相关论文: Acoustic Teleportation via Disentangled Neural Aud…

We present a novel source separation model to decompose asingle-channel speech signal into two speech segments belonging to two different speakers. The proposed model is a neural network based on residual blocks, and uses learnt speaker…

Auditory spatial attention detection (ASAD) aims to decode the attended spatial location with EEG in a multiple-speaker setting. ASAD methods are inspired by the brain lateralization of cortical neural responses during the processing of…

We introduce CrossNet, a complex spectral mapping approach to speaker separation and enhancement in reverberant and noisy conditions. The proposed architecture comprises an encoder layer, a global multi-head self-attention module, a…

Diffusion speech enhancement on discrete audio codec features gain immense attention due to their improved speech component reconstruction capability. However, they usually suffer from high inference computational complexity due to multiple…

Personalized speech enhancement (PSE) models can improve the audio quality of teleconferencing systems by adapting to the characteristics of a speaker's voice. However, most existing methods require a separate speaker embedding model to…

This paper proposes StreamCodec, a streamable neural audio codec designed for real-time communication. StreamCodec adopts a fully causal, symmetric encoder-decoder structure and operates in the modified discrete cosine transform (MDCT)…

This paper introduces SoundSculpt, a neural network designed to extract target sound fields from ambisonic recordings. SoundSculpt employs an ambisonic-in-ambisonic-out architecture and is conditioned on both spatial information (e.g.,…

Contrastive speaker embedding assumes that the contrast between the positive and negative pairs of speech segments is attributed to speaker identity only. However, this assumption is incorrect because speech signals contain not only speaker…

Speech emotion recognition (SER) systems often struggle in real-world environments, where ambient noise severely degrades their performance. This paper explores a novel approach that exploits prior knowledge of testing environments to…

With the advent of modern AI architectures, a shift has happened towards end-to-end architectures. This pivot has led to neural architectures being trained without domain-specific biases/knowledge, optimized according to the task. We in…

Human speech can be characterized by different components, including semantic content, speaker identity and prosodic information. Significant progress has been made in disentangling representations for semantic content and speaker identity…

Unsupervised representation learning of speech has been of keen interest in recent years, which is for example evident in the wide interest of the ZeroSpeech challenges. This work presents a new method for learning frame level…

We introduce BANC, a neural binaural audio codec designed for efficient speech compression in single and two-speaker scenarios while preserving the spatial location information of each speaker. Our key contributions are as follows: 1) The…

In acoustic signal processing, the target signals usually carry semantic information, which is encoded in a hierarchal structure of short and long-term contexts. However, the background noise distorts these structures in a nonuniform way.…

While existing speech audio codecs designed for compression exploit limited forms of temporal redundancy and allow for multi-scale representations, they tend to represent all features of audio in the same way. In contrast, generative voice…

Speaker embeddings represent a means to extract representative vectorial representations from a speech signal such that the representation pertains to the speaker identity alone. The embeddings are commonly used to classify and discriminate…

Supervised learning methods have shown effectiveness in estimating spatial acoustic parameters such as time difference of arrival, direct-to-reverberant ratio and reverberation time. However, they still suffer from the simulation-to-reality…

Speaker identification typically involves three stages. First, a front-end speaker embedding model is trained to embed utterance and speaker profiles. Second, a scoring function is applied between a runtime utterance and each speaker…

Anomalous sound detection (ASD) in the wild requires robustness to distribution shifts such as unseen low-SNR input mixtures of machine and noise types. State-of-the-art systems extract embeddings from an adapted audio encoder and detect…

Factorizing speech as disentangled speech representations is vital to achieve highly controllable style transfer in voice conversion (VC). Conventional speech representation learning methods in VC only factorize speech as speaker and…