相关论文: Training Articulatory Inversion Models for Intersp…

Building a persona-based conversation agent is challenging owing to the lack of large amounts of speaker-specific conversation data for model training. This paper addresses the problem by proposing a multi-task learning approach to training…

Speaker-Attributed Automatic Speech Recognition (SAA) enhances traditional ASR systems by incorporating relative speaker identity tags directly into the transcript (e.g., [Speaker 1]:, [Speaker 2]:). In this work, we extend the capabilities…

Nowadays, training end-to-end neural models for spoken language translation (SLT) still has to confront with extreme data scarcity conditions. The existing SLT parallel corpora are indeed orders of magnitude smaller than those available for…

Audio and speech self-supervised encoder models are now widely used for a lot of different tasks. Many of these models are often trained on clean segmented speech content such as LibriSpeech. In this paper, we look into how the pretraining…

Spoken language understanding (SLU) system usually consists of various pipeline components, where each component heavily relies on the results of its upstream ones. For example, Intent detection (ID), and slot filling (SF) require its…

The performance of deep learning models depends significantly on their capacity to encode input features efficiently and decode them into meaningful outputs. Better input and output representation has the potential to boost models'…

Accent conversion aims to convert the accent of a source speech to a target accent, meanwhile preserving the speaker's identity. This paper introduces a novel non-autoregressive framework for accent conversion that learns accent-agnostic…

Self-supervised learning (SSL) methods have proven to be very successful in automatic speech recognition (ASR). These great improvements have been reported mostly based on highly curated datasets such as LibriSpeech for non-streaming…

Recent advances in large language models (LLMs) have attracted significant interest in extending their capabilities to multimodal scenarios, particularly for speech-to-speech conversational systems. However, existing multimodal models…

One-shot style transfer is a challenging task, since training on one utterance makes model extremely easy to over-fit to training data and causes low speaker similarity and lack of expressiveness. In this paper, we build on the…

Recently, adapting the idea of self-supervised learning (SSL) on continuous speech has started gaining attention. SSL models pre-trained on a huge amount of unlabeled audio can generate general-purpose representations that benefit a wide…

Speech therapy is essential for rehabilitating speech disorders caused by neurological impairments such as stroke. However, traditional manual and computer-assisted systems are limited in real-time accessibility and articulatory motion…

This paper investigates the in-context learning abilities of the Whisper automatic speech recognition (ASR) models released by OpenAI. A novel speech-based in-context learning (SICL) approach is proposed for test-time adaptation, which can…

Most organisms including humans function by coordinating and integrating sensory signals with motor actions to survive and accomplish desired tasks. Learning these complex sensorimotor mappings proceeds simultaneously and often in an…

This paper introduces a novel application of Test-Time Training (TTT) for Speech Enhancement, addressing the challenges posed by unpredictable noise conditions and domain shifts. This method combines a main speech enhancement task with a…

In real-life applications, the performance of speaker recognition systems always degrades when there is a mismatch between training and evaluation data. Many domain adaptation methods have been successfully used for eliminating the domain…

Speech foundation models have achieved state-of-the-art (SoTA) performance across various tasks, such as automatic speech recognition (ASR) in hundreds of languages. However, multi-speaker ASR remains a challenging task for these models due…

Multilingual audio-text retrieval (ML-ATR) is a challenging task that aims to retrieve audio clips or multilingual texts from databases. However, existing ML-ATR schemes suffer from inconsistencies for instance similarity matching across…

The viability of an Augmentative and Alternative Communication device often depends on its ability to adapt to an individual user's unique abilities. Though human input can be noisy, there is often structure to our errors. For example,…

Joint optimization of multi-channel front-end and automatic speech recognition (ASR) has attracted much interest. While promising results have been reported for various tasks, past studies on its meeting transcription application were…