Related papers: Softwire Hub and Spoke Deployment Framework with L…

We introduce Glinthawk, an architecture for offline Large Language Model (LLM) inference. By leveraging a two-tiered structure, Glinthawk optimizes the utilization of the high-end accelerators ("Tier 1") by offloading the attention…

This paper introduces Typhoon 2, a series of text and multimodal large language models optimized for the Thai language. The series includes models for text, vision, and audio. Typhoon2-Text builds on state-of-the-art open models, such as…

To fulfill two integral aims of abating cellular traffic and enhancing efficiency of cellular network, D2D is considered as a novel channel of communication. This form of communication has introduced for 4th cellular communication and…

We introduce a text-to-speech(TTS) framework based on a neural transducer. We use discretized semantic tokens acquired from wav2vec2.0 embeddings, which makes it easy to adopt a neural transducer for the TTS framework enjoying its monotonic…

Centralized Virtual Private Networks (VPNs) when used in distributed systems have performance constraints as all traffic must traverse through a central server. In recent years, there has been a paradigm shift towards the use of P2P in VPNs…

Empathetic interaction is a cornerstone of human-machine communication, due to the need for understanding speech enriched with paralinguistic cues and generating emotional and expressive responses. However, the most powerful empathetic…

We introduce StableLM 2 1.6B, the first in a new generation of our language model series. In this technical report, we present in detail the data and training procedure leading to the base and instruction-tuned versions of StableLM 2 1.6B.…

This paper introduces a cross-lingual dubbing system that translates speech from one language to another while preserving key characteristics such as duration, speaker identity, and speaking speed. Despite the strong translation quality of…

Device-to-device (D2D) communication is one of the most recent advancements in wireless communication technology. It was introduced in cellular communication technology by the 3rd Generation Partnership Project (3GPP) to lay a foundation…

Switching connectivity over multiple wireless interfaces of a mobile node is essential when performing handover between heterogeneous networks. In such a communication scenario, session continuity as experienced by the user can be enhanced…

In many real-world OpenFlow-based SDN deployments, the ability to program heterogeneous forwarding elements built with different forwarding architectures is a desirable capability. In this paper, we discuss a data plane programming…

This paper explores the design and development of a language-based interface for dynamic mission programming of autonomous underwater vehicles (AUVs). The proposed `Word2Wave' (W2W) framework enables interactive programming and parameter…

Lightweight Tunnels (LWTs) in the Linux kernel enable efficient per-route tunneling and are widely used by protocols such as In Situ Operations, Administration, and Maintenance (IOAM), Segment Routing over IPv6 (SRv6), and Routing Protocol…

This paper proposes a model that integrates sub-band processing and deep filtering to fully exploit information from the target time-frequency (TF) bin and its surrounding TF bins for single-channel speech enhancement. The sub-band module…

We consider the problem of performing Spoken Language Understanding (SLU) on small devices typical of IoT applications. Our contributions are twofold. First, we outline the design of an embedded, private-by-design SLU system and show that…

A recent line of research on spoken language assessment (SLA) employs neural models such as BERT and wav2vec 2.0 (W2V) to evaluate speaking proficiency across linguistic and acoustic modalities. Although both models effectively capture…

The increasing proliferation of Internet of Things (IoT) devices has created a growing need for more efficient communication networks, especially in areas where continuous connectivity is unstable or unavailable. Opportunistic networks have…

To scale neural speech synthesis to various real-world languages, we present a multilingual end-to-end framework that maps byte inputs to spectrograms, thus allowing arbitrary input scripts. Besides strong results on 40+ languages, the…

In the recent years, many solutions for Vehicle to Vehicle (V2V) communication were proposed to overcome failure problems (also known as dead ends). This paper proposes a novel framework for V2V failure recovery using Device-to-Device (D2D)…

Autonomous driving is usually recognized as a promising technology to replace human drivers in the near future. To guarantee the safety performance in the daily life scenario, multiple-car intelligence with high quality inter-vehicle…