Related papers: Complex Frequency Domain Linear Prediction: A Tool…
In the context of wireless communications, we propose a deep learning approach to learn the mapping from the instantaneous state of a frequency selective fading channel to the corresponding frame error probability (FEP) for an arbitrary set…
Conventional continual pretraining (CPT) for large language model (LLM) domain adaptation often suffers from catastrophic forgetting and limited domain capacity. Existing strategies adopt layer expansion, introducing additional trainable…
In multi-speaker speech synthesis, data from a number of speakers usually tend to have great diversity due to the fact that the speakers may differ largely in ages, speaking styles, emotions, and so on. It is important but challenging to…
Modeling the errors of a speech recognizer can help simulate errorful recognized speech data from plain text, which has proven useful for tasks like discriminative language modeling, improving robustness of NLP systems, where limited or…
Nearly all Statistical Parametric Speech Synthesizers today use Mel Cepstral coefficients as the vocal tract parameterization of the speech signal. Mel Cepstral coefficients were never intended to work in a parametric speech synthesis…
Deep neural networks have achieved great success in computer vision, speech recognition and many other areas. The potential of recurrent neural networks especially the Long Short-Term Memory (LSTM) for open set communication signal…
Recently, the application of diffusion probabilistic models has advanced speech enhancement through generative approaches. However, existing diffusion-based methods have focused on the generation process in high-dimensional waveform or…
Most deep learning-based models for speech enhancement have mainly focused on estimating the magnitude of spectrogram while reusing the phase from noisy speech for reconstruction. This is due to the difficulty of estimating the phase of…
This paper provides a fundamental characterization of the discrete ambiguity functions (AFs) of random communication waveforms under arbitrary orthonormal modulation with random constellation symbols, which serve as a key metric for…
Speech-aware LLMs (SLLMs) have recently achieved state-of-the-art ASR performance; however, they still fail to accurately transcribe bias words that appear rarely or never in the training data. Contextual biasing mechanisms are commonly…
Most generative models of audio directly generate samples in one of two domains: time or frequency. While sufficient to express any signal, these representations are inefficient, as they do not utilize existing knowledge of how sound is…
This paper explores silent speech decoding in active brain-computer interface (BCI) systems, which offer more natural and flexible communication than traditional BCI applications. We collected a new silent speech dataset of over 120 hours…
To improve the performance of speaker identification systems, an effective and robust method is proposed to extract speech features, capable of operating in noisy environment. Based on the time-frequency multi-resolution property of wavelet…
We describe a novel index modulation (IM) scheme exploiting a unique feature of the recently proposed affine frequency division multiplexing (AFDM) in doubly-dispersive (DD) channels. Dubbed AFDM chirp-permutation-index modulation (CPIM),…
Speech recognition and speaker identification are important for authentication and verification in security purpose, but they are difficult to achieve. Speaker identification methods can be divided into text-independent and text-dependent.…
This paper proposes a novel multi-carrier modulation framework for high-mobility communication scenarios. Our key idea lies in spreading data symbols across the delay-Doppler (DD) domain through orthogonal chirp-Zak transform (CZT). To…
Continuous speech separation (CSS) aims to separate overlapping voices from a continuous influx of conversational audio containing an unknown number of utterances spoken by an unknown number of speakers. A common application scenario is…
We propose the multi-layered cepstrum (MLC) method to estimate multiple fundamental frequencies (MF0) of a signal under challenging contamination such as high-pass filter noise. Taking the operation of cepstrum (i.e., Fourier transform,…
As an old and widely used tool, it is still possible to find new insights and applications from Fast Fourier Transform (FFT)-based analyses. The FFT is frequently used to generate the Power Spectral Density (PSD) function, by squaring the…
Speech codecs learn compact representations of speech signals to facilitate data transmission. Many recent deep neural network (DNN) based end-to-end speech codecs achieve low bitrates and high perceptual quality at the cost of model…