相关论文: Real-Time MRI Video synthesis from time aligned ph…

Accented automatic speech recognition (ASR) often degrades due to the limited availability of accented training data. Prior work has explored accent modeling in low-resource settings, but existing approaches typically require minutes to…

Audio-visual speech recognition (AVSR) system is thought to be one of the most promising solutions for robust speech recognition, especially in noisy environment. In this paper, we propose a novel multimodal attention based method for…

Recently, phase processing is attracting increasinginterest in speech enhancement community. Some researchersintegrate phase estimations module into speech enhancementmodels by using complex-valued short-time Fourier transform(STFT)…

End-to-end learning models using raw waveforms as input have shown superior performances in many audio recognition tasks. However, most model architectures are based on convolutional neural networks (CNN) which were mainly developed for…

Magnetic resonance imaging (MRI) enables 3-D imaging of anatomical structures. However, the acquisition of MR volumes with high spatial resolution leads to long scan times. To this end, we propose volumetric super-resolution forests (VSRF)…

A simplified speech recognition system that uses the maximum mutual information (MMI) criterion is considered. End-to-end training using gradient descent is suggested, similarly to the training of connectionist temporal classification…

We propose a first step toward multilingual end-to-end automatic speech recognition (ASR) by integrating knowledge about speech articulators. The key idea is to leverage a rich set of fundamental units that can be defined "universally"…

Referring Image Segmentation (RIS) aims to segment target objects expressed in natural language within a scene at the pixel level. Various recent RIS models have achieved state-of-the-art performance by generating contextual tokens to model…

Recently in statistical parametric speech synthesis, we proposed a continuous sinusoidal model (CSM) using continuous F0 (contF0) in combination with Maximum Voiced Frequency (MVF), which was successfully giving state-of-the-art vocoders…

In this paper, we aim to generate clean speech frame by frame from a live video stream and a noisy audio stream without relying on future inputs. To this end, we propose RT-LA-VocE, which completely re-designs every component of LA-VocE, a…

Speech-to-text alignment is a critical component of neural text to speech (TTS) models. Autoregressive TTS models typically use an attention mechanism to learn these alignments on-line, while non-autoregressive end to end TTS models rely on…

Recent progress in Spoken Language Modeling has shown that learning language directly from speech is feasible. Generating speech through a pipeline that operates at the text level typically loses nuances, intonations, and non-verbal…

Articulatory-to-acoustic (forward) mapping is a technique to predict speech using various articulatory acquisition techniques as input (e.g. ultrasound tongue imaging, MRI, lip video). The advantage of lip video is that it is easily…

Purpose: Different Magnetic resonance imaging (MRI) modalities of the same anatomical structure are required to present different pathological information from the physical level for diagnostic needs. However, it is often difficult to…

Recently, our proposed recurrent neural network (RNN) based all deep learning minimum variance distortionless response (ADL-MVDR) beamformer method yielded superior performance over the conventional MVDR by replacing the matrix inversion…

ASR has been shown to achieve great performance recently. However, most of them rely on massive paired data, which is not feasible for low-resource languages worldwide. This paper investigates how to learn directly from unpaired phone…

Video to sound generation aims to generate realistic and natural sound given a video input. However, previous video-to-sound generation methods can only generate a random or average timbre without any controls or specializations of the…

In this work, we describe a novel method of training an embedding-matching word-level connectionist temporal classification (CTC) automatic speech recognizer (ASR) such that it directly produces word start times and durations, required by…

Video-to-video moment retrieval (Vid2VidMR) is the task of localizing unseen events or moments in a target video using a query video. This task poses several challenges, such as the need for semantic frame-level alignment and modeling…

In this paper, we propose a novel approach to convert given speech audio to a photo-realistic speaking video of a specific person, where the output video has synchronized, realistic, and expressive rich body dynamics. We achieve this by…