相关论文: TrimTail: Low-Latency Streaming ASR with Simple bu…

It is very important to locate the short-circuit fault in a power system quickly and accurately. Electromagnetic time reversal (EMTR) has drawn increasing attention because of its clear physical background and excellent performance. This…

In this paper, a multilingual end-to-end framework, called as ATCSpeechNet, is proposed to tackle the issue of translating communication speech into human-readable text in air traffic control (ATC) systems. In the proposed framework, we…

In large-scale applications including medical imaging, collocation differential equation solvers, and estimation with differential privacy, the underlying linear inverse problem can be reformulated as a streaming problem. In theory, the…

In this paper, we propose a novel solution that can improve the quality of THz transmission with systematic random linear network coding (sRLNC) and a low-bitrate auxiliary channel. To minimize complexity of channel coding, we complement a…

Sparse plus Low-Rank $(\mathbf{S} + \mathbf{LR})$ decomposition of Large Language Models (LLMs) has emerged as a promising direction in model compression, aiming to decompose pre-trained model weights into a sum of sparse and low-rank…

The Streaming Unmixing and Recognition Transducer (SURT) model was proposed recently as an end-to-end approach for continuous, streaming, multi-talker speech recognition (ASR). Despite impressive results on multi-turn meetings, SURT has…

Applications such as cloud gaming, video streaming, telemetry, ML inference, and data transfer provide a better experience when data is released at the receiver with timing reflecting how the data enters the sender. In practice, network…

Activation sparsity is a promising approach for accelerating large language model (LLM) inference by reducing computation and memory movement. However, existing activation sparsity methods typically apply uniform sparsity across…

Transformers are slow to train on videos due to extremely large numbers of input tokens, even though many video tokens are repeated over time. Existing methods to remove such uninformative tokens either have significant overhead, negating…

Training on the Edge enables neural networks to learn continuously from new data after deployment on memory-constrained edge devices. Previous work is mostly concerned with reducing the number of model parameters which is only beneficial…

Vision-Language Models (VLMs) are increasingly deployed in real-world applications, but their high inference cost makes them vulnerable to resource consumption attacks. Prior attacks attempt to extend VLM output sequences by optimizing…

Automatic Speech Recognition (ASR) systems typically yield output in lexical form. However, humans prefer a written form output. To bridge this gap, ASR systems usually employ Inverse Text Normalization (ITN). In previous works, Weighted…

Conversational recommender systems (CRS) aim to provide the recommendation service via natural language conversations. To develop an effective CRS, high-quality CRS datasets are very crucial. However, existing CRS datasets suffer from the…

This paper introduces Interleaved Speech-Text Language Model (IST-LM) for zero-shot streaming Text-to-Speech (TTS). Unlike many previous approaches, IST-LM is directly trained on interleaved sequences of text and speech tokens with a fixed…

Security Operations Centers face massive, heterogeneous alert streams under minute-level service windows, creating the Alert Triage Latency Paradox: verbose reasoning chains ensure accuracy and compliance but incur prohibitive latency and…

Latency-critical speech applications (e.g., live transcription, voice commands, and real-time translation) demand low time-to-first-token (TTFT) and high transcription accuracy, particularly on resource-constrained edge devices.…

Automatic Lyrics Transcription (ALT) aims to recognize lyrics from singing voices, similar to Automatic Speech Recognition (ASR) for spoken language, but faces added complexity due to domain-specific properties of the singing voice. While…

We present a streaming, Transformer-based end-to-end automatic speech recognition (ASR) architecture which achieves efficient neural inference through compute cost amortization. Our architecture creates sparse computation pathways…

In this work, we propose a streaming AV-ASR system based on a hybrid connectionist temporal classification (CTC)/attention neural network architecture. The audio and the visual encoder neural networks are both based on the conformer…

Split learning (SL) is a promising approach for training artificial intelligence (AI) models, in which devices collaborate with a server to train an AI model in a distributed manner, based on a same fixed split point. However, due to the…