Related papers: Towards Unsupervised Speech Recognition and Synthe…
Generating high-quality speech efficiently remains a key challenge for generative models in speech synthesis. This paper introduces VQalAttent, a lightweight model designed to generate fake speech with tunable performance and…
Vector quantization approaches (VQ-VAE, VQ-GAN) learn discrete neural representations of images, but these representations are inherently position-dependent: codes are spatially arranged and contextually entangled, requiring autoregressive…
In most automatic speech recognition (ASR) systems, the audio signal is processed to produce a time series of sensor measurements (e.g., filterbank outputs). This time series encodes semantic information in a speaker-dependent way. An…
In this paper, we are interested in audio-visual speech separation given a single-channel audio recording as well as visual information (lips movements) associated with each speaker. We propose an unsupervised technique based on…
Recently, audio-visual speech enhancement has been tackled in the unsupervised settings based on variational auto-encoders (VAEs), where during training only clean data is used to train a generative model for speech, which at test time is…
We present a VAE architecture for encoding and generating high dimensional sequential data, such as video or audio. Our deep generative model learns a latent representation of the data which is split into a static and dynamic part, allowing…
Self-supervised audio representation learning offers an attractive alternative for obtaining generic audio embeddings, capable to be employed into various downstream tasks. Published approaches that consider both audio and words/tags…
Unsupervised representation learning for speech audios attained impressive performances for speech recognition tasks, particularly when annotated speech is limited. However, the unsupervised paradigm needs to be carefully designed and…
Recent studies have explored the use of deep generative models of speech spectra based of variational autoencoders (VAEs), combined with unsupervised noise models, to perform speech enhancement. These studies developed iterative algorithms…
In self-supervised learning, it is challenging to reduce the gap between the enhancement performance on the estimated and target speech signals with existed pre-tasks. In this paper, we propose a multi-task pre-training method to improve…
The process of reconstructing missing parts of speech audio from context is called speech in-painting. Human perception of speech is inherently multi-modal, involving both audio and visual (AV) cues. In this paper, we introduce and study a…
The representation learning of speech, without textual resources, is an area of significant interest for many low resource speech applications. In this paper, we describe an approach to self-supervised representation learning from raw audio…
Synthesizing realistic co-speech gestures is an important and yet unsolved problem for creating believable motions that can drive a humanoid robot to interact and communicate with human users. Such capability will improve the impressions of…
Unsupervised disentangled representation learning from the unlabelled audio data, and high fidelity audio generation have become two linchpins in the machine learning research fields. However, the representation learned from an unsupervised…
Recent advancements in Neural Audio Codec (NAC) models have inspired their use in various speech processing tasks, including speech enhancement (SE). In this work, we propose a novel, efficient SE approach by leveraging the pre-quantization…
State-of-the-art automatic speech recognition (ASR) systems struggle with the lack of data for rare accents. For sufficiently large datasets, neural engines tend to outshine statistical models in most natural language processing problems.…
We investigate segmenting and clustering speech into low-bitrate phone-like sequences without supervision. We specifically constrain pretrained self-supervised vector-quantized (VQ) neural networks so that blocks of contiguous feature…
Real-Time Magnetic resonance imaging (rtMRI) of the midsagittal plane of the mouth is of interest for speech production research. In this work, we focus on estimating utterance level rtMRI video from the spoken phoneme sequence. We obtain…
Learning compact and meaningful latent space representations has been shown to be very useful in generative modeling tasks for visual data. One particular example is applying Vector Quantization (VQ) in variational autoencoders (VQ-VAEs,…
Recent research has delved into speech enhancement (SE) approaches that leverage audio embeddings from pre-trained models, diverging from time-frequency masking or signal prediction techniques. This paper introduces an efficient and…