Related papers: A Compact End-to-End Model with Local and Global C…

To join the advantages of classical and end-to-end approaches for speech recognition, we present a simple, novel and competitive approach for phoneme-based neural transducer modeling. Different alignment label topologies are compared and…

A key challenge in continuous sign language recognition (CSLR) is to efficiently capture long-range spatial interactions over time from the video input. To address this challenge, we propose TCNet, a hybrid network that effectively models…

In this work, we present a hybrid CTC/Attention model based on a ResNet-18 and Convolution-augmented transformer (Conformer), that can be trained in an end-to-end manner. In particular, the audio and visual encoders learn to extract…

Task-oriented Dialogue Systems (TODS) often face the challenge of encountering new intents. New Intent Discovery (NID) is a crucial task that aims to identify these novel intents while maintaining the capability to recognize existing ones.…

Effective extraction and application of linguistic features are central to the enhancement of spoken Language IDentification (LID) performance. With the success of recent large models, such as GPT and Whisper, the potential to leverage such…

End-to-end autonomous driving systems built on Vision Language Models (VLMs) have shown significant promise, yet their reliance on autoregressive architectures introduces some limitations for real-world applications. The sequential,…

The goal of this work is to synchronise audio and video of a talking face using deep neural network models. Existing works have trained networks on proxy tasks such as cross-modal similarity learning, and then computed similarities between…

This paper presents our modeling and architecture approaches for building a highly accurate low-latency language identification system to support multilingual spoken queries for voice assistants. A common approach to solve multilingual…

Speech foundation models have recently demonstrated the ability to perform Speech In-Context Learning (SICL). Selecting effective in-context examples is crucial for SICL performance, yet selection methodologies remain underexplored. In this…

This paper presents a novel streaming end-to-end target-speaker speech recognition that addresses two critical limitations in systems: the handling of noisy enrollment utterances and specific enrollment phrase requirements. This paper…

This work focuses on improving the Spoken Language Identification (LangId) system for a challenge that focuses on developing robust language identification systems that are reliable for non-standard, accented (Singaporean accent),…

Voice recognition and speaker identification are vital for applications in security and personal assistants. This paper presents a lightweight 1D-Convolutional Neural Network (1D-CNN) designed to perform speaker identification on minimal…

Large language models run every token through every layer, regardless of difficulty. We present TIDE, a post-training system that attaches tiny learned routers at periodic checkpoint layers and, at inference time, selects the earliest layer…

Streaming processing of speech audio is required for many contemporary practical speech recognition tasks. Even with the large corpora of manually transcribed speech data available today, it is impossible for such corpora to cover…

We investigate training end-to-end speech recognition models with the recurrent neural network transducer (RNN-T): a streaming, all-neural, sequence-to-sequence architecture which jointly learns acoustic and language model components from…

Robots that follow natural-language instructions often either plan at a high level using hand-designed interfaces or rely on large end-to-end models that are difficult to deploy for real-time control. We propose TeNet (Text-to-Network), a…

Driven by the evolution toward 6G and AI-native edge intelligence, network operations increasingly require predictive and risk-aware adaptation under stringent computation and latency constraints. Network Traffic Matrix (TM), which…

Scene text spotting aims to detect and recognize text in real-world images, where instances are often short, fragmented, or visually ambiguous. Existing methods primarily rely on visual cues and implicitly capture local character…

This paper describes an end-to-end (E2E) neural architecture for the audio rendering of small portions of display content on low resource personal computing devices. It is intended to address the problem of accessibility for vision-impaired…

In this paper we proposed an end-to-end short utterances speech language identification(SLD) approach based on a Long Short Term Memory (LSTM) neural network which is special suitable for SLD application in intelligent vehicles. Features…