Related papers: LauraTSE: Target Speaker Extraction using Auto-Reg…

Target speaker extraction (TSE) aims to extract the speech of a target speaker from mixtures containing multiple competing speakers. Conventional TSE systems predominantly rely on speaker cues, such as pre-enrolled speech, to identify and…

Informed speaker extraction aims to extract a target speech signal from a mixture of sources given prior knowledge about the desired speaker. Recent deep learning-based methods leverage a speaker discriminative model that maps a reference…

Developing a robust speech emotion recognition (SER) system in noisy conditions faces challenges posed by different noise properties. Most previous studies have not considered the impact of human speech noise, thus limiting the application…

This paper addresses end-to-end automatic speech recognition (ASR) for long audio recordings such as lecture and conversational speeches. Most end-to-end ASR models are designed to recognize independent utterances, but contextual…

Most end-to-end (E2E) speech recognition models are composed of encoder and decoder blocks that perform acoustic and language modeling functions. Pretrained large language models (LLMs) have the potential to improve the performance of E2E…

Audio-language models combine audio encoders with large language models to enable multimodal reasoning, but they also introduce new security vulnerabilities. We propose a universal targeted latent space attack, an encoder-level adversarial…

Target speech extraction (TSE) aims to recover a target speaker's voice from a mixture. While recent text-prompted approaches have shown promise, most approaches assume fully overlapped mixtures, limiting insight into behavior across…

Existing Large Language Model (LLM) based autoregressive (AR) text-to-speech (TTS) systems, while achieving state-of-the-art quality, still face critical challenges. The foundation of this LLM-based paradigm is the discretization of the…

The prevailing noise-resistant and reverberation-resistant localization algorithms primarily emphasize separating and providing directional output for each speaker in multi-speaker scenarios, without association with the identity of…

Speech enhancement aims to improve the perceptual quality of the speech signal by suppression of the background noise. However, excessive suppression may lead to speech distortion and speaker information loss, which degrades the performance…

End-to-end (E2E) models have made rapid progress in automatic speech recognition (ASR) and perform competitively relative to conventional models. To further improve the quality, a two-pass model has been proposed to rescore streamed…

Although end-to-end (E2E) trainable automatic speech recognition (ASR) has shown great success by jointly learning acoustic and linguistic information, it still suffers from the effect of domain shifts, thus limiting potential applications.…

Generative autoencoders offer a promising approach for controllable text generation by leveraging their latent sentence representations. However, current models struggle to maintain coherent latent spaces required to perform meaningful text…

Tensor decomposition (TD) is essential for analyzing high-dimensional sparse data, yet its irregular computations and memory-access patterns pose major performance challenges on modern parallel processors. Prior works rely on…

Speech 'in-the-wild' is a handicap for speaker recognition systems due to the variability induced by real-life conditions, such as environmental noise and the emotional state of the speaker. Taking advantage of the principles of…

Recent speech language models rely on encoders that are optimized separately from autoregressive models. Since these encoders are unaware of the downstream objectives, the extracted representations may not be optimal for downstream tasks.…

High-quality speech corpora are essential foundations for most speech applications. However, such speech data are expensive and limited since they are collected in professional recording environments. In this work, we propose an…

Neural text-to-speech (TTS) generally consists of cascaded architecture with separately optimized acoustic model and vocoder, or end-to-end architecture with continuous mel-spectrograms or self-extracted speech frames as the intermediate…

Although discrete speech tokens have exhibited strong potential for language model-based speech generation, their high bitrates and redundant timbre information restrict the development of such models. In this work, we propose LSCodec, a…

Target Sound Extraction (TSE) focuses on the problem of separating sources of interest, indicated by a user's cue, from the input mixture. Most existing solutions operate in an offline fashion and are not suited to the low-latency causal…