相关论文: Non-Linear Speech coding with MLP, RBF and Elman b…

Using neural network based acoustic frontends for improving robustness of streaming automatic speech recognition (ASR) systems is challenging because of the causality constraints and the resulting distortion that the frontend processing…

Neural speech coding is a rapidly developing topic, where state-of-the-art approaches now exhibit superior compression performance than conventional methods. Despite significant progress, existing methods still have limitations in…

In recent years, artificial neural networks and their applications for large data sets have became a crucial part of scientific research. In this work, we implement the Multilayer Perceptron (MLP), which is a class of feedforward artificial…

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…

Inspired by the recent advances in deep learning (DL), this work presents a deep neural network aided decoding algorithm for binary linear codes. Based on the concept of deep unfolding, we design a decoding network by unfolding the…

This paper describes a method for learning low-dimensional approximations of nonlinear dynamical systems, based on neural-network approximations of the underlying Koopman operator. Extended Dynamic Mode Decomposition (EDMD) provides a…

Evaluating the performance of a lecturer has been essential for enhancing teaching quality, improving student learning outcomes, and strengthening the institution's reputation. The absence of such a system brings about lecturer performance…

Level-of-detail (LoD) representation is critical for efficiently modeling and transmitting various types of signals, such as images and 3D shapes. In this work, we propose a novel network architecture that enables LoD signal representation.…

In this paper, we present several adaptation methods for non-native speech recognition. We have tested pronunciation modelling, MLLR and MAP non-native pronunciation adaptation and HMM models retraining on the HIWIRE foreign accented…

A framework for linear-programming (LP) decoding of nonbinary linear codes over rings is developed. This framework facilitates linear-programming based reception for coded modulation systems which use direct modulation mapping of coded…

Speaker identification is a powerful, non-invasive and in-expensive biometric technique. The recognition accuracy, however, deteriorates when noise levels affect a specific band of frequency. In this paper, we present a sub-band based…

In this paper, we propose an improved LPCNet vocoder using a linear prediction (LP)-structured mixture density network (MDN). The recently proposed LPCNet vocoder has successfully achieved high-quality and lightweight speech synthesis…

Connecting audio encoders with large language models (LLMs) allows the LLM to perform various audio understanding tasks, such as automatic speech recognition (ASR) and audio captioning (AC). Most research focuses on training an adapter…

Recently, there has been a growing interest in text-to-speech (TTS) methods that can be trained with minimal supervision by combining two types of discrete speech representations and using two sequence-to-sequence tasks to decouple TTS.…

Saliency prediction can benefit from training that involves scene understanding that may be tangential to the central task; this may include understanding places, spatial layout, objects or involve different datasets and their bias. One can…

Multilingual sentence encoders have seen much success in cross-lingual model transfer for downstream NLP tasks. Yet, we know relatively little about the properties of individual languages or the general patterns of linguistic variation that…

We propose a new shallow fusion (SF) method to exploit an external backward language model (BLM) for end-to-end automatic speech recognition (ASR). The BLM has complementary characteristics with a forward language model (FLM), and the…

In this paper, we propose a speaker verification method by an Attentive Multi-scale Convolutional Recurrent Network (AMCRN). The proposed AMCRN can acquire both local spatial information and global sequential information from the input…

Recent research has demonstrated that training a linear connector between speech foundation encoders and large language models (LLMs) enables this architecture to achieve strong ASR capabilities. Despite the impressive results, it remains…

Learning high-quality text representations is fundamental to a wide range of NLP tasks. While encoder pretraining has traditionally relied on Masked Language Modeling (MLM), recent evidence suggests that decoder models pretrained with…