Related papers: Context-Aware Dynamic Chunking for Streaming Tibet…

Long-context inference remains challenging for large language models due to attention dilution and out-of-distribution degradation. Context selection mitigates this limitation by attending to a subset of key-value cache entries, yet most…

Action chunking emerged as a pivotal technique in imitation learning, enabling policies to predict cohesive action sequences rather than single actions. Recently, this approach has expanded to reinforcement learning (RL), enhancing…

In this study, we present an innovative technique for speaker adaptation in order to improve the accuracy of segmentation with application to unit-selection Text-To-Speech (TTS) systems. Unlike conventional techniques for speaker…

End-to-end acoustic speech recognition has quickly gained widespread popularity and shows promising results in many studies. Specifically the joint transformer/CTC model provides very good performance in many tasks. However, under noisy and…

Recent techniques such as retrieval-augmented generation or chain-of-thought reasoning have led to longer contexts and increased inference costs. Context compression techniques can reduce these costs, but the most effective approaches…

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…

Effective token compression remains a critical challenge for scaling models to handle increasingly complex and diverse datasets. A novel mechanism based on contextual reinforcement is introduced, dynamically adjusting token importance…

In this pilot study, we propose a neuro-inspired approach that compresses temporal sequences into context-tagged chunks, where each tag represents a recurring structural unit or``community'' in the sequence. These tags are generated during…

We present a Transformer architecture for long-context language modeling that combines global attention with two biologically inspired components: chunked local attention and a gated FIFO memory mechanism. This unified attention block…

Bengali, despite being one of the most widely spoken languages globally, remains underrepresented in long form speech technology, particularly in systems addressing transcription and speaker attribution. We present frameworks for long form…

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…

This paper describes our speaker diarization system submitted to the Multi-channel Multi-party Meeting Transcription (M2MeT) challenge, where Mandarin meeting data were recorded in multi-channel format for diarization and automatic speech…

Recently, Transformers have gained significant popularity in image restoration tasks such as image super-resolution and denoising, owing to their superior performance. However, balancing performance and computational burden remains a…

Anomalous audio in speech recordings is often caused by speaker voice distortion, external noise, or even electric interferences. These obstacles have become a serious problem in some fields, such as high-quality music mixing and speech…

OpenAI Whisper is a family of robust Automatic Speech Recognition (ASR) models trained on 680,000 hours of audio. However, its encoder-decoder architecture, trained with a sequence-to-sequence objective, lacks native support for streaming…

Context-aware neural machine translation aims to use the document-level context to improve translation quality. However, not all words in the context are helpful. The irrelevant or trivial words may bring some noise and distract the model…

Connectionist Temporal Classification (CTC) is a widely used method for automatic speech recognition (ASR), renowned for its simplicity and computational efficiency. However, it often falls short in recognition performance. In this work, we…

Convolutional Neural Networks (CNNs) are effective models for reducing spectral variations and modeling spectral correlations in acoustic features for automatic speech recognition (ASR). Hybrid speech recognition systems incorporating CNNs…

Streaming voice conversion has become increasingly popular for its potential in real-time applications. The recently proposed DualVC 2 has achieved robust and high-quality streaming voice conversion with a latency of about 180ms.…

Temporal contexts among consecutive frames are far from being fully utilized in existing visual trackers. In this work, we present TCTrack, a comprehensive framework to fully exploit temporal contexts for aerial tracking. The temporal…