相关论文: Mutually-Constrained Monotonic Multihead Attention…

Forced alignment (FA) plays a key role in speech research through the automatic time alignment of speech signals with corresponding text transcriptions. Despite the move towards end-to-end architectures for speech technology, FA is still…

This paper focuses on the challenging crowd counting task. As large-scale variations often exist within crowd images, neither fixed-size convolution kernel of CNN nor fixed-size attention of recent vision transformers can well handle this…

In this paper, we introduce a method for fine-tuning Large Language Models (LLMs), inspired by Multi-Task learning in a federated manner. Our approach leverages the structure of each client's model and enables a learning scheme that…

Multimodal Emotion Recognition (MER) aims to automatically identify and understand human emotional states by integrating information from various modalities. However, the scarcity of annotated multimodal data significantly hinders the…

Multi-label image classification allows predicting a set of labels from a given image. Unlike multiclass classification, where only one label per image is assigned, such a setup is applicable for a broader range of applications. In this…

Applying large pre-trained speech models like Whisper has shown promise in reducing training costs for various speech tasks. However, integrating these models into streaming systems remains a challenge. This paper presents a novel…

Despite progress in end-to-end ASR, real-world domain mismatches still cause performance drops, which Test-Time Adaptation (TTA) aims to mitigate by adjusting models during inference. Recent work explores combining TTA with external…

This paper introduces the integration of language-specific bi-directional context into a speech large language model (SLLM) to improve multilingual continuous conversational automatic speech recognition (ASR). We propose a character-level…

Joint attention - the ability to purposefully coordinate attention with another agent, and mutually attend to the same thing -- is a critical component of human social cognition. In this paper, we ask whether joint attention can be useful…

In the field of multi-task reinforcement learning, the modular principle, which involves specializing functionalities into different modules and combining them appropriately, has been widely adopted as a promising approach to prevent the…

Speech recognition and speech synthesis models are typically trained separately, each with its own set of learning objectives, training data, and model parameters, resulting in two distinct large networks. We propose a parameter-efficient…

In this paper, we propose a novel multi-modal multi-task encoder-decoder pre-training framework (MMSpeech) for Mandarin automatic speech recognition (ASR), which employs both unlabeled speech and text data. The main difficulty in…

Significant progress has been made in the area of model-based reinforcement learning. State-of-the-art algorithms are now able to match the asymptotic performance of model-free methods while being significantly more data efficient. However,…

While aspect-based sentiment analysis (ABSA) has made substantial progress, challenges remain for low-resource languages, which are often overlooked in favour of English. Current cross-lingual ABSA approaches focus on limited, less complex…

In this work, we propose novel decoding algorithms to enable streaming automatic speech recognition (ASR) on unsegmented long-form recordings without voice activity detection (VAD), based on monotonic chunkwise attention (MoChA) with an…

Measuring performance of an automatic speech recognition (ASR) system without ground-truth could be beneficial in many scenarios, especially with data from unseen domains, where performance can be highly inconsistent. In conventional ASR…

End-to-end approaches for automatic speech recognition (ASR) benefit from directly modeling the probability of the word sequence given the input audio stream in a single neural network. However, compared to conventional ASR systems, these…

Multi-speaker automatic speech recognition (ASR) is crucial for many real-world applications, but it requires dedicated modeling techniques. Existing approaches can be divided into modular and end-to-end methods. Modular approaches separate…

With the surge of online meetings, it has become more critical than ever to provide high-quality speech audio and live captioning under various noise conditions. However, most monaural speech enhancement (SE) models introduce processing…

We propose a novel end-to-end multi-talker automatic speech recognition (ASR) framework that enables both multi-speaker (MS) ASR and target-speaker (TS) ASR. Our proposed model is trained in a fully end-to-end manner, incorporating speaker…