相关论文: Parameter-efficient Dysarthric Speech Recognition …

Dysarthric speech reconstruction (DSR) typically employs a cascaded system that combines automatic speech recognition (ASR) and sentence-level text-to-speech (TTS) to convert dysarthric speech into normally-prosodied speech. However,…

The objective of this work is to train noise-robust speaker embeddings adapted for speaker diarisation. Speaker embeddings play a crucial role in the performance of diarisation systems, but they often capture spurious information such as…

Most of the prior studies in the spatial \ac{DoA} domain focus on a single modality. However, humans use auditory and visual senses to detect the presence of sound sources. With this motivation, we propose to use neural networks with audio…

Disordered speech recognition is a highly challenging task. The underlying neuro-motor conditions of people with speech disorders, often compounded with co-occurring physical disabilities, lead to the difficulty in collecting large…

Automatic dysarthric speech detection can provide reliable and cost-effective computer-aided tools to assist the clinical diagnosis and management of dysarthria. In this paper we propose a novel automatic dysarthric speech detection…

Distant-microphone meeting transcription is a challenging task. State-of-the-art end-to-end speaker-attributed automatic speech recognition (SA-ASR) architectures lack a multichannel noise and reverberation reduction front-end, which limits…

Ear recognition is a contactless and unobtrusive biometric technique with applications across various domains. However, deploying high-performing ear recognition models on resource-constrained devices is challenging, limiting their…

Automatic recognition of disordered speech remains a highly challenging task to date. The underlying neuro-motor conditions, often compounded with co-occurring physical disabilities, lead to the difficulty in collecting large quantities of…

Recent advances in multilingual dependency parsing have brought the idea of a truly universal parser closer to reality. However, cross-language interference and restrained model capacity remain major obstacles. To address this, we propose a…

This work presents a broad study on the adaptation of neural network acoustic models by means of learning hidden unit contributions (LHUC) -- a method that linearly re-combines hidden units in a speaker- or environment-dependent manner…

Parameter-efficient transfer learning (PETL) methods have emerged as a solid alternative to the standard full fine-tuning approach. They only train a few extra parameters for each downstream task, without sacrificing performance and…

The joint training framework for speech enhancement and recognition methods have obtained quite good performances for robust end-to-end automatic speech recognition (ASR). However, these methods only utilize the enhanced feature as the…

Adapters are an efficient, composable alternative to full fine-tuning of pre-trained models and help scale the deployment of large ASR models to many tasks. In practice, a task ID is commonly prepended to the input during inference to route…

State-of-the-art parameter-efficient fine-tuning methods rely on introducing adapter modules between the layers of a pretrained language model. However, such modules are trained separately for each task and thus do not enable sharing…

We propose an end-to-end joint optimization framework of a multi-channel neural speech extraction and deep acoustic model without mel-filterbank (FBANK) extraction for overlapped speech recognition. First, based on a multi-channel…

Automatic speech recognition (ASR) for low-resource languages remains a challenge due to the scarcity of labeled training data. Parameter-efficient fine-tuning and text-only adaptation are two popular methods that have been used to address…

Dysarthric speech reconstruction (DSR) aims to convert dysarthric speech into comprehensible speech while maintaining the speaker's identity. Despite significant advancements, existing methods often struggle with low speech intelligibility…

Fine-tuning large pre-trained language models on various downstream tasks with whole parameters is prohibitively expensive. Hence, Parameter-efficient fine-tuning has attracted attention that only optimizes a few task-specific parameters…

Adapting pretrained language models to novel domains, such as clinical applications, traditionally involves retraining their entire set of parameters. Parameter-Efficient Fine-Tuning (PEFT) techniques for fine-tuning language models…

Meetings are a common activity in professional contexts, and it remains challenging to endow vocal assistants with advanced functionalities to facilitate meeting management. In this context, a task like active speaker detection can provide…