Related papers: Neural source-filter-based waveform model for stat…
In this paper, we conduct a cross-dataset study on parametric and non-parametric raw-waveform based speaker embeddings through speaker verification experiments. In general, we observe a more significant performance degradation of these…
In speech synthesis, a generative adversarial network (GAN), training a generator (speech synthesizer) and a discriminator in a min-max game, is widely used to improve speech quality. An ensemble of discriminators is commonly used in recent…
Recently proposed self-supervised learning approaches have been successful for pre-training speech representation models. The utility of these learned representations has been observed empirically, but not much has been studied about the…
This work introduces a wavelet neural network to learn a filter-bank specialized to fit non-stationary signals and improve interpretability and performance for digital signal processing. The network uses a wavelet transform as the first…
Conventional automatic speech recognition (ASR) typically performs multi-level pattern recognition tasks that map the acoustic speech waveform into a hierarchy of speech units. But, it is widely known that information loss in the earlier…
This paper proposes a generative pretraining foundation model for high-quality speech restoration tasks. By directly operating on complex-valued short-time Fourier transform coefficients, our model does not rely on any vocoders for…
In this paper, we present a statistical beamforming algorithm as a pre-processing step for robust automatic speech recognition (ASR). By modeling the target speech as a non-stationary Laplacian distribution, a mask-based statistical…
Non-Autoregressive generation is a sequence generation paradigm, which removes the dependency between target tokens. It could efficiently reduce the text generation latency with parallel decoding in place of token-by-token sequential…
Automatic Speech Recognition (ASR) has seen remarkable progress, with models like OpenAI Whisper and NVIDIA Canary achieving state-of-the-art (SOTA) performance in offline transcription. However, these models are not designed for streaming…
Speech enhancement (SE) is usually required as a front end to improve the speech quality in noisy environments, while the enhanced speech might not be optimal for automatic speech recognition (ASR) systems due to speech distortion. On the…
Speech is a rich biometric signal that contains information about the identity, gender and emotional state of the speaker. In this work, we explore its potential to generate face images of a speaker by conditioning a Generative Adversarial…
Recent advances in deep learning for sequential data have given rise to fast and powerful models that produce realistic videos of talking humans. The state of the art in talking face generation focuses mainly on lip-syncing, being…
Large language models show that simple autoregressive training can yield scalable and coherent generation, but extending this paradigm to speech remains challenging due to the entanglement of semantic and acoustic information. Most existing…
In this paper, we propose a dual-stage architecture for bandwidth extension (BWE) increasing the effective sampling rate of speech signals from 8 kHz to 48 kHz. Unlike existing end-to-end deep learning models, our proposed method explicitly…
The recent developments in technology have re-warded us with amazing audio synthesis models like TACOTRON and WAVENETS. On the other side, it poses greater threats such as speech clones and deep fakes, that may go undetected. To tackle…
We propose a learning-based method for the joint design of a transmit and receive filter, the constellation geometry and associated bit labeling, as well as a neural network (NN)-based detector. The method maximizes an achievable…
This paper describes a method for decomposing steady-state instrument data into excitation and formant filter components. The input data, taken from several series of recordings of acoustical instruments is analyzed in the frequency domain,…
The state-of-art methods for acoustic beamforming in multi-channel ASR are based on a neural mask estimator that predicts the presence of speech and noise. These models are trained using a paired corpus of clean and noisy recordings…
We describe a new convolutional framework for waveform evaluation, WEnets, and build a Narrowband Audio Waveform Evaluation Network, or NAWEnet, using this framework. NAWEnet is single-ended (or no-reference) and was trained three separate…
Adversarial waveform generation has been a popular approach as the backend of singing voice conversion (SVC) to generate high-quality singing audio. However, the instability of GAN also leads to other problems, such as pitch jitters and U/V…