Related papers: Learning Hidden Unit Contributions for Unsupervise…

In this paper, we study a novel technique that exploits the interaction between speaker traits and linguistic content to improve both speaker verification and utterance verification performance. We implement an idea of speaker-utterance…

Thanks to the latest deep learning algorithms, silent speech interfaces (SSI) are now able to synthesize intelligible speech from articulatory movement data under certain conditions. However, the resulting models are rather…

Collecting sufficient labeled data for spoken language understanding (SLU) is expensive and time-consuming. Recent studies achieved promising results by using pre-trained models in low-resource scenarios. Inspired by this, we aim to ask:…

When there is a mismatch between the training and test domains, current speech recognition systems show significant performance degradation. Self-training methods, such as noisy student teacher training, can help address this and enable the…

In the realm of spoken language understanding (SLU), numerous natural language understanding (NLU) methodologies have been adapted by supplying large language models (LLMs) with transcribed speech instead of conventional written text. In…

Spoken language understanding (SLU) systems extract transcriptions, as well as semantics of intent or named entities from speech, and are essential components of voice activated systems. SLU models, which either directly extract semantics…

Speech representations learned in a self-supervised fashion from massive unlabeled speech corpora have been adapted successfully toward several downstream tasks. However, such representations may be skewed toward canonical data…

The attenuation of acoustic loudspeaker echoes remains to be one of the open challenges to achieve pleasant full-duplex hands free speech communication. In many modern signal enhancement interfaces, this problem is addressed by a linear…

An utterance-level speaker embedding is typically obtained by aggregating a sequence of frame-level representations. However, in real-world scenarios, individual frames encode not only speaker-relevant information but also various nuisance…

In general, the performance of automatic speech recognition (ASR) systems is significantly degraded due to the mismatch between training and test environments. Recently, a deep-learning-based image-to-image translation technique to…

Automatic speaker verification systems are vulnerable to a variety of access threats, prompting research into the formulation of effective spoofing detection systems to act as a gate to filter out such spoofing attacks. This study…

Visual Speech Recognition (VSR) aims to infer speech into text depending on lip movements alone. As it focuses on visual information to model the speech, its performance is inherently sensitive to personal lip appearances and movements, and…

Spoken Language Understanding (SLU) is composed of two subtasks: intent detection (ID) and slot filling (SF). There are two lines of research on SLU. One jointly tackles these two subtasks to improve their prediction accuracy, and the other…

Attention-based sequence-to-sequence models for automatic speech recognition jointly train an acoustic model, language model, and alignment mechanism. Thus, the language model component is only trained on transcribed audio-text pairs. This…

Recent advancements in audio-aware large language models (ALLMs) enable them to process and understand audio inputs. However, these models often hallucinate non-existent sound events, reducing their reliability in real-world applications.…

LLM-based automatic speech recognition models demonstrate strong performance by connecting audio encoders and LLMs. However, data scarcity of paired speech and transcription often hinders their adaptation to new domains, making text-only…

Speech distortions are a long-standing problem that degrades the performance of supervisely trained speech processing models. It is high time that we enhance the robustness of speech processing models to obtain good performance when…

Despite the rapid progress of automatic speech recognition (ASR) technologies in the past few decades, recognition of disordered speech remains a highly challenging task to date. Disordered speech presents a wide spectrum of challenges to…

Compensation for channel mismatch and noise interference is essential for robust automatic speech recognition. Enhanced speech has been introduced into the multi-condition training of acoustic models to improve their generalization ability.…

The majority of existing Unsupervised Domain Adaptation (UDA) methods presumes source and target domain data to be simultaneously available during training. Such an assumption may not hold in practice, as source data is often inaccessible…