相关论文: A Deep Learning Approach to Data-driven Parameteri…

In speech synthesis and speech enhancement systems, melspectrograms need to be precise in acoustic representations. However, the generated spectrograms are over-smooth, that could not produce high quality synthesized speech. Inspired by…

Disentangled representation learning in speech processing has lagged behind other domains, largely due to the lack of datasets with annotated generative factors for robust evaluation. To address this, we propose SynSpeech, a novel…

This paper addresses source tracing in synthetic speech-identifying generative systems behind manipulated audio via speaker recognition-inspired pipelines. While prior work focuses on spoofing detection, source tracing lacks robust…

This paper proposes a unified deep speaker embedding framework for modeling speech data with different sampling rates. Considering the narrowband spectrogram as a sub-image of the wideband spectrogram, we tackle the joint modeling problem…

This paper presents a method of decoupled pronunciation and prosody modeling to improve the performance of meta-learning-based multilingual speech synthesis. The baseline meta-learning synthesis method adopts a single text encoder with a…

In this paper, we propose a deep learning (DL)-based parameter enhancement method for a mixed excitation linear prediction (MELP) speech codec in noisy communication environment. Unlike conventional speech enhancement modules that are…

Speaker embedding models that utilize neural networks to map utterances to a space where distances reflect similarity between speakers have driven recent progress in the speaker recognition task. However, there is still a significant…

This paper presents an improved deep embedding learning method based on convolutional neural network (CNN) for text-independent speaker verification. Two improvements are proposed for x-vector embedding learning: (1) Multi-scale convolution…

Semantically meaningful sentence embeddings are important for numerous tasks in natural language processing. To obtain such embeddings, recent studies explored the idea of utilizing synthetically generated data from pretrained language…

Most of the speech processing applications use triangular filters spaced in mel-scale for feature extraction. In this paper, we propose a new data-driven filter design method which optimizes filter parameters from a given speech data.…

The aim of latent variable disentanglement is to infer the multiple informative latent representations that lie behind a data generation process and is a key factor in controllable data generation. In this paper, we propose a deep neural…

The conversion from text to speech relies on the accurate mapping from linguistic to acoustic symbol sequences, for which current practice employs recurrent statistical models like recurrent neural networks. Despite the good performance of…

In this paper, we propose a novel algorithm for speaker diarization using metric learning for graph based clustering. The graph clustering algorithms use an adjacency matrix consisting of similarity scores. These scores are computed between…

In this paper, we develop a deep learning based semantic communication system for speech transmission, named DeepSC-ST. We take the speech recognition and speech synthesis as the transmission tasks of the communication system, respectively.…

Speech signals are inherently complex as they encompass both global acoustic characteristics and local semantic information. However, in the task of target speech extraction, certain elements of global and local semantic information in the…

The integration of pre-trained text-based large language models (LLM) with speech input has enabled instruction-following capabilities for diverse speech tasks. This integration requires the use of a speech encoder, a speech adapter, and an…

A fundamental challenge in neuroscience is to understand what structure in the world is represented in spatially distributed patterns of neural activity from multiple single-trial measurements. This is often accomplished by learning a…

Multi-source localization is an important and challenging technique for multi-talker conversation analysis. This paper proposes a novel supervised learning method using deep neural networks to estimate the direction of arrival (DOA) of all…

Over the last few years, deep learning has grown in popularity for speaker verification, identification, and diarization. Inarguably, a significant part of this success is due to the demonstrated effectiveness of their speaker…

In this work, we introduce metric learning (ML) to enhance the deep embedding learning for text-independent speaker verification (SV). Specifically, the deep speaker embedding network is trained with conventional cross entropy loss and…