Related papers: GPU-accelerated Guided Source Separation for Meeti…

Speaker extraction requires a sample speech from the target speaker as the reference. However, enrolling a speaker with a long speech is not practical. We propose a speaker extraction technique, that performs in multiple stages to take full…

Target speech separation refers to isolating target speech from a multi-speaker mixture signal by conditioning on auxiliary information about the target speaker. Different from the mainstream audio-visual approaches which usually require…

Deep generative models have achieved significant progress in speech synthesis to date, while high-fidelity singing voice synthesis is still an open problem for its long continuous pronunciation, rich high-frequency parts, and strong…

Although recent advances in deep learning technology have boosted automatic speech recognition (ASR) performance in the single-talker case, it remains difficult to recognize multi-talker speech in which many voices overlap. One conventional…

In this paper, we introduce the task of language-queried audio source separation (LASS), which aims to separate a target source from an audio mixture based on a natural language query of the target source (e.g., "a man tells a joke followed…

This paper presents a Gaze-Guided Audio-Visual Speech Enhancement (GG-AVSE) framework to address the cocktail party problem. A major challenge in conventional AVSE is identifying the listener's intended speaker in multi-talker environments.…

This work proposes GLM-TTS, a production-level TTS system designed for efficiency, controllability, and high-fidelity speech generation. GLM-TTS follows a two-stage architecture, consisting of a text-to-token autoregressive model and a…

Continuous speech separation (CSS) is a recently proposed framework which aims at separating each speaker from an input mixture signal in a streaming fashion. Hereafter we perform an evaluation study on practical design considerations for a…

In this paper, we propose difficulty-guided sampling (DGS) to bridge the target gap between the distillation objective and the downstream task, therefore improving the performance of dataset distillation. Deep neural networks achieve…

Language-queried audio source separation (LASS) focuses on separating sounds using textual descriptions of the desired sources. Current methods mainly use discriminative approaches, such as time-frequency masking, to separate target sounds…

The goal of this work is to develop a meeting transcription system that can recognize speech even when utterances of different speakers are overlapped. While speech overlaps have been regarded as a major obstacle in accurately transcribing…

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…

Large language models (LLMs) can memorize and reproduce training sequences verbatim -- a tendency that undermines both generalization and privacy. Existing mitigation methods apply interventions uniformly, degrading performance on the…

This paper presents an unsupervised method that trains neural source separation by using only multichannel mixture signals. Conventional neural separation methods require a lot of supervised data to achieve excellent performance. Although…

Speaker independent continuous speech separation (SI-CSS) is a task of converting a continuous audio stream, which may contain overlapping voices of unknown speakers, into a fixed number of continuous signals each of which contains no…

Many applications of single channel source separation (SCSS) including automatic speech recognition (ASR), hearing aids etc. require an estimation of only one source from a mixture of many sources. Treating this special case as a regular…

Spurred by the demand for interpretable models, research on eXplainable AI for language technologies has experienced significant growth, with feature attribution methods emerging as a cornerstone of this progress. While prior work in NLP…

Target Speech Extraction (TSE) traditionally relies on explicit clues about the speaker's identity like enrollment audio, face images, or videos, which may not always be available. In this paper, we propose a text-guided TSE model StyleTSE…

While Transformer has become the de-facto standard for speech, modeling upon the fine-grained frame-level features remains an open challenge of capturing long-distance dependencies and distributing the attention weights. We propose…

Generative target speaker extraction (TSE) methods often produce more natural outputs than predictive models. Recent work based on diffusion or flow matching (FM) typically relies on a small, fixed number of reverse steps with a fixed step…