Related papers: Ultra-Low-Bitrate Mel-Spectrogram-based Neural Spe…

Recently, autoregressive neural vocoders have provided remarkable performance in generating high-fidelity speech and have been able to produce synthetic speech in real-time. However, autoregressive neural vocoders such as WaveFlow are…

High-fidelity general audio compression at ultra-low bitrates is crucial for applications ranging from low-bandwidth communication to generative audio-language modeling. Traditional audio compression methods and contemporary neural codecs…

Dysarthric speech reconstruction (DSR) aims to transform dysarthric speech into normal speech. It still suffers from low speaker similarity and poor prosody naturalness. In this paper, we propose a multi-modal DSR model by leveraging neural…

Mel Frequency Cepstral Coefficients (MFCCs) are the most popularly used speech features in most speech and speaker recognition applications. In this paper, we study the effect of resampling a speech signal on these speech features. We first…

Neural audio codecs and autoencoders have emerged as versatile models for audio compression, transmission, feature-extraction, and latent-space generation. However, a key limitation is that most are trained to maximize reconstruction…

This paper proposes ESTVocoder, a novel excitation-spectral-transformed neural vocoder within the framework of source-filter theory. The ESTVocoder transforms the amplitude and phase spectra of the excitation into the corresponding speech…

We propose a Multi-Stage, Multi-Codebook (MSMC) approach to high-performance neural TTS synthesis. A vector-quantized, variational autoencoder (VQ-VAE) based feature analyzer is used to encode Mel spectrograms of speech training data by…

Audio classification is vital in areas such as speech and music recognition. Feature extraction from the audio signal, such as Mel-Spectrograms and MFCCs, is a critical step in audio classification. These features are transformed into…

Recent studies have shown that neural vocoders based on generative adversarial network (GAN) can generate audios with high quality. While GAN based neural vocoders have shown to be computationally much more efficient than those based on…

FullSubNet is our recently proposed real-time single-channel speech enhancement network that achieves outstanding performance on the Deep Noise Suppression (DNS) Challenge dataset. A number of variants of FullSubNet have been proposed, but…

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…

Current large speech language models are mainly based on semantic tokens from discretization of self-supervised learned representations and acoustic tokens from a neural codec, following a semantic-modeling and acoustic-synthesis paradigm.…

The tokenization of speech with neural audio codec models is a vital part of modern AI pipelines for the generation or understanding of speech, alone or in a multimodal context. Traditionally such tokenization models have concentrated on…

Convolutional recurrent networks (CRN) integrating a convolutional encoder-decoder (CED) structure and a recurrent structure have achieved promising performance for monaural speech enhancement. However, feature representation across…

Modern compression algorithms are often the result of laborious domain-specific research; industry standards such as MP3, JPEG, and AMR-WB took years to develop and were largely hand-designed. We present a deep neural network model which…

While current deep learning (DL)-based beamforming techniques have been proved effective in speech separation, they are often designed to process narrow-band (NB) frequencies independently which results in higher computational costs and…

Decoding speech from brain signals is a challenging research problem. Although existing technologies have made progress in reconstructing the mel spectrograms of auditory stimuli at the word or letter level, there remain core challenges in…

Multiple Description Coding (MDC) is a promising error-resilient source coding method that is particularly suitable for dynamic networks with multiple (yet noisy and unreliable) paths. However, conventional MDC video codecs suffer from…

Decoding continuous speech from intracortical recordings is a central challenge for brain-computer interfaces (BCIs), with transformative potential for individuals with conditions that impair their ability to speak. While recent…

The neural codec language model (CLM) has demonstrated remarkable performance in text-to-speech (TTS) synthesis. However, troubled by ``recency bias", CLM lacks sufficient attention to coarse-grained information at a higher temporal scale,…