相关论文: Visual Speech Recognition for Languages with Limit…

Automatic speech recognition (ASR) is crucial for human-machine interaction in diverse applications like conversational agents, industrial robotics, call center automation, and automated subtitling. However, developing high-performance ASR…

Streaming end-to-end automatic speech recognition (ASR) models are widely used on smart speakers and on-device applications. Since these models are expected to transcribe speech with minimal latency, they are constrained to be causal with…

Automatic speech recognition (ASR) has been widely researched with supervised approaches, while many low-resourced languages lack audio-text aligned data, and supervised methods cannot be applied on them. In this work, we propose a…

We show for the first time that learning powerful representations from speech audio alone followed by fine-tuning on transcribed speech can outperform the best semi-supervised methods while being conceptually simpler. wav2vec 2.0 masks the…

Multi-media communications facilitate global interaction among people. However, despite researchers exploring cross-lingual translation techniques such as machine translation and audio speech translation to overcome language barriers, there…

The speech representations learned from large-scale unlabeled data have shown better generalizability than those from supervised learning and thus attract a lot of interest to be applied for various downstream tasks. In this paper, we…

Spoken language understanding (SLU) treats automatic speech recognition (ASR) and natural language understanding (NLU) as a unified task and usually suffers from data scarcity. We exploit an ASR and NLU joint training method based on meta…

Whispering is a ubiquitous mode of communication that humans use daily. Despite this, whispered speech has been poorly served by existing speech technology due to a shortage of resources and processing methodology. To remedy this, this…

Self-supervised learning (SSL) has made significant advances in speech representation learning. Models like wav2vec 2.0 and HuBERT have achieved state-of-the-art results in tasks such as speech recognition, particularly in monolingual…

Multilingual end-to-end(E2E) models have shown a great potential in the expansion of the language coverage in the realm of automatic speech recognition(ASR). In this paper, we aim to enhance the multilingual ASR performance in two ways,…

Few-shot learning is a promising way for reducing the label cost in new categories adaptation with the guidance of a small, well labeled support set. But for few-shot semantic segmentation, the pixel-level annotations of support images are…

Speaker identification systems in a real-world scenario are tasked to identify a speaker amongst a set of enrolled speakers given just a few samples for each enrolled speaker. This paper demonstrates the effectiveness of meta-learning and…

The goal of this paper is to learn robust speaker representation for bilingual speaking scenario. The majority of the world's population speak at least two languages; however, most speaker recognition systems fail to recognise the same…

Large language models (LLMs) have driven substantial advances in speech language models (SpeechLMs), yielding strong performance in automatic speech recognition (ASR) under high-resource conditions. However, existing benchmarks…

There is growing interest in models that can learn from unlabelled speech paired with visual context. This setting is relevant for low-resource speech processing, robotics, and human language acquisition research. Here we study how a…

Building robust and generic object detection frameworks requires scaling to larger label spaces and bigger training datasets. However, it is prohibitively costly to acquire annotations for thousands of categories at a large scale. We…

The evolution of speech technology has been spurred by the rapid increase in dataset sizes. Traditional speech models generally depend on a large amount of labeled training data, which is scarce for low-resource languages. This paper…

Performance in Speech Emotion Recognition (SER) on a single language has increased greatly in the last few years thanks to the use of deep learning techniques. However, cross-lingual SER remains a challenge in real-world applications due to…

For conversational large-vocabulary continuous speech recognition (LVCSR) tasks, up to about two thousand hours of audio is commonly used to train state of the art models. Collection of labeled conversational audio however, is prohibitively…

Audio-visual speech recognition (AVSR) provides a promising solution to ameliorate the noise-robustness of audio-only speech recognition with visual information. However, most existing efforts still focus on audio modality to improve…