Related papers: Distributed Asynchronous Device Speech Enhancement…
Teleconferencing is becoming essential during the COVID-19 pandemic. However, in real-world applications, speech quality can deteriorate due to, for example, background interference, noise, or reverberation. To solve this problem, target…
Audio and visual signals typically occur simultaneously, and humans possess an innate ability to correlate and synchronize information from these two modalities. Recently, a challenging problem known as Audio-Visual Segmentation (AVS) has…
We propose a cross-attention Transformer for joint decoding of uplink OFDM signals received by multiple coordinated access points. A shared per-receiver encoder learns the time-frequency structure of each grid, and a token-wise…
This paper presents the Crossmodal Attentive Skill Learner (CASL), integrated with the recently-introduced Asynchronous Advantage Option-Critic (A2OC) architecture [Harb et al., 2017] to enable hierarchical reinforcement learning across…
The human brain can easily focus on one speaker and suppress others in scenarios such as a cocktail party. Recently, researchers found that auditory attention can be decoded from the electroencephalogram (EEG) data. However, most existing…
End-to-end speech recognition has become popular in recent years, since it can integrate the acoustic, pronunciation and language models into a single neural network. Among end-to-end approaches, attention-based methods have emerged as…
Machine comprehension is a representative task of natural language understanding. Typically, we are given context paragraph and the objective is to answer a question that depends on the context. Such a problem requires to model the complex…
Automatic speech recognition (ASR) of single channel far-field recordings with an unknown number of speakers is traditionally tackled by cascaded modules. Recent research shows that end-to-end (E2E) multi-speaker ASR models can achieve…
Classroom discourse is an essential vehicle through which teaching and learning take place. Assessing different characteristics of discursive practices and linking them to student learning achievement enhances the understanding of teaching…
In this paper, we propose an online attention mechanism, known as cumulative attention (CA), for streaming Transformer-based automatic speech recognition (ASR). Inspired by monotonic chunkwise attention (MoChA) and head-synchronous…
Multimedia recommendation systems leverage user-item interactions and multimodal information to capture user preferences, enabling more accurate and personalized recommendations. Despite notable advancements, existing approaches still face…
Automatic Speaker Verification (ASV) technology has become commonplace in virtual assistants. However, its performance suffers when there is a mismatch between the train and test domains. Mixed bandwidth training, i.e., pooling training…
Attention within windows has been widely explored in vision transformers to balance the performance, computation complexity, and memory footprint. However, current models adopt a hand-crafted fixed-size window design, which restricts their…
This paper investigates four types of cross-utterance speech contexts modeling approaches for streaming and non-streaming Conformer-Transformer (C-T) ASR systems: i) input audio feature concatenation; ii) cross-utterance Encoder embedding…
Distributed Complex Event Processing has emerged as a well-established paradigm to detect situations of interest from basic sensor streams, building an operator graph between sensors and applications. In order to detect event patterns that…
A one-shot algorithm called iterationless DANSE (iDANSE) is introduced to perform distributed adaptive node-specific signal estimation (DANSE) in a fully connected wireless acoustic sensor network (WASN) deployed in an environment with…
Speech classification tasks often require powerful language understanding models to grasp useful features, which becomes problematic when limited training data is available. To attain superior classification performance, we propose to…
Sparse attention, which selectively attends to a subset of tokens in the context was supposed to be efficient. However, its theoretical reduction in FLOPs has rarely translated into wall-clock speed-up over its dense attention counterparts…
Recent studies indicate that hierarchical Vision Transformer with a macro architecture of interleaved non-overlapped window-based self-attention \& shifted-window operation is able to achieve state-of-the-art performance in various visual…
The goal of this work is to develop a meeting transcription system that can recognize speech even when utterances of different speakers are overlapped. While speech overlaps have been regarded as a major obstacle in accurately transcribing…