Related papers: A Mel Spectrogram Enhancement Paradigm Based on CW…
Parallel text-to-speech models have been widely applied for real-time speech synthesis, and they offer more controllability and a much faster synthesis process compared with conventional auto-regressive models. Although parallel models have…
The rapid advancement of audio generation technologies has escalated the risks of malicious deepfake audio across speech, sound, singing voice, and music, threatening multimedia security and trust. While existing countermeasures (CMs)…
Automatic speech quality assessment plays a crucial role in the development of speech synthesis systems, but existing models exhibit significant performance variations across different granularity levels of prediction tasks. This paper…
Designing a speech quality assessment (SQA) system for estimating mean-opinion-score (MOS) of multi-rate speech with varying sampling frequency (16-48 kHz) is a challenging task. The challenge arises due to the limited availability of a…
Neural network-based vocoders have recently demonstrated the powerful ability to synthesize high-quality speech. These models usually generate samples by conditioning on spectral features, such as Mel-spectrogram and fundamental frequency,…
Multi-resolution spectro-temporal features of a speech signal represent how the brain perceives sounds by tuning cortical cells to different spectral and temporal modulations. These features produce a higher dimensional representation of…
Language models (LMs) have shown superior performances in various speech generation tasks recently, demonstrating their powerful ability for semantic context modeling. Given the intrinsic similarity between speech generation and speech…
The synthesis of sound via deep learning methods has recently received much attention. Some problems for deep learning approaches to sound synthesis relate to the amount of data needed to specify an audio signal and the necessity of…
Most state-of-the-art Text-to-Speech systems use the mel-spectrogram as an intermediate representation, to decompose the task into acoustic modelling and waveform generation. A mel-spectrogram is extracted from the waveform by a simple,…
This paper introduces R-MelNet, a two-part autoregressive architecture with a frontend based on the first tier of MelNet and a backend WaveRNN-style audio decoder for neural text-to-speech synthesis. Taking as input a mixed sequence of…
The paper addresses acoustic vehicle detection and speed estimation from single sensor measurements. We predict the vehicle's pass-by instant by minimizing clipped vehicle-to-microphone distance, which is predicted from the mel-spectrogram…
For most of the state-of-the-art speech enhancement techniques, a spectrogram is usually preferred than the respective time-domain raw data since it reveals more compact presentation together with conspicuous temporal information over a…
Most neural network speech enhancement models ignore speech production mathematical models by directly mapping Fourier transform spectrums or waveforms. In this work, we propose a neural source filter network for speech enhancement.…
In this paper we explore the possibility of maximizing the information represented in spectrograms by making the spectrogram basis functions trainable. We experiment with two different tasks, namely keyword spotting (KWS) and automatic…
Accomplishments in the field of artificial intelligence are utilized in the advancement of computing and making of intelligent machines for facilitating mankind and improving user experience. Emotions are rudimentary for people, affecting…
In recent years, Speech Emotion Recognition (SER) has been investigated mainly transforming the speech signal into spectrograms that are then classified using Convolutional Neural Networks pretrained on generic images and fine tuned with…
In recent years, the continuous wavelet transform (CWT) has been employed as a spectral feature extractor for acoustic recognition tasks in conjunction with machine learning and deep learning models. However, applying the CWT to each…
Noise suppression systems generally produce output speech with compromised quality. We propose to utilize the high quality speech generation capability of neural vocoders for noise suppression. We use a neural network to predict clean…
Most of the current deep learning-based approaches for speech enhancement only operate in the spectrogram or waveform domain. Although a cross-domain transformer combining waveform- and spectrogram-domain inputs has been proposed, its…
This paper explores applying the wav2vec2 framework to speaker recognition instead of speech recognition. We study the effectiveness of the pre-trained weights on the speaker recognition task, and how to pool the wav2vec2 output sequence…