satellite (HTS) communications market for recent five years. ETSI provisioned a technical report (TR) ETSI TR 101 545-4 as rudimentary guidelines for implementing a DVB-S2/DVB-RCS2 satellite system with security functions. Based on the ETSI guidelines, this paper depicts security implementations for a scenario of several distributed hub gateway stations which was unincorporated in the TR. Moreover, several optimizations and modifications were made to improve correctness and efficiency. A top-level star network security architecture, a hub security architecture, a return channel satellite terminal (RCST) security architecture, encrypted frame structures, authentication, and key distribution are described in this paper. The test results shew a less than 9% payload data rate decrease for the given security system in comparison to the unencrypted, proving the same speed performance level as the insecure commercial HTS ground infrastructure.

The background to, analysis and specification of a standard generic interface for the configuration of services on main telephone switching elements are described. This includes the specification of services on analog, integrated services digital network (ISDN), and Centrex lines. An emerging international standard - the European Telecommunications Standards Institute, Customer Administration Model - is employed. >

After the initial grants of patents, contracts, industry customs and standards are adopted voluntarily by the market participants and they function as self-regulating or governing instruments to coordinate fragmentations caused by territorial rights. The activities of the standard-setting organizations (SSOs) that set standards for the use of the standard essential patents (SEPs) are one such example of self-regulation. Often, while the patent rights are local, SSOs are organizations often with multiple and heterogeneous participants. The guidelines and other soft law policies that SSOs voluntarily adopt are often likely to reflect such multi-territorial nature of SSOs’ participants. When a dispute arises on the conditions that are set by SSOs over the assertion of SEPs, the problem would be likely to include factual considerations that arise across territories. As such, disputes surrounding SEPs force local courts to consider not only local judicial standards and doctrines, but also those used elsewhere that may be relevant to understanding complex facts of disputes. This chapter discusses such tendency of the courts in the interpretation of a particular licensing principle of ‘fair, reasonable and non-discriminatory’ (FRAND) adopted by an European SSO, the European Telecommunications Standards Institute (ETSI), in Chinese courts. The chapter explores in detail the dispute surrounding SEPs between Huawei and InterDigital in China, and analyses it in the context of similar cases surrounding SEPs and FRANDs elsewhere. We argue that there seems to be a judicial globalization, where courts use of foreign-developed principles in judging local disputes with global commercial impacts, resulting from self-regulation, and that the Chinese court cases may be understood in the same vein. We conclude by arguing that this may be a next phase in the development of Chinese IP law, where the local practices of governance have to be built after the initial norms transplant.

In this paper, we will outline the current European development of wireless communications to support cooperative Intelligent Transport Systems (ITS). The focus will be on spectrum allocation and the physical and medium access control layers of the ITS-G5 access technology, which is under specification by the European Telecommunications Standards Institute (ETSI). The European ITS architecture and European standardization will also be briefly discussed.

WITHDRAWN: Ultra-secure transmissions for 5G-V2X communications

The broadband integrated services digital network (BISDN) will become the ubiquitous network of the future, which will be required to support a wide range and complex set of services to the end user. In order for a network operator to provide a full service network to all its customers it will be necessary to provide the full range of broadband ISDN services to end users connected to the broadband local exchange (BLE) via a broadband access network (BAN) which will replace part or the whole of the local line distribution network. To ensure that the full range of services can be delivered by the BAN to the end users in a consistent and correct manner, the Council of the European Commission (CEC) have given the European Telecommunications Standards Institute (ETSI) a mandate to define an ATM (i.e. cell) based interface between the BAN and BLE which will be called Vb5. The ETSI have produced a technical requirement which will form the framework for the detailed specification of Vb5. Vb5 shall be capable of supporting narrowband services, symmetrical and asymmetric broadband services and broadcast services. The paper describes the major capabilities and features of the Vb5 interface by focusing on the general architecture, service architecture, protocol stack and BAN/BLE configurations. The paper recommends that the narrowband stepping stones of V5.1 and V5.2 are progressively rolled out into the network to lay the foundations for the support of Vb5 and to build operational experience in the support of V5 interfaces. (12 pages)

Communications-on-the-move (COTM) is becoming an indispensable feature for next generation satellites. Many commercial and government based satellite communications programs are including support for terminal mobility as a key feature. Adding COTM capabilities to regenerative (non-transponded) satellite systems, such as layer-2 and layer-3 switching satellites impacts the satellite system, network and protocol architecture and design. The unique challenges and complications arising from supporting COTM capabilities can impact all segments of a satellite communications program, including ground stations, satellites, and terminals. In this paper, we examine the key aspects associated with implementing mobile satellite services (MSS) for next generation regenerative satellites which were originally designed to support fixed satellite services (FSS). We identify common challenges that arise when architecting a mobile regenerative satellite communications system and show methods to successfully address them. In particular, we focus on the SPACEWAY satellite system and show how COTM can be supported through enhancement to the baseline architecture. SPACEWAY was originally designed to support commercial fixed satellite service. SPACEWAY implements the European Telecommunications Standards Institute (ETSI) Regenerative Satellite Mesh-A (RSM-A) air interface standard and complies with the ETSI Broadband Satellite Multimedia (BSM) Satellite Independent Service Access Point (SI-SAP). This will serve as a blueprint for standards based RSM-A systems and the concepts can be extended to other non-standards based regenerative satellite systems as well.

This paper examines the impact of Vehicle-to-Everything (V2X) communications on vehicle cooperation, focusing on increasing the robustness and feasibility of Cooperative, Connected, and Automated Vehicles (CCAVs). V2X communications enable CCAVs to obtain a holistic environmental perception, facilitating informed decision making regarding their trajectory. This technological innovation is essential to mitigate accidents resulting from inadequate or absent communication on the roads. As the importance of vehicle cooperation grows, the European Telecommunications Standards Institute (ETSI) has been standardizing messages and services for V2X communications, in order to improve the synchronization of CCAVs actions. In this context, this preliminary work explores the use of Maneuver Coordination Messages (MCMs), under standardization by ETSI, for cooperative path planning. This work presents a novel approach by implementing these messages as well as the associated Maneuver Coordination Service (MCS) with a Cooperative Driving System to process maneuver coordination. Additionally, a trajectory approach is introduced along with a message generation mechanism and a process to dynamically handle collisions. This was implemented in an Artery V2X simulation framework combining both network communications and SUMO traffic simulations. The obtained results demonstrate the effectiveness of using V2X communications to ensure the safety and efficiency of Cooperative Intelligent Transportation Systems (C-ITS).

New cellular networks like 5G and 6G put novel methods and technologies forth which sustainably change the mobile communication domain. Edge cloud computing is one of these emerging technologies providing computational resources at the edge of the network in closer proximity to end users. It promises significantly reduced network latencies, better load balancing, and more precise optimizations through information about the states of the access networks provided by the cloud infrastructure, e.g., radio conditions, location information, and others. The European Telecommunications Standards Institute (ETSI) has summarized and standardized the requirements for a multi-access edge computing (MEC) architecture as basis for future implementations. Among others, the standard defines a large number of interfaces between the various components and to the environment. It also formulates security requirements for these interfaces. However, the implementation details are usually left to the platform operators. In this paper, we present an in-depth analysis of the privacy properties of these interfaces and point out several potential privacy vulnerabilities. We describe three possible attacks that exploit these vulnerabilities. For our analysis, we use a simulative edge computing sandbox environment that has been developed by ETSI to investigate the interfaces. As a conclusion, we formulate recommendations on how data protection requirements can be met in future MEC implementations.