Related papers: SENS-ASR: Semantic Embedding injection in Neural-t…

Previous work on emotion recognition demonstrated a synergistic effect of combining several modalities such as auditory, visual, and transcribed text to estimate the affective state of a speaker. Among these, the linguistic modality is…

Recent advances have demonstrated the potential of decoderonly large language models (LLMs) for automatic speech recognition (ASR). However, enabling streaming recognition within this framework remains a challenge. In this work, we propose…

This paper addresses the problem of automatic speech recognition (ASR) error detection and their use for improving spoken language understanding (SLU) systems. In this study, the SLU task consists in automatically extracting, from ASR…

Although modern automatic speech recognition (ASR) systems can achieve high performance, they may produce errors that weaken readers' experience and do harm to downstream tasks. To improve the accuracy and reliability of ASR hypotheses, we…

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…

Self-supervised learning (SSL) methods which learn representations of data without explicit supervision have gained popularity in speech-processing tasks, particularly for single-talker applications. However, these models often have…

In the present paper, an attempt is made to combine Mask-CTC and the triggered attention mechanism to construct a streaming end-to-end automatic speech recognition (ASR) system that provides high performance with low latency. The triggered…

Current ASR systems are mainly trained and evaluated at the utterance level. Long range cross utterance context can be incorporated. A key task is to derive a suitable compact representation of the most relevant history contexts. In…

As human-machine voice interfaces provide easy access to increasingly intelligent machines, many state-of-the-art automatic speech recognition (ASR) systems are proposed. However, commercial ASR systems usually have poor performance on…

Speech recognition on smart devices is challenging owing to the small memory footprint. Hence small size ASR models are desirable. With the use of popular transducer-based models, it has become possible to practically deploy streaming…

An inferior performance of the streaming automatic speech recognition models versus non-streaming model is frequently seen due to the absence of future context. In order to improve the performance of the streaming model and reduce the…

Non-autoregressive (NAR) modeling has gained more and more attention in speech processing. With recent state-of-the-art attention-based automatic speech recognition (ASR) structure, NAR can realize promising real-time factor (RTF)…

Automatic speech recognition (ASR) systems, increasingly prevalent in education, healthcare, employment, and mobile technology, face significant challenges in inclusivity, particularly for the 80 million-strong global community of people…

It's challenging to customize transducer-based automatic speech recognition (ASR) system with context information which is dynamic and unavailable during model training. In this work, we introduce a light-weight contextual spelling…

Automatic speech recognition (ASR) and speech translation (ST) can both use neural transducers as the model structure. It is thus possible to use a single transducer model to perform both tasks. In real-world applications, such joint ASR…

Compression artifacts from standard video codecs often degrade perceptual quality. We propose a lightweight, semantic-aware pre-processing framework that enhances perceptual fidelity by selectively addressing these distortions. Our method…

Alongside acoustic information, linguistic features based on speech transcripts have been proven useful in Speech Emotion Recognition (SER). However, due to the scarcity of emotion labelled data and the difficulty of recognizing emotional…

In this work, we propose a streaming AV-ASR system based on a hybrid connectionist temporal classification (CTC)/attention neural network architecture. The audio and the visual encoder neural networks are both based on the conformer…

Modern automatic speech recognition (ASR) model is required to accurately transcribe diverse speech signals (from different domains, languages, accents, etc) given the specific contextual information in various application scenarios.…

Recent studies find existing self-supervised speech encoders contain primarily acoustic rather than semantic information. As a result, pipelined supervised automatic speech recognition (ASR) to large language model (LLM) systems achieve…