Related papers: Integration of TensorFlow based Acoustic Model wit…

Industrial soft sensing is crucial for accurate process monitoring through reliable inference of dominant sensor variables. However, developing effective data-driven soft sensor models presents challenges, such as achieving domain…

Tree tensor networks (TTNs) offer powerful models for image classification. While these TTN image classifiers already show excellent performance on classical hardware, embedding them into quantum neural networks (QNNs) may further improve…

Voice interfaces are becoming accepted widely as input methods for a diverse set of devices. This development is driven by rapid improvements in automatic speech recognition (ASR), which now performs on par with human listening in many…

The conventional speaker recognition frameworks (e.g., the i-vector and CNN-based approach) have been successfully applied to various tasks when the channel of the enrolment dataset is similar to that of the test dataset. However, in…

Discriminative training techniques define state-of-the-art performance for automatic speech recognition systems. However, they are inherently prone to overfitting, leading to poor generalization performance when using limited training data.…

Interest in deploying Deep Neural Network (DNN) inference on edge devices has resulted in an explosion of the number and types of hardware platforms to use. While the high-level programming interface, such as TensorFlow, can be readily…

Recent research shows end-to-end ASR systems can recognize overlapped speech from multiple speakers. However, all published works have assumed no latency constraints during inference, which does not hold for most voice assistant…

Flow matching offers a robust and stable approach to training diffusion models. However, directly applying flow matching to neural vocoders can result in subpar audio quality. In this work, we present WaveFM, a reparameterized flow matching…

Transformers excel in Natural Language Processing (NLP) due to their prowess in capturing long-term dependencies but suffer from exponential resource consumption with increasing sequence lengths. To address these challenges, we propose MCSD…

Both reverberation and additive noises degrade the speech quality and intelligibility. Weighted prediction error (WPE) method performs well on the dereverberation but with limitations. First, WPE doesn't consider the influence of the…

Swift for TensorFlow is a deep learning platform that scales from mobile devices to clusters of hardware accelerators in data centers. It combines a language-integrated automatic differentiation system and multiple Tensor implementations…

We introduce an algorithmic framework based on tensor networks for computing fluid flows around immersed objects in curvilinear coordinates. We show that the tensor network simulations can be carried out solely using highly compressed…

In this work, we investigate the use of embeddings for speaker-adaptive training of DNNs (DNN-SAT) focusing on a small amount of adaptation data per speaker. DNN-SAT can be viewed as learning a mapping from each embedding to transformation…

An embedding-based speaker adaptive training (SAT) approach is proposed and investigated in this paper for deep neural network acoustic modeling. In this approach, speaker embedding vectors, which are a constant given a particular speaker,…

We propose an end-to-end speech enhancement method with trainable time-frequency~(T-F) transform based on invertible deep neural network~(DNN). The resent development of speech enhancement is brought by using DNN. The ordinary DNN-based…

Latent diffusion models offer an attractive alternative to discrete diffusion for non-autoregressive text generation by operating on continuous text representations and denoising entire sequences in parallel. The major challenge in latent…

While large language models (LLMs) have been applied to automatic speech recognition (ASR), the task of making the model streamable remains a challenge. This paper proposes a novel model architecture, Transducer-Llama, that integrates LLMs…

Recurrent neural networks (RNNs) are powerful tools for sequential modeling, but typically require significant overparameterization and regularization to achieve optimal performance. This leads to difficulties in the deployment of large…

Large language models (LLMs) have demonstrated promising performance in both automatic speech recognition (ASR) and text-to-speech (TTS) systems, gradually becoming the mainstream approach. However, most current approaches address these…

Modern deep learning has enabled unprecedented achievements in various domains. Nonetheless, employment of machine learning for wave function representations is focused on more traditional architectures such as restricted Boltzmann machines…