Related papers: Reducing the Gap Between Pretrained Speech Enhance…

This paper proposes a dual-stage, low complexity, and reconfigurable technique to enhance the speech contaminated by various types of noise sources. Driven by input data and audio contents, the proposed dual-stage speech enhancement…

Today, many state-of-the-art automatic speech recognition (ASR) systems apply all-neural models that map audio to word sequences trained end-to-end along one global optimisation criterion in a fully data driven fashion. These models allow…

Although neural machine translation (NMT) has achieved impressive progress recently, it is usually trained on the clean parallel data set and hence cannot work well when the input sentence is the production of the automatic speech…

Noisy speech separation systems are typically trained on fully-synthetic mixtures, limiting generalization to real-world scenarios. Though training on mixtures of in-domain (thus often noisy) speech is possible, we show that this leads to…

We present a system for non-intrusive prediction of speech quality in noisy and enhanced speech, developed for Track 3 of the VoiceMOS 2024 Challenge. The task required estimating the ITU-T P.835 metrics SIG, BAK, and OVRL without reference…

To realize robust end-to-end Automatic Speech Recognition(E2E ASR) under radio communication condition, we propose a multitask-based method to joint train a Speech Enhancement (SE) module as the front-end and an E2E ASR model as the…

The perceptual task of speech quality assessment (SQA) is a challenging task for machines to do. Objective SQA methods that rely on the availability of the corresponding clean reference have been the primary go-to approaches for SQA.…

Neural network based approaches to speech enhancement have shown to be particularly powerful, being able to leverage a data-driven approach to result in a significant performance gain versus other approaches. Such approaches are reliant on…

Speech emotion recognition (SER) often experiences reduced performance due to background noise. In addition, making a prediction on signals with only background noise could undermine user trust in the system. In this study, we propose a…

Unsupervised single-channel overlapped speech recognition is one of the hardest problems in automatic speech recognition (ASR). Permutation invariant training (PIT) is a state of the art model-based approach, which applies a single neural…

Automatic Speech Recognition (ASR) systems have been examined and shown to exhibit biases toward particular groups of individuals, influenced by factors such as demographic traits, accents, and speech styles. Noise can disproportionately…

Performance of learning based Automatic Speech Recognition (ASR) is susceptible to noise, especially when it is introduced in the testing data while not presented in the training data. This work focuses on a feature enhancement for noise…

Traditional speech separation and speaker diarization approaches rely on prior knowledge of target speakers or a predetermined number of participants in audio signals. To address these limitations, recent advances focus on developing…

Speech enhancement is a demanding task in automated speech processing pipelines, focusing on separating clean speech from noisy channels. Transformer based models have recently bested RNN and CNN models in speech enhancement, however at the…

Noise-robust speaker verification leverages joint learning of speech enhancement (SE) and speaker verification (SV) to improve robustness. However, prevailing approaches rely on implicit noise suppression, which struggles to separate noise…

Feature-mapping with deep neural networks is commonly used for single-channel speech enhancement, in which a feature-mapping network directly transforms the noisy features to the corresponding enhanced ones and is trained to minimize the…

We introduce a new cross-modal fusion technique designed for generative error correction in automatic speech recognition (ASR). Our methodology leverages both acoustic information and external linguistic representations to generate accurate…

Automatic speech recognition systems are part of people's daily lives, embedded in personal assistants and mobile phones, helping as a facilitator for human-machine interaction while allowing access to information in a practically intuitive…

This paper examines the implications of using the Scale-Invariant Signal-to-Distortion Ratio (SI-SDR) as both evaluation and training objective in supervised speech separation, when the training references contain noise, as is the case with…

Although great progresses have been made in automatic speech recognition (ASR), significant performance degradation is still observed when recognizing multi-talker mixed speech. In this paper, we propose and evaluate several architectures…