Related papers: APCodec+: A Spectrum-Coding-Based High-Fidelity an…

In this paper, we propose MDCTCodec, an efficient lightweight end-to-end neural audio codec based on the modified discrete cosine transform (MDCT). The encoder takes the MDCT spectrum of audio as input, encoding it into a continuous latent…

This paper presents a method of sequence-to-sequence (seq2seq) voice conversion using non-parallel training data. In this method, disentangled linguistic and speaker representations are extracted from acoustic features, and voice conversion…

In this paper, we proposed AI-based audio coding using MFCC features in an adversarial setting. We combined a conventional encoder with an adversarial learning decoder to better reconstruct the original waveform. Since GAN gives implicit…

This paper presents an adversarial learning method for recognition-synthesis based non-parallel voice conversion. A recognizer is used to transform acoustic features into linguistic representations while a synthesizer recovers output…

We present a method to separate speech signals from noisy environments in the embedding space of a neural audio codec. We introduce a new training procedure that allows our model to produce structured encodings of audio waveforms given by…

Embedding acoustic information into fixed length representations is of interest for a whole range of applications in speech and audio technology. Two novel unsupervised approaches to generate acoustic embeddings by modelling of acoustic…

Neural speech codecs have demonstrated their ability to compress high-quality speech and audio by converting them into discrete token representations. Most existing methods utilize Residual Vector Quantization (RVQ) to encode speech into…

Transformers have become central to recent advances in audio classification. However, training an audio spectrogram transformer, e.g. AST, from scratch can be resource and time-intensive. Furthermore, the complexity of transformers heavily…

In neural audio synthesis, neural vocoders and codecs are models that reconstruct waveforms from acoustic and latent representations, which are essential to the resulting audio quality. While current models are capable of generating…

Recently, cycle-consistent adversarial network (Cycle-GAN) has been successfully applied to voice conversion to a different speaker without parallel data, although in those approaches an individual model is needed for each target speaker.…

Previous DCASE challenges contributed to an increase in the performance of acoustic scene classification systems. State-of-the-art classifiers demand significant processing capabilities and memory which is challenging for…

Voice anonymization masks vocal traits while preserving linguistic content, which may still leak speaker-specific patterns. To assess and strengthen privacy evaluation, we propose a dual-stream attacker that fuses spectral and…

Convolutional layers with 1-D filters are often used as frontend to encode audio signals. Unlike fixed time-frequency representations, they can adapt to the local characteristics of input data. However, 1-D filters on raw audio are hard to…

The recent advancement of end-to-end neural audio codecs enables compressing audio at very low bitrates while reconstructing the output audio with high fidelity. Nonetheless, such improvements often come at the cost of increased model…

We study a novel neural architecture and its training strategies of speaker encoder for speaker recognition without using any identity labels. The speaker encoder is trained to extract a fixed-size speaker embedding from a spoken utterance…

Brain-computer interfaces (BCI) offer numerous human-centered application possibilities, particularly affecting people with neurological disorders. Text or speech decoding from brain activities is a relevant domain that could augment the…

A divide and conquer strategy for enhancement of noisy speeches in adverse environments involving lower levels of SNR is presented in this paper, where the total system of speech enhancement is divided into two separate steps. The first…

This paper proposes a novel framework for unsupervised audio source separation using a deep autoencoder. The characteristics of unknown source signals mixed in the mixed input is automatically by properly configured autoencoders implemented…

Non-parallel many-to-many voice conversion remains an interesting but challenging speech processing task. Recently, AutoVC, a conditional autoencoder based method, achieved excellent conversion results by disentangling the speaker identity…

Neural audio codecs (NACs) provide compact representations that can be leveraged in many downstream applications, in particular large language models. Yet most NACs encode mixtures of multiple sources in an entangled manner, which may…