相关论文: From Oracle to Noisy Context: Mitigating Contextua…

Compared with automatic speech recognition (ASR), the human auditory system is more adept at handling noise-adverse situations, including environmental noise and channel distortion. To mimic this adeptness, auditory models have been widely…

While word error rates of automatic speech recognition (ASR) systems have consistently fallen, natural language understanding (NLU) applications built on top of ASR systems still attribute significant numbers of failures to low-quality…

Contextual information plays a crucial role in speech recognition technologies and incorporating it into the end-to-end speech recognition models has drawn immense interest recently. However, previous deep bias methods lacked explicit…

Attention-based contextual biasing approaches have shown significant improvements in the recognition of generic and/or personal rare-words in End-to-End Automatic Speech Recognition (E2E ASR) systems like neural transducers. These…

Speaker Diarization (SD) is a crucial component of modern end-to-end ASR pipelines. Traditional SD systems, which are typically audio-based and operate independently of ASR, often introduce speaker errors, particularly during speaker…

Automatic speech recognition (ASR) models make fewer errors when more surrounding speech information is presented as context. Unfortunately, acquiring a larger future context leads to higher latency. There exists an inevitable trade-off…

Speaker-attributed automatic speech recognition (ASR) in multi-speaker environments remains a significant challenge, particularly when systems conditioned on speaker embeddings fail to generalize to unseen speakers. In this work, we propose…

The recognition of rare named entities, such as personal names and terminologies, is challenging for automatic speech recognition (ASR) systems, especially when they are not frequently observed in the training data. In this paper, we…

An ongoing challenge in current natural language processing is how its major advancements tend to disproportionately favor resource-rich languages, leaving a significant number of under-resourced languages behind. Due to the lack of…

In a pipeline speech translation system, automatic speech recognition (ASR) system will transmit errors in recognition to the downstream machine translation (MT) system. A standard machine translation system is usually trained on parallel…

As speech recognition model sizes and training data requirements grow, it is increasingly common for systems to only be available via APIs from online service providers rather than having direct access to models themselves. In this scenario…

A crucial part of an accurate and reliable spoken language assessment system is the underlying ASR model. Recently, large-scale pre-trained ASR foundation models such as Whisper have been made available. As the output of these models is…

Contextualized end-to-end automatic speech recognition has been an active research area, with recent efforts focusing on the implicit learning of contextual phrases based on the final loss objective. However, these approaches ignore the…

We propose a novel approach to end-to-end automatic speech recognition (ASR) to achieve efficient speech in-context learning (SICL) for (i) long-form speech decoding, (ii) test-time speaker adaptation, and (iii) test-time contextual…

Leveraging context information is an intuitive idea to improve performance on conversational automatic speech recognition(ASR). Previous works usually adopt recognized hypotheses of historical utterances as preceding context, which may bias…

We present a first large-scale public synthetic dataset for contextual spellchecking customization of automatic speech recognition (ASR) with focus on diverse rare and out-of-vocabulary (OOV) phrases, such as proper names or terms. The…

New-age conversational agent systems perform both speech emotion recognition (SER) and automatic speech recognition (ASR) using two separate and often independent approaches for real-world application in noisy environments. In this paper,…

While Automatic Speech Recognition (ASR) is typically benchmarked by word error rate (WER), real-world applications ultimately hinge on semantic fidelity. This mismatch is particularly problematic for dysarthric speech, where articulatory…

We develop a large language model (LLM) based automatic speech recognition (ASR) system that can be contextualized by providing keywords as prior information in text prompts. We adopt decoder-only architecture and use our in-house LLM,…

The development of resource-constrained approaches to automatic speech recognition (ASR) is of great interest due to its broad applicability to many low-resource languages for which there is scant usable data. Existing approaches to many…