相关论文: Identifiability Conditions for Acoustic Feedback C…

One of the most challenging scenarios for smart speakers is multi-talker, when target speech from the desired speaker is mixed with interfering speech from one or more speakers. A smart assistant needs to determine which voice to recognize…

This paper presents an acoustic echo canceler based on a U-Net convolutional neural network for single-talk and double-talk scenarios. U-Net networks have previously been used in the audio processing area for source separation problems…

When multiple people share a single voice assistant, the system conflates their histories: one resident's preferences can leak into another's responses, eroding utility and trust. We call this failure mode persona confusion, and we show it…

Automatic speech recognition (ASR) in multichannel, multi-speaker scenarios remains challenging due to ambient noise, reverberation and overlapping speakers. In this paper, we propose a beamforming approach that processes specific angular…

Large pre-trained language models are increasingly adapted to downstream tasks using parameter-efficient fine-tuning (PEFT), but existing PEFT methods are typically deterministic and unimodal, making them poorly suited for low-resource…

This paper investigates methods to effectively retrieve speaker information from the personalized speaker adapted neural network acoustic models (AMs) in automatic speech recognition (ASR). This problem is especially important in the…

Distortion resulting from acoustic echo suppression (AES) is a common issue in full-duplex communication. To address the distortion problem, a multi-frame minimum variance distortionless response (MFMVDR) filtering technique is proposed.…

Many speaker localization methods can be found in the literature. However, speaker localization under strong reverberation still remains a major challenge in the real-world applications. This paper proposes two algorithms for localizing…

Adaptive filtering algorithms are commonplace in signal processing and have wide-ranging applications from single-channel denoising to multi-channel acoustic echo cancellation and adaptive beamforming. Such algorithms typically operate via…

To build speech processing methods that can handle speech as naturally as humans, researchers have explored multiple ways of building an invertible mapping from speech to an interpretable space. The articulatory space is a promising…

Speech representation and modelling in high-dimensional spaces of acoustic waveforms, or a linear transformation thereof, is investigated with the aim of improving the robustness of automatic speech recognition to additive noise. The…

Connecting audio encoders with large language models (LLMs) allows the LLM to perform various audio understanding tasks, such as automatic speech recognition (ASR) and audio captioning (AC). Most research focuses on training an adapter…

The performance of automatic speech recognition systems under noisy environments still leaves room for improvement. Speech enhancement or feature enhancement techniques for increasing noise robustness of these systems usually add components…

At the end of Moore's law, new computing paradigms are required to prolong the battery life of wearable and IoT smart audio devices. Theoretical analysis and physical validation have shown that analog signal processing (ASP) can be more…

Conventional Multi-modal multi-label emotion recognition (MMER) assumes complete access to visual, textual, and acoustic modalities. However, real-world multi-party settings often violate this assumption, as non-speakers frequently lack…

Generating semantically coherent responses is still a major challenge in dialogue generation. Different from conventional text generation tasks, the mapping between inputs and responses in conversations is more complicated, which highly…

Auditory attention decoding (AAD) is the process of identifying the attended speech in a multi-talker environment using brain signals, typically recorded through electroencephalography (EEG). Over the past decade, AAD has undergone…

Decoding the attended speaker in a multi-speaker environment from electroencephalography (EEG) has attracted growing interest in recent years, with neuro-steered hearing devices as a driver application. Current approaches typically rely on…

Open-vocabulary audio language models (ALMs), like Contrastive Language Audio Pretraining (CLAP), represent a promising new paradigm for audio-text retrieval using natural language queries. In this paper, for the first time, we perform…

Rich sources of variability in natural speech present significant challenges to current data intensive speech recognition technologies. To model both speaker and environment level diversity, this paper proposes a novel Bayesian factorised…