Related papers: Integration of Frame- and Label-synchronous Beam S…

Beam search decoding is the de-facto method for decoding auto-regressive Neural Machine Translation (NMT) models, including multilingual NMT where the target language is specified as an input. However, decoding multilingual NMT models…

Recently, large-scale visual language pre-trained (VLP) models have demonstrated impressive performance across various downstream tasks. Motivated by these advancements, pioneering efforts have emerged in multi-label image recognition with…

Disfluency detection has mainly been solved in a pipeline approach, as post-processing of speech recognition. In this study, we propose Transformer-based encoder-decoder models that jointly solve speech recognition and disfluency detection,…

Beam search is a go-to strategy for decoding neural sequence models. The algorithm can naturally be viewed as a subset optimization problem, albeit one where the corresponding set function does not reflect interactions between candidates.…

Recent mask proposal models have significantly improved the performance of zero-shot semantic segmentation. However, the use of a `background' embedding during training in these methods is problematic as the resulting model tends to…

This work proposes a frame-wise online/streaming end-to-end neural diarization (EEND) method, which detects speaker activities in a frame-in-frame-out fashion. The proposed model mainly consists of a causal embedding encoder and an online…

We present a systematic analysis on the performance of a phonetic recogniser when the window of input features is not symmetric with respect to the current frame. The recogniser is based on Context Dependent Deep Neural Networks (CD-DNNs)…

We adapt the well-known beam-search algorithm for machine translation to operate in a cascaded real-time speech translation system. This proved to be more complex than initially anticipated, due to four key challenges: (1) real-time…

State-of-the-art audio captioning methods typically use the encoder-decoder structure with pretrained audio neural networks (PANNs) as encoders for feature extraction. However, the convolution operation used in PANNs is limited in capturing…

In-context learning enables language models (LM) to adapt to downstream data or tasks by incorporating few samples as demonstrations within the prompts. It offers strong performance without the expense of fine-tuning. However, the…

Autonomous driving vehicles and robotic systems rely on accurate perception of their surroundings. Scene understanding is one of the crucial components of perception modules. Among all available sensors, LiDARs are one of the essential…

We describe in this report our audio scene recognition system submitted to the DCASE 2016 challenge. Firstly, given the label set of the scenes, a label tree is automatically constructed. This category taxonomy is then used in the feature…

Beam search is widely used for approximate decoding in structured prediction problems. Models often use a beam at test time but ignore its existence at train time, and therefore do not explicitly learn how to use the beam. We develop an…

The attention-based Transformer model has achieved promising results for speech recognition (SR) in the offline mode. However, in the streaming mode, the Transformer model usually incurs significant latency to maintain its recognition…

By incorporating additional contextual information, deep biasing methods have emerged as a promising solution for speech recognition of personalized words. However, for real-world voice assistants, always biasing on such personalized words…

Neural audio coding has shown very promising results recently in the literature to largely outperform traditional codecs but limited attention has been paid on its error resilience. Neural codecs trained considering only source coding tend…

In this paper, we propose a multi-label classification framework to detect multiple speaking styles in a speech sample. Unlike previous studies that have primarily focused on identifying a single target style, our framework effectively…

Sequence generative models with RNN variants, such as LSTM, GRU, show promising performance on abstractive document summarization. However, they still have some issues that limit their performance, especially while deal-ing with long…

Multi-label image classification is a prediction task that aims to identify more than one label from a given image. This paper considers the semantic consistency of the latent space between the visual patch and linguistic label domains and…

Modern systems for automatic speech recognition, including the RNN-Transducer and Attention-based Encoder-Decoder (AED), are designed so that the encoder is not required to alter the time-position of information from the audio sequence into…