Related papers: Dialog act guided contextual adapter for personali…
While end-to-end (E2E) automatic speech recognition (ASR) models excel at general transcription, they struggle to recognize rare or unseen named entities (e.g., contact names, locations), which are critical for downstream applications like…
This study investigates the performance of personalized automatic speech recognition (ASR) for recognizing disordered speech using small amounts of per-speaker adaptation data. We trained personalized models for 195 individuals with…
The prevalence of the powerful multilingual models, such as Whisper, has significantly advanced the researches on speech recognition. However, these models often struggle with handling the code-switching setting, which is essential in…
The usage of automatic speech recognition (ASR) systems are becoming omnipresent ranging from personal assistant to chatbots, home, and industrial automation systems, etc. Modern robots are also equipped with ASR capabilities for…
Self-supervised learning models have revolutionized the field of speech processing. However, the process of fine-tuning these models on downstream tasks requires substantial computational resources, particularly when dealing with multiple…
Dialogue systems have many applications such as customer support or question answering. Typically they have been limited to shallow single turn interactions. However more advanced applications such as career coaching or planning a trip…
When applying parameter-efficient finetuning via LoRA onto speaker adaptive text-to-speech models, adaptation performance may decline compared to full-finetuned counterparts, especially for out-of-domain speakers. Here, we propose…
Despite the success of deep learning in speech recognition, multi-dialect speech recognition remains a difficult problem. Although dialect-specific acoustic models are known to perform well in general, they are not easy to maintain when…
Automatic Speech Recognition (ASR) has witnessed a profound research interest. Recent breakthroughs have given ASR systems different prospects such as faithfully transcribing spoken language, which is a pivotal advancement in building…
This paper addresses end-to-end automatic speech recognition (ASR) for long audio recordings such as lecture and conversational speeches. Most end-to-end ASR models are designed to recognize independent utterances, but contextual…
Adapting an automatic speech recognition (ASR) system to unseen noise environments is crucial. Integrating adapters into neural networks has emerged as a potent technique for transfer learning. This study thoroughly investigates…
We propose a novel preference alignment framework for improving spoken dialogue models on real-time conversations from user interactions. Current preference learning methods primarily focus on text-based language models, and are not…
Personalizing automatic speech recognition (ASR) systems for non-normative speech, such as dysarthric and aphasic speech, is challenging. While speaker-specific fine-tuning (SS-FT) is widely used, it is typically initialized directly from a…
End-to-end autonomous driving has great potential in the transportation industry. However, the lack of transparency and interpretability of the automatic decision-making process hinders its industrial adoption in practice. There have been…
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…
Interactions with virtual assistants typically start with a predefined trigger phrase followed by the user command. To make interactions with the assistant more intuitive, we explore whether it is feasible to drop the requirement that users…
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…
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…
Running automatic speech recognition (ASR) on edge devices is non-trivial due to resource constraints, especially in scenarios that require supporting multiple languages. We propose a new approach to enable multilingual speech recognition…
Contextual ASR or hotword customization holds substantial practical value. Despite the impressive performance of current end-to-end (E2E) automatic speech recognition (ASR) systems, they often face challenges in accurately recognizing rare…