Related papers: PL-EESR: Perceptual Loss Based END-TO-END Robust S…

One persistent challenge in Speech Emotion Recognition (SER) is the ubiquitous environmental noise, which frequently results in deteriorating SER performance in practice. In this paper, we introduce a Two-level Refinement Network, dubbed…

The performances of automatic speech recognition (ASR) systems degrade drastically under noisy conditions. Explicit distortion modelling (EDM), as a feature compensation step, is able to enhance ASR systems under such conditions by…

In recent Text-to-Speech (TTS) systems, a neural vocoder often generates speech samples by solely conditioning on acoustic features predicted from an acoustic model. However, there are always distortions existing in the predicted acoustic…

Self-supervised learning (SSL) representation for speech has achieved state-of-the-art (SOTA) performance on several downstream tasks. However, there remains room for improvement in speech enhancement (SE) tasks. In this study, we used a…

Target speaker extraction focuses on isolating a specific speaker's voice from an audio mixture containing multiple speakers. To provide information about the target speaker's identity, prior works have utilized clean audio samples as…

Significant progress has been made in spoken question answering (SQA) in recent years. However, many existing methods, including large audio language models, struggle with processing long audio. Follow the success of retrieval augmented…

Semi-supervised learning in automatic speech recognition (ASR) typically relies on pseudo-labeling, which often suffers from confirmation bias and error accumulation due to noisy supervision. To address this limitation, we propose ReHear, a…

Learning robust feature representation from large-scale noisy faces stands out as one of the key challenges in high-performance face recognition. Recent attempts have been made to cope with this challenge by alleviating the intra-class…

The primary objective of speech enhancement is to reduce background noise while preserving the target's speech. A common dilemma occurs when a speaker is confined to a noisy environment and receives a call with high background and…

Edge-based automatic speech recognition (ASR) technologies are increasingly prevalent in the development of intelligent and personalized assistants. However, resource-constrained ASR models face significant challenges in adaptivity,…

Speech utterances recorded under differing conditions exhibit varying degrees of confidence in their embedding estimates, i.e., uncertainty, even if they are extracted using the same neural network. This paper aims to incorporate the…

Target Speaker Extraction (TSE) aims to extract the clean speech of the target speaker in an audio mixture, eliminating irrelevant background noise and speech. While prior work has explored various auxiliary cues including pre-recorded…

Current speaker anonymization methods, especially with self-supervised learning (SSL) models, require massive computational resources when hiding speaker identity. This paper proposes an effective and parameter-efficient speaker…

Despite recent improvements in End-to-End Automatic Speech Recognition (E2E ASR) systems, the performance can degrade due to vocal characteristic mismatches between training and testing data, particularly with limited target speaker…

Automatic speech recognition (ASR) systems typically rely on an external endpointer (EP) model to identify speech boundaries. In this work, we propose a method to jointly train the ASR and EP tasks in a single end-to-end (E2E) multitask…

Deep neural networks have largely demonstrated their ability to perform automated speech recognition (ASR) by extracting meaningful features from input audio frames. Such features, however, may consist not only of information about the…

In this paper, we propose self-supervised speaker representation learning strategies, which comprise of a bootstrap equilibrium speaker representation learning in the front-end and an uncertainty-aware probabilistic speaker embedding…

Target-speaker speech recognition aims to recognize target-speaker speech from noisy environments with background noise and interfering speakers. This work presents a joint framework that combines time-domain target-speaker speech…

Sound Event Detection (SED) is challenging in noisy environments where overlapping sounds obscure target events. Language-queried audio source separation (LASS) aims to isolate the target sound events from a noisy clip. However, this…

This paper presents our system for the MISP-Meeting Challenge Track 2. The primary difficulty lies in the dataset, which contains strong background noise, reverberation, overlapping speech, and diverse meeting topics. To address these…