相关论文: Improving Streaming Speech Recognition With Time-S…

In this paper, we present DuTongChuan, a novel context-aware translation model for simultaneous interpreting. This model allows to constantly read streaming text from the Automatic Speech Recognition (ASR) model and simultaneously determine…

Retrieval-Augmented Generation (RAG) has significantly advanced large language models (LLMs) by grounding their outputs in external tools and knowledge sources. However, existing RAG systems are typically constrained to static, single-turn…

While speech recognition Word Error Rate (WER) has reached human parity for English, long-form dictation scenarios still suffer from segmentation and punctuation problems resulting from irregular pausing patterns or slow speakers.…

Dialogue act recognition is a fundamental task for an intelligent dialogue system. Previous work models the whole dialog to predict dialog acts, which may bring the noise from unrelated sentences. In this work, we design a hierarchical…

Diffusion Language Models (DLMs) have recently achieved significant success due to their any-order generation capabilities. However, existing inference methods typically rely on local, immediate-step metrics such as confidence or entropy…

Rare word recognition can be improved by adapting ASR models to synthetic data that includes these words. Further improvements can be achieved through contextual biasing, which trains and adds a biasing module into the model architecture to…

Attention mechanism has been used as an ancillary means to help RNN or CNN. However, the Transformer (Vaswani et al., 2017) recently recorded the state-of-the-art performance in machine translation with a dramatic reduction in training time…

This paper delves into the challenging task of Active Speaker Detection (ASD), where the system needs to determine in real-time whether a person is speaking or not in a series of video frames. While previous works have made significant…

In this paper, we explore the benefits of incorporating context into a Recurrent Neural Network (RNN-T) based Automatic Speech Recognition (ASR) model to improve the speech recognition for virtual assistants. Specifically, we use meta…

MEGA is a recent transformer-based architecture, which utilizes a linear recurrent operator whose parallel computation, based on the FFT, scales as $O(LlogL)$, with $L$ being the sequence length. We build upon their approach by replacing…

This work investigates bidirectional Mamba (BiMamba) for unified streaming and non-streaming automatic speech recognition (ASR). Dynamic chunk size training enables a single model for offline decoding and streaming decoding with various…

Autoregressive Transformers adopted in Large Language Models (LLMs) are hard to scale to long sequences. Despite several works trying to reduce their computational cost, most of LLMs still adopt attention layers between all pairs of tokens…

Softmax attention struggles with long contexts due to structural limitations: the strict sum-to-one constraint forces attention sinks on irrelevant tokens, and probability mass disperses as sequence lengths increase. We tackle these…

The current research focus on Content-Based Video Retrieval requires higher-level video representation describing the long-range semantic dependencies of relevant incidents, events, etc. However, existing methods commonly process the frames…

Recently, there has been an increasing interest in end-to-end speech recognition that directly transcribes speech to text without any predefined alignments. One approach is the attention-based encoder-decoder framework that learns a mapping…

The use of channel-wise attention in CNN based speaker representation networks has achieved remarkable performance in speaker verification (SV). But these approaches do simple averaging on time and frequency feature maps before channel-wise…

This paper proposes a self-regularised minimum latency training (SR-MLT) method for streaming Transformer-based automatic speech recognition (ASR) systems. In previous works, latency was optimised by truncating the online attention weights…

Distributed LLM serving systems optimize per-request latency and throughput. However, under long-context workloads, inference accuracy becomes more variable. When incorrect responses trigger retries, accuracy directly translates into…

Streaming video recognition reasons about objects and their actions in every frame of a video. A good streaming recognition model captures both long-term dynamics and short-term changes of video. Unfortunately, in most existing methods, the…

Mispronunciation detection and diagnosis (MDD) is a popular research focus in computer-aided pronunciation training (CAPT) systems. End-to-end (e2e) approaches are becoming dominant in MDD. However an e2e MDD model usually requires entire…