Related papers: Bridging the Granularity Gap for Acoustic Modeling
In this paper, we summarize recent progresses made in deep learning based acoustic models and the motivation and insights behind the surveyed techniques. We first discuss acoustic models that can effectively exploit variable-length…
The human brain distinguishes speech sounds by mapping acoustic signals into a latent perceptual space. This space can be estimated via multidimensional scaling (MDS), preserving the similarity structure in lower dimensions. However,…
It is promising to design a single model that can suppress various distortions and improve speech quality, i.e., universal speech enhancement (USE). Compared to supervised learning-based predictive methods, diffusion-based generative models…
End-to-end acoustic speech recognition has quickly gained widespread popularity and shows promising results in many studies. Specifically the joint transformer/CTC model provides very good performance in many tasks. However, under noisy and…
Most text-to-speech (TTS) methods use high-quality speech corpora recorded in a well-designed environment, incurring a high cost for data collection. To solve this problem, existing noise-robust TTS methods are intended to use noisy speech…
Diffusion models have recently attained significant interest within the community owing to their strong performance as generative models. Furthermore, its application to inverse problems have demonstrated state-of-the-art performance.…
In this work, we investigate application of generative speech enhancement to improve the robustness of ASR models in noisy and reverberant conditions. We employ a recently-proposed speech enhancement model based on Schr\"odinger bridge,…
Multilingual automatic speech recognition (ASR) systems mostly benefit low resource languages but suffer degradation in performance across several languages relative to their monolingual counterparts. Limited studies have focused on…
Neural front-ends represent a promising approach to feature extraction for automatic speech recognition (ASR) systems as they enable to learn specifically tailored features for different tasks. Yet, many of the existing techniques remain…
Approximately 1.2% of the world's population has impaired voice production. As a result, automatic dysphonic voice detection has attracted considerable academic and clinical interest. However, existing methods for automated voice assessment…
We propose a Perceiver-based sequence classifier to detect abnormalities in speech reflective of several neurological disorders. We combine this classifier with a Universal Speech Model (USM) that is trained (unsupervised) on 12 million…
Negative transfer in training of acoustic models for automatic speech recognition has been reported in several contexts such as domain change or speaker characteristics. This paper proposes a novel technique to overcome negative transfer by…
Diffusion models have recently shown promising results for difficult enhancement tasks such as the conditional and unconditional restoration of natural images and audio signals. In this work, we explore the possibility of leveraging a…
With the advance in self-supervised learning for audio and visual modalities, it has become possible to learn a robust audio-visual speech representation. This would be beneficial for improving the audio-visual speech recognition (AVSR)…
In-air acoustic imaging systems demand beamforming techniques that offer a high dynamic range and spatial resolution while also remaining robust. Conventional Delay-and-Sum (DAS) beamforming fails to meet these quality demands due to high…
Pre-trained language models (PLMs) are engineered to be robust in contextual understanding and exhibit outstanding performance in various natural language processing tasks. However, their considerable size incurs significant computational…
Diffusion models are a new class of generative models that have shown outstanding performance in image generation literature. As a consequence, studies have attempted to apply diffusion models to other tasks, such as speech enhancement. A…
Distant speech recognition is a challenge, particularly due to the corruption of speech signals by reverberation caused by large distances between the speaker and microphone. In order to cope with a wide range of reverberations in…
In this study we develop dimension-reduction techniques to accelerate diffusion model inference in the context of synthetic data generation. The idea is to integrate compressed sensing into diffusion models (hence, CSDM): First, compress…
Self-supervised learning (SSL) models have achieved considerable improvements in automatic speech recognition (ASR). In addition, ASR performance could be further improved if the model is dedicated to audio content information learning…